Models

442 models

• Aion-2.0

  aion-labs/aion-2.0

  Copy id

  Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....

  ToolsJSON
  by Aion Labs131k tokens$0.872/M in · $1.7441/M out

• Aion-3.0

  aion-labs/aion-3.0

  Copy id

  Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...

  ToolsJSON
  by Aion Labs131k tokens$3.2702/M in · $6.5404/M out

• Aion-3.0-Mini

  aion-labs/aion-3.0-mini

  Copy id

  Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...

  ToolsJSON
  by Aion Labs131k tokens$0.763/M in · $1.5261/M out

• Aion-RP 1.0 (8B)

  aion-labs/aion-rp-llama-3.1-8b

  Copy id

  Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

  by Aion Labs33k tokens$0.872/M in · $1.7441/M out

• Claude 3 Haiku

  anthropic/claude-3-haiku

  Copy id

  Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

  ToolsVision
  by Anthropic200k tokens$0.2725/M in · $1.3626/M out

• Claude Fable 5

  anthropic/claude-fable-5

  Copy id

  Anthropic's most capable model. Adaptive thinking always on. 1M context. Premium for reasoning and agentic workflows.

  ZDRToolsVisionJSON
  by Anthropic1M tokens$10.9006/M in · $54.503/M out

• Claude Fable 5 (batch)

  anthropic/claude-fable-5:batch

  Copy id

  Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

  ToolsVisionJSON
  by Anthropic1M tokens$5.4503/M in · $27.2515/M out

• Claude Haiku 4.5

  anthropic/claude-haiku-4-5

  Copy id

  The fastest and cheapest of the Claude family. Extended thinking. Ideal for high volume, classification, extraction.

  ZDRToolsVisionJSON
  by Anthropic200k tokens$1.0901/M in · $5.4503/M out

• Claude Haiku 4.5

  anthropic/claude-haiku-4.5

  Copy id

  Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

  ToolsVisionJSON
  by Anthropic200k tokens$1.0901/M in · $5.4503/M out

• Claude Haiku 4.5 (batch)

  anthropic/claude-haiku-4.5:batch

  Copy id

  Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

  ToolsVisionJSON
  by Anthropic200k tokens$0.545/M in · $2.7251/M out

• Claude Opus 4

  anthropic/claude-opus-4

  Copy id

  Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

  ToolsVision
  by Anthropic200k tokens$16.3509/M in · $81.7545/M out

• Claude Opus 4.1

  anthropic/claude-opus-4.1

  Copy id

  Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

  ToolsVision
  by Anthropic200k tokens$16.3509/M in · $81.7545/M out

• Claude Opus 4.1 (batch)

  anthropic/claude-opus-4.1:batch

  Copy id

  Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

  ToolsVisionJSON
  by Anthropic200k tokens$8.1754/M in · $40.8772/M out

• Claude Opus 4.5

  anthropic/claude-opus-4.5

  Copy id

  Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

  ToolsVisionJSON
  by Anthropic200k tokens$5.4503/M in · $27.2515/M out

• Claude Opus 4.5 (batch)

  anthropic/claude-opus-4.5:batch

  Copy id

  Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

  ToolsVisionJSON
  by Anthropic200k tokens$2.7251/M in · $13.6257/M out

• Claude Opus 4.6

  anthropic/claude-opus-4.6

  Copy id

  Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

  ToolsVisionJSON
  by Anthropic1M tokens$5.4503/M in · $27.2515/M out

• Claude Opus 4.6 (batch)

  anthropic/claude-opus-4.6:batch

  Copy id

  Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

  ToolsVisionJSON
  by Anthropic1M tokens$2.7251/M in · $13.6257/M out

• Claude Opus 4.7

  anthropic/claude-opus-4.7

  Copy id

  Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

  ToolsVisionJSON
  by Anthropic1M tokens$5.4503/M in · $27.2515/M out

• Claude Opus 4.7 (batch)

  anthropic/claude-opus-4.7:batch

  Copy id

  Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...

  ToolsVisionJSON
  by Anthropic1M tokens$2.7251/M in · $13.6257/M out

• Claude Opus 4.7 (Fast)

  anthropic/claude-opus-4.7-fast

  Copy id

  Fast-mode variant of [Opus 4.7](/anthropic/claude-opus-4.7) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

  ToolsVisionJSON
  by Anthropic1M tokens$32.7018/M in · $163.509/M out

• Claude Opus 4.8

  anthropic/claude-opus-4.8

  Copy id

  Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

  ToolsVisionJSON
  by Anthropic1M tokens$5.4503/M in · $27.2515/M out

• Claude Opus 4.8 (batch)

  anthropic/claude-opus-4.8:batch

  Copy id

  Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

  ToolsVisionJSON
  by Anthropic1M tokens$2.7251/M in · $13.6257/M out

• Claude Opus 4.8 (Fast)

  anthropic/claude-opus-4.8-fast

  Copy id

  Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

  ToolsVisionJSON
  by Anthropic1M tokens$10.9006/M in · $54.503/M out

• Claude Opus 4.8 (legacy)

  anthropic/claude-opus-4-8

  Copy id

  Previous Opus generation. Kept for backward compat with existing clients; Opus 5 is 3x cheaper with more context.

  ZDRToolsVisionJSON
  by Anthropic200k tokens$16.3509/M in · $81.7545/M out

• Claude Opus 5

  anthropic/claude-opus-5

  Copy id

  Opus 5 drops the Opus 4.x pricing to $5/$25 with 1M context and adaptive thinking. The default upgrade in the Opus family.

  ZDRToolsVisionJSON
  by Anthropic1M tokens$5.4503/M in · $27.2515/M out

• Claude Opus 5 (batch)

  anthropic/claude-opus-5:batch

  Copy id

  Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...

  ToolsVisionJSON
  by Anthropic1M tokens$2.7251/M in · $13.6257/M out

• Claude Opus 5 (Fast)

  anthropic/claude-opus-5-fast

  Copy id

  Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

  ToolsVisionJSON
  by Anthropic1M tokens$10.9006/M in · $54.503/M out

• Claude Sonnet 4

  anthropic/claude-sonnet-4

  Copy id

  Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...

  ToolsVision
  by Anthropic1M tokens$3.2702/M in · $16.3509/M out

• Claude Sonnet 4.5

  anthropic/claude-sonnet-4.5

  Copy id

  Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

  ToolsVisionJSON
  by Anthropic1M tokens$3.2702/M in · $16.3509/M out

• Claude Sonnet 4.5 (batch)

  anthropic/claude-sonnet-4.5:batch

  Copy id

  Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

  ToolsVisionJSON
  by Anthropic1M tokens$1.6351/M in · $8.1754/M out

• Claude Sonnet 4.6

  anthropic/claude-sonnet-4.6

  Copy id

  Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

  ToolsVisionJSON
  by Anthropic1M tokens$3.2702/M in · $16.3509/M out

• Claude Sonnet 4.6 (batch)

  anthropic/claude-sonnet-4.6:batch

  Copy id

  Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...

  ToolsVisionJSON
  by Anthropic1M tokens$1.6351/M in · $8.1754/M out

• Claude Sonnet 4.6 (legacy)

  anthropic/claude-sonnet-4-6

  Copy id

  Sonnet 4.6 kept for backward compat. Sonnet 5 has the same price with 1M context and adaptive thinking.

  ZDRToolsVisionJSON
  by Anthropic200k tokens$3.2702/M in · $16.3509/M out

• Claude Sonnet 5

  anthropic/claude-sonnet-5

  Copy id

  Anthropic's sweet spot. Nearly as capable as Opus 5, half the price, same 1M context. Recommended default.

  ZDRToolsVisionJSON
  by Anthropic1M tokens$3.2702/M in · $16.3509/M out

• Claude Sonnet 5 (batch)

  anthropic/claude-sonnet-5:batch

  Copy id

  Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

  ToolsVisionJSON
  by Anthropic1M tokens$1.0901/M in · $5.4503/M out

• Codestral 2508

  mistralai/codestral-2508

  Copy id

  Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

  ToolsJSON
  by Mistral256k tokens$0.327/M in · $0.9811/M out

• Command A

  cohere/command-a

  Copy id

  Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...

  JSON
  by Cohere256k tokens$2.7251/M in · $10.9006/M out

• Command R (08-2024)

  cohere/command-r-08-2024

  Copy id

  command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...

  ToolsJSON
  by Cohere128k tokens$0.1635/M in · $0.654/M out

• Command R+ (08-2024)

  cohere/command-r-plus-08-2024

  Copy id

  command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...

  ToolsJSON
  by Cohere128k tokens$2.7251/M in · $10.9006/M out

• Command R7B (12-2024)

  cohere/command-r7b-12-2024

  Copy id

  Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

  JSON
  by Cohere128k tokens$0.0409/M in · $0.1635/M out

• Cydonia 24B V4.1

  thedrummer/cydonia-24b-v4.1

  Copy id

  Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

  JSON
  by Thedrummer131k tokens$0.327/M in · $0.545/M out

• DeepSeek V3

  deepseek/deepseek-chat

  Copy id

  DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

  ToolsJSON
  by DeepSeek164k tokens$0.2806/M in · $1.1213/M out

• DeepSeek V3 0324

  deepseek/deepseek-chat-v3-0324

  Copy id

  DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

  ToolsJSON
  by DeepSeek164k tokens$0.2725/M in · $1.0901/M out

• DeepSeek V3.1

  deepseek/deepseek-chat-v3.1

  Copy id

  DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

  ToolsJSON
  by DeepSeek164k tokens$0.5995/M in · $1.7986/M out

• DeepSeek V3.1 Terminus

  deepseek/deepseek-v3.1-terminus

  Copy id

  DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

  ToolsJSON
  by DeepSeek164k tokens$0.2943/M in · $1.0901/M out

• DeepSeek V3.2

  deepseek/deepseek-v3.2

  Copy id

  DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

  ToolsJSON
  by DeepSeek164k tokens$0.2834/M in · $0.4142/M out

• DeepSeek V3.2 Exp

  deepseek/deepseek-v3.2-exp

  Copy id

  DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

  ToolsJSON
  by DeepSeek164k tokens$0.2943/M in · $0.4469/M out

• DeepSeek V4 Flash

  deepseek/deepseek-v4-flash

  Copy id

  V4 Flash open-weight, aggressive pricing with 1M context. Cache hit drops input to $0.0028. Replaces DeepSeek Chat V3.

  ToolsVisionJSON
  by DeepSeek1M tokens$0.1526/M in · $0.3052/M out

• DeepSeek V4 Flash 0731

  deepseek/deepseek-v4-flash-0731

  Copy id

  DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

  ToolsJSON
  by DeepSeek1M tokens$0.1526/M in · $0.3052/M out

• DeepSeek V4 Flash Vision Exp

  deepseek/deepseek-v4-flash-vision-exp

  Copy id

  DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

  ToolsVisionJSON
  by DeepSeek1M tokens$0.2398/M in · $0.7194/M out

• DeepSeek V4 Pro

  deepseek/deepseek-v4-pro

  Copy id

  V4 Pro with reasoning + non-reasoning modes. Cache hit $0.003625. Replaces DeepSeek Reasoner R1.

  ToolsVisionJSON
  by DeepSeek1M tokens$0.4742/M in · $0.9484/M out

• DeepSeek V4 Pro 0813

  deepseek/deepseek-v4-pro-0813

  Copy id

  DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

  ToolsJSON
  by DeepSeek1M tokens$1.223/M in · $3.6691/M out

• Dots3-Note Preview (free)

  dots-studio/dots-3-note-preview:free

  Copy id

  Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...

  ToolsVisionJSON
  by Dots Studio512k tokensFree

• ERNIE 4.5 VL 424B A47B

  baidu/ernie-4.5-vl-424b-a47b

  Copy id

  ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...

  Vision
  by Baidu123k tokens$0.4578/M in · $1.3626/M out

• Flux 1.1 Pro

  fal/flux-1.1-pro

  Copy id

  Best open-weight on the market. Quality/price sweet spot. The recommended default.

  by fal.ai—$0.0436 / image

• Flux 1.1 Pro Ultra

  fal/flux-1.1-pro-ultra

  Copy id

  Flux at 4K resolution. For hi-fi marketing and print campaigns.

  by fal.ai—$0.0654 / image

• Fugu Ultra

  sakana/fugu-ultra

  Copy id

  Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

  ToolsVisionJSON
  by Sakana1M tokens$5.4503/M in · $32.7018/M out

• Gemini 2.5 Flash

  google/gemini-2.5-flash

  Copy id

  Flash with hybrid reasoning. Price went up in the July refresh ($0.15/$0.60 → $0.30/$2.50) reflecting the provider change.

  ZDRToolsVisionJSONAudio
  by Google1M tokens$0.327/M in · $2.7251/M out

• Gemini 2.5 Flash (batch)

  google/gemini-2.5-flash:batch

  Copy id

  Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

  ToolsVisionJSONAudio
  by Google—$0.1635 / min

• Gemini 2.5 Flash Image

  google/gemini-2.5-flash-image

  Copy id

  Replaces Imagen 4. Excellent with text embedded in the image (much better than Flux/DALL·E) at the catalog's lowest price.

  by Google—$0.0425 / image

• Gemini 2.5 Flash Lite (batch)

  google/gemini-2.5-flash-lite:batch

  Copy id

  Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

  ToolsVisionJSONAudio
  by Google—$0.0545 / min

• Gemini 2.5 Flash-Lite

  google/gemini-2.5-flash-lite

  Copy id

  Cheapest in the catalog with 1M context. Output at $0.40 / 1M. Alternative when you want to minimize cost.

  ZDRToolsVisionJSONAudio
  by Google1M tokens$0.109/M in · $0.436/M out

• Gemini 2.5 Pro

  google/gemini-2.5-pro

  Copy id

  2M context, multimodal, reasoning. Google updated output pricing ($5 → $10) in the July refresh.

  ZDRToolsVisionJSONAudio
  by Google2M tokens$1.3626/M in · $10.9006/M out

• Gemini 2.5 Pro (batch)

  google/gemini-2.5-pro:batch

  Copy id

  Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

  ToolsVisionJSONAudio
  by Google—$0.6813 / min

• Gemini 2.5 Pro Preview 05-06

  google/gemini-2.5-pro-preview-05-06

  Copy id

  Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

  ToolsVisionJSONAudio
  by Google—$1.3626 / min

• Gemini 2.5 Pro Preview 06-05

  google/gemini-2.5-pro-preview

  Copy id

  Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

  ToolsVisionJSONAudio
  by Google—$1.3626 / min

• Gemini 3 Flash Preview

  google/gemini-3-flash-preview

  Copy id

  Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

  ToolsVisionJSONAudio
  by Google—$0.545 / min

• Gemini 3 Flash Preview (batch)

  google/gemini-3-flash-preview:batch

  Copy id

  Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...

  ToolsVisionJSONAudio
  by Google—$0.2725 / min

• Gemini 3.1 Flash Lite (batch)

  google/gemini-3.1-flash-lite:batch

  Copy id

  Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...

  ToolsVisionJSONAudio
  by Google—$0.1363 / min

• Gemini 3.1 Flash Lite Preview

  google/gemini-3.1-flash-lite-preview

  Copy id

  Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

  ToolsVisionJSONAudio
  by Google—$0.2725 / min

• Gemini 3.1 Flash-Lite

  google/gemini-3.1-flash-lite

  Copy id

  3.1 Flash-Lite. Cheap and fast for classification, extraction, and light chat.

  ZDRToolsVisionJSONAudio
  by Google1M tokens$0.2725/M in · $1.6351/M out

• Gemini 3.1 Pro (preview)

  google/gemini-3.1-pro-preview

  Copy id

  Preview of the 3.1 Pro flagship. 2M context. Price for ≤200k tokens tier; scales ~2x above that.

  ZDRToolsVisionJSONAudio
  by Google2M tokens$2.1801/M in · $13.0807/M out

• Gemini 3.1 Pro Preview (batch)

  google/gemini-3.1-pro-preview:batch

  Copy id

  Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

  ToolsVisionJSONAudio
  by Google—$1.0901 / min

• Gemini 3.1 Pro Preview Custom Tools

  google/gemini-3.1-pro-preview-customtools

  Copy id

  Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...

  ToolsVisionJSONAudio
  by Google—$2.1801 / min

• Gemini 3.5 Flash

  google/gemini-3.5-flash

  Copy id

  Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

  ToolsVisionJSONAudio
  by Google—$1.6351 / min

• Gemini 3.5 Flash (batch)

  google/gemini-3.5-flash:batch

  Copy id

  Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...

  ToolsVisionJSONAudio
  by Google—$0.8175 / min

• Gemini 3.5 Flash Lite (batch)

  google/gemini-3.5-flash-lite:batch

  Copy id

  Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

  ToolsVisionJSONAudio
  by Google—$0.1635 / min

• Gemini 3.5 Flash-Lite

  google/gemini-3.5-flash-lite

  Copy id

  Economic tier of the 3.5 family. Same price as Gemini 2.5 Flash post-refresh, with quality improvements.

  ZDRToolsVisionJSONAudio
  by Google1M tokens$0.327/M in · $2.7251/M out

• Gemini 3.6 Flash

  google/gemini-3.6-flash

  Copy id

  Latest Flash generation. Native multimodal, 1M context, integrated hybrid reasoning.

  ZDRToolsVisionJSONAudio
  by Google1M tokens$1.6351/M in · $8.1754/M out

• Gemini 3.6 Flash (batch)

  google/gemini-3.6-flash:batch

  Copy id

  Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...

  ToolsVisionJSONAudio
  by Google—$0.4088 / min

• Gemini 3.7 Flash

  google/gemini-3.7-flash

  Copy id

  Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

  ToolsVisionJSONAudio
  by Google—$0.4088 / min

• Gemini 3.7 Flash (batch)

  google/gemini-3.7-flash:batch

  Copy id

  Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...

  ToolsVisionJSONAudio
  by Google—$0.2044 / min

• Gemma 2 27B

  google/gemma-2-27b-it

  Copy id

  Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

  JSON
  by Google8k tokens$0.7085/M in · $0.7085/M out

• Gemma 3 12B

  google/gemma-3-12b-it

  Copy id

  Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

  ToolsVisionJSON
  by Google131k tokens$0.0545/M in · $0.1635/M out

• Gemma 3 27B

  google/gemma-3-27b-it

  Copy id

  Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

  ToolsVisionJSON
  by Google262k tokens$0.0872/M in · $0.4905/M out

• Gemma 3 4B

  google/gemma-3-4b-it

  Copy id

  Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

  VisionJSON
  by Google131k tokens$0.0545/M in · $0.109/M out

• Gemma 3n 4B

  google/gemma-3n-e4b-it

  Copy id

  Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

  JSON
  by Google33k tokens$0.0654/M in · $0.1308/M out

• Gemma 4 26B A4B

  google/gemma-4-26b-a4b-it

  Copy id

  Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

  ToolsVisionJSON
  by Google262k tokens$0.0763/M in · $0.3706/M out

• Gemma 4 26B A4B (free)

  google/gemma-4-26b-a4b-it:free

  Copy id

  Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

  ToolsVisionJSON
  by Google262k tokensFree

• Gemma 4 31B

  google/gemma-4-31b-it

  Copy id

  Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

  ToolsVisionJSON
  by Google262k tokens$0.109/M in · $0.3706/M out

• Gemma 4 31B (free)

  google/gemma-4-31b-it:free

  Copy id

  Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

  ToolsVisionJSON
  by Google262k tokensFree

• GLM 4.5

  z-ai/glm-4.5

  Copy id

  GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

  ToolsJSON
  by Zhipu131k tokens$0.654/M in · $2.3981/M out

• GLM 4.5 Air

  z-ai/glm-4.5-air

  Copy id

  GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

  Tools
  by Zhipu131k tokens$0.1417/M in · $0.9266/M out

• GLM 4.5V

  z-ai/glm-4.5v

  Copy id

  GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

  ToolsVisionJSON
  by Zhipu66k tokens$0.654/M in · $1.9621/M out

• GLM 4.6

  z-ai/glm-4.6

  Copy id

  Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

  ToolsJSON
  by Zhipu205k tokens$0.545/M in · $2.1801/M out

• GLM 4.6V

  z-ai/glm-4.6v

  Copy id

  GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

  ToolsVisionJSON
  by Zhipu131k tokens$0.327/M in · $0.9811/M out

• GLM 4.7

  z-ai/glm-4.7

  Copy id

  GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

  ToolsJSON
  by Zhipu205k tokens$0.436/M in · $1.9076/M out

• GLM 4.7 Flash

  z-ai/glm-4.7-flash

  Copy id

  As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...

  ToolsJSON
  by Zhipu203k tokens$0.0654/M in · $0.436/M out

• GLM 5

  z-ai/glm-5

  Copy id

  GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

  ToolsJSON
  by Zhipu205k tokens$0.654/M in · $2.0929/M out

• GLM 5 Turbo

  z-ai/glm-5-turbo

  Copy id

  GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...

  ToolsJSON
  by Zhipu203k tokens$1.3081/M in · $4.3602/M out

• GLM 5.1

  z-ai/glm-5.1

  Copy id

  GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

  ToolsJSON
  by Zhipu205k tokens$1.053/M in · $3.3094/M out

• GLM 5.2

  z-ai/glm-5.2

  Copy id

  GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

  ToolsJSON
  by Zhipu1M tokens$1.053/M in · $3.3094/M out

• GLM 5.2 (batch)

  z-ai/glm-5.2:batch

  Copy id

  GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

  ToolsJSON
  by Zhipu1M tokens$1.5261/M in · $4.7963/M out

• GLM 5.2 (free)

  z-ai/glm-5.2:free

  Copy id

  GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

  ToolsJSON
  by Zhipu256k tokensFree

• GLM 5.3

  z-ai/glm-5.3

  Copy id

  GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

  ToolsJSON
  by Zhipu1M tokens$1.5261/M in · $4.7963/M out

• GLM 5V Turbo

  z-ai/glm-5v-turbo

  Copy id

  GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

  ToolsVisionJSON
  by Zhipu203k tokens$1.3081/M in · $4.3602/M out

• GPT Audio

  openai/gpt-audio

  Copy id

  The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

  ToolsJSONAudio
  by OpenAI128k tokens$2.7251/M in · $10.9006/M out

• GPT Audio Mini

  openai/gpt-audio-mini

  Copy id

  A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...

  ToolsJSONAudio
  by OpenAI128k tokens$0.654/M in · $2.6161/M out

• GPT Chat Latest

  openai/gpt-chat-latest

  Copy id

  GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...

  ToolsVisionJSON
  by OpenAI400k tokens$5.4503/M in · $32.7018/M out

• GPT Image 1 (legacy)

  openai/gpt-image-1

  Copy id

  GPT Image 1 moved to tokenized pricing ($10/$40 per 1M tokens). We show approximate price per 1024×1024 high-quality image. A new 'image-tokens' kind is coming in a future sprint.

  by OpenAI—$0.2071 / image

• GPT-3.5 Turbo

  openai/gpt-3.5-turbo

  Copy id

  GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

  ToolsJSON
  by OpenAI16k tokens$0.545/M in · $1.6351/M out

• GPT-3.5 Turbo (batch)

  openai/gpt-3.5-turbo:batch

  Copy id

  GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

  ToolsJSON
  by OpenAI16k tokens$0.2725/M in · $0.8175/M out

• GPT-3.5 Turbo (older v0613)

  openai/gpt-3.5-turbo-0613

  Copy id

  GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

  ToolsJSON
  by OpenAI4k tokens$1.0901/M in · $2.1801/M out

• GPT-3.5 Turbo 16k

  openai/gpt-3.5-turbo-16k

  Copy id

  This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...

  ToolsJSON
  by OpenAI16k tokens$3.2702/M in · $4.3602/M out

• GPT-3.5 Turbo Instruct

  openai/gpt-3.5-turbo-instruct

  Copy id

  This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.

  JSON
  by OpenAI4k tokens$1.6351/M in · $2.1801/M out

• GPT-4

  openai/gpt-4

  Copy id

  OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...

  ToolsJSON
  by OpenAI8k tokens$32.7018/M in · $65.4036/M out

• GPT-4 Turbo

  openai/gpt-4-turbo

  Copy id

  The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

  ToolsVisionJSON
  by OpenAI128k tokens$10.9006/M in · $32.7018/M out

• GPT-4 Turbo (batch)

  openai/gpt-4-turbo:batch

  Copy id

  The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

  ToolsVisionJSON
  by OpenAI128k tokens$5.4503/M in · $16.3509/M out

• GPT-4 Turbo Preview

  openai/gpt-4-turbo-preview

  Copy id

  The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...

  ToolsJSON
  by OpenAI128k tokens$10.9006/M in · $32.7018/M out

• GPT-4.1

  openai/gpt-4.1

  Copy id

  GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

  ToolsVisionJSON
  by OpenAI1M tokens$2.1801/M in · $8.7205/M out

• GPT-4.1 (batch)

  openai/gpt-4.1:batch

  Copy id

  GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...

  ToolsVisionJSON
  by OpenAI1M tokens$1.0901/M in · $4.3602/M out

• GPT-4.1 Mini (batch)

  openai/gpt-4.1-mini:batch

  Copy id

  GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

  ToolsVisionJSON
  by OpenAI1M tokens$0.218/M in · $0.872/M out

• GPT-4.1 mini (legacy)

  openai/gpt-4.1-mini

  Copy id

  1M context at low price. Replaceable by GPT-5.6 Luna or Gemini 2.5 Flash-Lite.

  ZDRToolsVisionJSON
  by OpenAI1M tokens$0.436/M in · $1.7441/M out

• GPT-4.1 Nano

  openai/gpt-4.1-nano

  Copy id

  For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

  ToolsVisionJSON
  by OpenAI1M tokens$0.109/M in · $0.436/M out

• GPT-4.1 Nano (batch)

  openai/gpt-4.1-nano:batch

  Copy id

  For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

  ToolsVisionJSON
  by OpenAI1M tokens$0.0545/M in · $0.218/M out

• GPT-4o

  openai/gpt-4o

  Copy id

  GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

  ToolsVisionJSON
  by OpenAI128k tokens$2.7251/M in · $10.9006/M out

• GPT-4o (2024-05-13)

  openai/gpt-4o-2024-05-13

  Copy id

  GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

  ToolsVisionJSON
  by OpenAI128k tokens$5.4503/M in · $16.3509/M out

• GPT-4o (2024-08-06)

  openai/gpt-4o-2024-08-06

  Copy id

  The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...

  ToolsVisionJSON
  by OpenAI128k tokens$2.7251/M in · $10.9006/M out

• GPT-4o (2024-11-20)

  openai/gpt-4o-2024-11-20

  Copy id

  The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...

  ToolsVisionJSON
  by OpenAI128k tokens$2.7251/M in · $10.9006/M out

• GPT-4o (batch)

  openai/gpt-4o:batch

  Copy id

  GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

  ToolsVisionJSON
  by OpenAI128k tokens$1.3626/M in · $5.4503/M out

• GPT-4o mini TTS

  openai/gpt-4o-mini-tts

  Copy id

  Latest generation: prompt-controlled voice (instructions for tone, emotion, pace). 7 voices.

  by OpenAI—$13.0807 / 1M chars

• GPT-4o-mini

  openai/gpt-4o-mini

  Copy id

  GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

  ToolsVisionJSON
  by OpenAI128k tokens$0.1635/M in · $0.654/M out

• GPT-4o-mini (2024-07-18)

  openai/gpt-4o-mini-2024-07-18

  Copy id

  GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

  ToolsVisionJSON
  by OpenAI128k tokens$0.1635/M in · $0.654/M out

• GPT-4o-mini (batch)

  openai/gpt-4o-mini:batch

  Copy id

  GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

  ToolsVisionJSON
  by OpenAI128k tokens$0.0818/M in · $0.327/M out

• GPT-5 (batch)

  openai/gpt-5:batch

  Copy id

  GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

  ToolsVisionJSON
  by OpenAI400k tokens$0.6813/M in · $5.4503/M out

• GPT-5 (legacy)

  openai/gpt-5

  Copy id

  Original GPT-5. Kept for backward compat; recommend migrating to 5.1 or 5.4-mini depending on use case.

  ZDRToolsVisionJSON
  by OpenAI400k tokens$1.3626/M in · $10.9006/M out

• GPT-5 Codex (batch)

  openai/gpt-5-codex:batch

  Copy id

  GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

  ToolsVisionJSON
  by OpenAI400k tokens$0.6813/M in · $5.4503/M out

• GPT-5 Image

  openai/gpt-5-image

  Copy id

  GPT-5 Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

  VisionJSON
  by OpenAI400k tokens$10.9006/M in · $10.9006/M out

• GPT-5 Image Mini

  openai/gpt-5-image-mini

  Copy id

  GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by GPT-5 Mini, with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

  VisionJSON
  by OpenAI400k tokens$2.7251/M in · $2.1801/M out

• GPT-5 Mini

  openai/gpt-5-mini

  Copy id

  GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

  ToolsVisionJSON
  by OpenAI400k tokens$0.2725/M in · $2.1801/M out

• GPT-5 Mini (batch)

  openai/gpt-5-mini:batch

  Copy id

  GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

  ToolsVisionJSON
  by OpenAI400k tokens$0.1363/M in · $1.0901/M out

• GPT-5 Nano

  openai/gpt-5-nano

  Copy id

  GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

  ToolsVisionJSON
  by OpenAI400k tokens$0.0545/M in · $0.436/M out

• GPT-5 Nano (batch)

  openai/gpt-5-nano:batch

  Copy id

  GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

  ToolsVisionJSON
  by OpenAI400k tokens$0.0273/M in · $0.218/M out

• GPT-5 Pro

  openai/gpt-5-pro

  Copy id

  GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...

  ToolsVisionJSON
  by OpenAI400k tokens$16.3509/M in · $130.8072/M out

• GPT-5 Pro (batch)

  openai/gpt-5-pro:batch

  Copy id

  GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...

  ToolsVisionJSON
  by OpenAI400k tokens$8.1754/M in · $65.4036/M out

• GPT-5.1

  openai/gpt-5.1

  Copy id

  Refinement of GPT-5 at the same price. Better instruction following and tool handling.

  ZDRToolsVisionJSON
  by OpenAI400k tokens$1.3626/M in · $10.9006/M out

• GPT-5.1 (batch)

  openai/gpt-5.1:batch

  Copy id

  GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

  ToolsVisionJSON
  by OpenAI400k tokens$0.6813/M in · $5.4503/M out

• GPT-5.1-Codex

  openai/gpt-5.1-codex

  Copy id

  GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

  ToolsVisionJSON
  by OpenAI400k tokens$1.3626/M in · $10.9006/M out

• GPT-5.1-Codex-Max

  openai/gpt-5.1-codex-max

  Copy id

  GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...

  ToolsVisionJSON
  by OpenAI400k tokens$1.3626/M in · $10.9006/M out

• GPT-5.1-Codex-Mini

  openai/gpt-5.1-codex-mini

  Copy id

  GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

  ToolsVisionJSON
  by OpenAI400k tokens$0.2725/M in · $2.1801/M out

• GPT-5.2

  openai/gpt-5.2

  Copy id

  GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

  ToolsVisionJSON
  by OpenAI400k tokens$1.9076/M in · $15.2608/M out

• GPT-5.2 (batch)

  openai/gpt-5.2:batch

  Copy id

  GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...

  ToolsVisionJSON
  by OpenAI400k tokens$0.9538/M in · $7.6304/M out

• GPT-5.2 Chat

  openai/gpt-5.2-chat

  Copy id

  GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...

  ToolsVisionJSON
  by OpenAI128k tokens$1.9076/M in · $15.2608/M out

• GPT-5.2 Pro

  openai/gpt-5.2-pro

  Copy id

  GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

  ToolsVisionJSON
  by OpenAI400k tokens$22.8913/M in · $183.13/M out

• GPT-5.2 Pro (batch)

  openai/gpt-5.2-pro:batch

  Copy id

  GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...

  ToolsVisionJSON
  by OpenAI400k tokens$11.4456/M in · $91.565/M out

• GPT-5.2-Codex

  openai/gpt-5.2-codex

  Copy id

  GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....

  ToolsVisionJSON
  by OpenAI400k tokens$1.9076/M in · $15.2608/M out

• GPT-5.3-Codex

  openai/gpt-5.3-codex

  Copy id

  GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

  ToolsVisionJSON
  by OpenAI400k tokens$1.9076/M in · $15.2608/M out

• GPT-5.4

  openai/gpt-5.4

  Copy id

  GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

  ToolsVisionJSON
  by OpenAI1M tokens$2.7251/M in · $16.3509/M out

• GPT-5.4 (batch)

  openai/gpt-5.4:batch

  Copy id

  GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

  ToolsVisionJSON
  by OpenAI1M tokens$1.3626/M in · $8.1754/M out

• GPT-5.4 Image 2

  openai/gpt-5.4-image-2

  Copy id

  GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

  VisionJSON
  by OpenAI272k tokens$8.7205/M in · $16.3509/M out

• GPT-5.4 mini

  openai/gpt-5.4-mini

  Copy id

  Economic variant of 5.4. Sub-dollar per 1M input tokens, good balance for chatbots.

  ZDRToolsVisionJSON
  by OpenAI272k tokens$0.8175/M in · $4.9053/M out

• GPT-5.4 Mini (batch)

  openai/gpt-5.4-mini:batch

  Copy id

  GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

  ToolsVisionJSON
  by OpenAI400k tokens$0.4088/M in · $2.4526/M out

• GPT-5.4 Nano

  openai/gpt-5.4-nano

  Copy id

  GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

  ToolsVisionJSON
  by OpenAI400k tokens$0.218/M in · $1.3626/M out

• GPT-5.4 Nano (batch)

  openai/gpt-5.4-nano:batch

  Copy id

  GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

  ToolsVisionJSON
  by OpenAI400k tokens$0.109/M in · $0.6813/M out

• GPT-5.4 Pro

  openai/gpt-5.4-pro

  Copy id

  GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

  ToolsVisionJSON
  by OpenAI1M tokens$32.7018/M in · $196.2107/M out

• GPT-5.4 Pro (batch)

  openai/gpt-5.4-pro:batch

  Copy id

  GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

  ToolsVisionJSON
  by OpenAI1M tokens$16.3509/M in · $98.1054/M out

• GPT-5.5

  openai/gpt-5.5

  Copy id

  5.5 generation with caching. 272k context. Same price tier as 5.6 Sol.

  ZDRToolsVisionJSON
  by OpenAI272k tokens$5.4503/M in · $32.7018/M out

• GPT-5.5 (batch)

  openai/gpt-5.5:batch

  Copy id

  GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...

  ToolsVisionJSON
  by OpenAI1M tokens$2.7251/M in · $16.3509/M out

• GPT-5.5 Pro

  openai/gpt-5.5-pro

  Copy id

  GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...

  ToolsVisionJSON
  by OpenAI1M tokens$32.7018/M in · $196.2107/M out

• GPT-5.5 Pro (batch)

  openai/gpt-5.5-pro:batch

  Copy id

  GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...

  ToolsVisionJSON
  by OpenAI1M tokens$16.3509/M in · $98.1054/M out

• GPT-5.6 Luna

  openai/gpt-5.6-luna

  Copy id

  Most efficient in 5.6. $0.20/$1.20 per 1M — very competitive for high volume.

  ZDRToolsVisionJSON
  by OpenAI400k tokens$0.218/M in · $1.3081/M out

• GPT-5.6 Luna (batch)

  openai/gpt-5.6-luna:batch

  Copy id

  GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

  ToolsVisionJSON
  by OpenAI1M tokens$0.109/M in · $0.654/M out

• GPT-5.6 Luna Pro

  openai/gpt-5.6-luna-pro

  Copy id

  GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

  ToolsVisionJSON
  by OpenAI1M tokens$0.218/M in · $1.3081/M out

• GPT-5.6 Luna Pro (batch)

  openai/gpt-5.6-luna-pro:batch

  Copy id

  GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

  ToolsVisionJSON
  by OpenAI1M tokens$0.109/M in · $0.654/M out

• GPT-5.6 Sol

  openai/gpt-5.6-sol

  Copy id

  Flagship of the 5.6 family. Three tiers Sol/Terra/Luna at different price-capability points.

  ZDRToolsVisionJSON
  by OpenAI400k tokens$5.4503/M in · $32.7018/M out

• GPT-5.6 Sol (batch)

  openai/gpt-5.6-sol:batch

  Copy id

  GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...

  ToolsVisionJSON
  by OpenAI1M tokens$1.0901/M in · $5.4503/M out

• GPT-5.6 Sol Pro

  openai/gpt-5.6-sol-pro

  Copy id

  GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

  ToolsVisionJSON
  by OpenAI1M tokens$2.1801/M in · $10.9006/M out

• GPT-5.6 Sol Pro (batch)

  openai/gpt-5.6-sol-pro:batch

  Copy id

  GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

  ToolsVisionJSON
  by OpenAI1M tokens$1.0901/M in · $5.4503/M out

• GPT-5.6 Terra

  openai/gpt-5.6-terra

  Copy id

  Mid-tier of 5.6. Price/quality balance for production tasks.

  ZDRToolsVisionJSON
  by OpenAI400k tokens$2.1801/M in · $13.0807/M out

• GPT-5.6 Terra (batch)

  openai/gpt-5.6-terra:batch

  Copy id

  GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

  ToolsVisionJSON
  by OpenAI1M tokens$1.0901/M in · $6.5404/M out

• GPT-5.6 Terra Pro

  openai/gpt-5.6-terra-pro

  Copy id

  GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

  ToolsVisionJSON
  by OpenAI1M tokens$2.1801/M in · $13.0807/M out

• GPT-5.6 Terra Pro (batch)

  openai/gpt-5.6-terra-pro:batch

  Copy id

  GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

  ToolsVisionJSON
  by OpenAI1M tokens$1.0901/M in · $6.5404/M out

• gpt-oss-120b

  openai/gpt-oss-120b

  Copy id

  gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

  ToolsJSON
  by OpenAI131k tokens$0.0403/M in · $0.1853/M out

• gpt-oss-20b

  openai/gpt-oss-20b

  Copy id

  gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

  ToolsJSON
  by OpenAI131k tokens$0.0327/M in · $0.1417/M out

• gpt-oss-safeguard-20b

  openai/gpt-oss-safeguard-20b

  Copy id

  gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

  ToolsJSON
  by OpenAI131k tokens$0.0818/M in · $0.327/M out

• Granite 4.0 Micro

  ibm-granite/granite-4.0-h-micro

  Copy id

  Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...

  JSON
  by IBM131k tokens$0.0185/M in · $0.1221/M out

• Granite 4.1 8B

  ibm-granite/granite-4.1-8b

  Copy id

  Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

  ToolsJSON
  by IBM131k tokens$0.0545/M in · $0.109/M out

• Grok 4.20

  x-ai/grok-4.20

  Copy id

  Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

  ToolsVisionJSON
  by xAI2M tokens$1.3626/M in · $2.7251/M out

• Grok 4.20 (reasoning)

  xai/grok-4.20-reasoning

  Copy id

  Reasoning-mode of 4.20. Same price tier as 4.3 with integrated Chain of Thought.

  ToolsVisionJSON
  by xAI1M tokens$1.3626/M in · $2.7251/M out

• Grok 4.20 Multi-Agent

  x-ai/grok-4.20-multi-agent

  Copy id

  Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...

  VisionJSON
  by xAI2M tokens$1.3626/M in · $2.7251/M out

• Grok 4.3

  xai/grok-4.3

  Copy id

  1M context and aggressive output pricing ($2.50). Sweet spot of the Grok 4.x family.

  ToolsVisionJSON
  by xAI1M tokens$1.3626/M in · $2.7251/M out

• Grok 4.3

  x-ai/grok-4.3

  Copy id

  Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...

  ToolsVisionJSON
  by xAI1M tokens$1.3626/M in · $2.7251/M out

• Grok 4.5

  xai/grok-4.5

  Copy id

  xAI's flagship. 500k context. Real-time X (Twitter) access. Price doubles above 200k tokens.

  ToolsVisionJSON
  by xAI500k tokens$2.1801/M in · $6.5404/M out

• Grok 4.5

  x-ai/grok-4.5

  Copy id

  Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

  ToolsVisionJSON
  by xAI500k tokens$2.1801/M in · $6.5404/M out

• Grok 4.6

  x-ai/grok-4.6

  Copy id

  Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

  ToolsVisionJSON
  by xAI500k tokens$2.1801/M in · $6.5404/M out

• Grok Build 0.1

  xai/grok-build

  Copy id

  Grok specialized for code workflows and agentic tasks. 256k context, low price for fast iteration.

  ToolsVisionJSON
  by xAI256k tokens$1.0901/M in · $2.1801/M out

• Grok Build 0.1

  x-ai/grok-build-0.1

  Copy id

  Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

  ToolsVisionJSON
  by xAI256k tokens$1.0901/M in · $2.1801/M out

• Grok Imagine Video 1.5

  xai/grok-imagine-video-1.5

  Copy id

  xAI video. Photorealistic style, lenient content policy like Grok.

  by xAI—$0.0872 / s

• Hailuo 02 (MiniMax)

  fal/hailuo-02

  Copy id

  The cheapest in the catalog. Default 6 seconds instead of 5.

  by fal.ai—$0.0436 / s

• Hermes 3 405B Instruct

  nousresearch/hermes-3-llama-3.1-405b

  Copy id

  Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

  JSON
  by Nous Research131k tokens$1.0901/M in · $1.0901/M out

• Hermes 3 70B Instruct

  nousresearch/hermes-3-llama-3.1-70b

  Copy id

  Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

  JSON
  by Nous Research131k tokens$0.763/M in · $0.763/M out

• Hermes 4 405B

  nousresearch/hermes-4-405b

  Copy id

  Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

  JSON
  by Nous Research131k tokens$1.0901/M in · $3.2702/M out

• Hermes 4 70B

  nousresearch/hermes-4-70b

  Copy id

  Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

  JSON
  by Nous Research131k tokens$0.1417/M in · $0.436/M out

• Hunyuan A13B Instruct

  tencent/hunyuan-a13b-instruct

  Copy id

  Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

  JSON
  by Tencent131k tokens$0.1526/M in · $0.6213/M out

• Hy-MT2-1.8B

  tencent/hy-mt2-1.8b

  Copy id

  Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

  by Tencent8k tokens$0.048/M in · $0.1929/M out

• Hy-MT2-30B-A3B

  tencent/hy-mt2-30b-a3b

  Copy id

  Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

  JSON
  by Tencent8k tokens$0.0807/M in · $0.3216/M out

• Hy-MT2-7B

  tencent/hy-mt2-7b

  Copy id

  Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

  JSON
  by Tencent8k tokens$0.0807/M in · $0.3216/M out

• Hy3

  tencent/hy3

  Copy id

  Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

  ToolsJSON
  by Tencent262k tokens$0.1439/M in · $0.5756/M out

• Hy3 preview

  tencent/hy3-preview

  Copy id

  Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

  Tools
  by Tencent262k tokens$0.1962/M in · $0.654/M out

• Ideogram V2

  fal/ideogram-v2

  Copy id

  Best for professional typography. If you need legible, beautiful text, go here.

  by fal.ai—$0.0872 / image

• Inkling

  thinkingmachines/inkling

  Copy id

  Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

  ToolsVisionJSONAudio
  by Thinkingmachines—$1.0901 / min

• Inkling (batch)

  thinkingmachines/inkling:batch

  Copy id

  Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

  ToolsVisionAudio
  by Thinkingmachines—$1.0901 / min

• Inkling (free)

  thinkingmachines/inkling:free

  Copy id

  Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...

  ToolsVisionAudio
  by Thinkingmachines—$0.00 / min

• Inkling Small

  thinkingmachines/inkling-small

  Copy id

  Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

  ToolsVisionAudio
  by Thinkingmachines—$0.4905 / min

• Inkling Small (free)

  thinkingmachines/inkling-small:free

  Copy id

  Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

  ToolsVisionAudio
  by Thinkingmachines—$0.00 / min

• KAT-Coder-Air V2.5

  kwaipilot/kat-coder-air-v2.5

  Copy id

  KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...

  ToolsJSON
  by Kwaipilot256k tokens$0.1635/M in · $0.654/M out

• KAT-Coder-Pro V2

  kwaipilot/kat-coder-pro-v2

  Copy id

  KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...

  ToolsJSON
  by Kwaipilot262k tokens$0.327/M in · $1.3081/M out

• KAT-Coder-Pro V2.5

  kwaipilot/kat-coder-pro-v2.5

  Copy id

  KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...

  ToolsJSON
  by Kwaipilot256k tokens$0.8066/M in · $3.2266/M out

• Kimi K2 0711

  moonshotai/kimi-k2

  Copy id

  Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

  Tools
  by Moonshot131k tokens$0.6213/M in · $2.5071/M out

• Kimi K2 0905

  moonshotai/kimi-k2-0905

  Copy id

  Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

  ToolsJSON
  by Moonshot262k tokens$0.654/M in · $2.7251/M out

• Kimi K2 Thinking

  moonshotai/kimi-k2-thinking

  Copy id

  Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

  ToolsJSON
  by Moonshot262k tokens$0.654/M in · $2.7251/M out

• Kimi K2.5

  moonshotai/kimi-k2.5

  Copy id

  Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

  ToolsVisionJSON
  by Moonshot262k tokens$0.4905/M in · $2.4526/M out

• Kimi K2.6

  moonshotai/kimi-k2.6

  Copy id

  Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

  ToolsVisionJSON
  by Moonshot262k tokens$1.0356/M in · $4.3602/M out

• Kimi K2.7 Code

  moonshot/kimi-k2.7-code

  Copy id

  Code-focused. 262k context. Cache hit input at $0.19. Price rose vs K2.5 but quality improved proportionally.

  ToolsVision
  by Moonshot (Kimi)262k tokens$1.0356/M in · $4.3602/M out

• Kimi K2.7 Code

  moonshotai/kimi-k2.7-code

  Copy id

  MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

  ToolsVisionJSON
  by Moonshot262k tokens$0.7303/M in · $3.7062/M out

• Kimi K2.7 Code · Highspeed

  moonshot/kimi-k2.7-code-highspeed

  Copy id

  Low-latency variant. Same input, output 2x more expensive for compute priority. For chatbots with high concurrency.

  ToolsVision
  by Moonshot (Kimi)262k tokens$1.0356/M in · $8.7205/M out

• Kimi K2.7 Code (batch)

  moonshotai/kimi-k2.7-code:batch

  Copy id

  MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

  ToolsVisionJSON
  by Moonshot262k tokens$1.0356/M in · $4.3602/M out

• Kimi K3

  moonshot/kimi-k3

  Copy id

  Moonshot's flagship: 2.8T params, 1M context, cache hit drops input to $0.30. Alternative to Sonnet 5.

  ToolsVision
  by Moonshot (Kimi)1M tokens$3.2702/M in · $16.3509/M out

• Kimi K3

  moonshotai/kimi-k3

  Copy id

  Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

  ToolsVisionJSON
  by Moonshot1M tokens$3.2702/M in · $16.3509/M out

• Kling v3 Pro

  fal/kling-3-pro

  Copy id

  Kling v3 Pro replaces Kling 2. Better coherence and camera control.

  by fal.ai—$0.2398 / s

• Laguna S 2.1

  poolside/laguna-s-2.1

  Copy id

  Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...

  Tools
  by Poolside1M tokens$0.0981/M in · $0.1962/M out

• Laguna S 2.1 (free)

  poolside/laguna-s-2.1:free

  Copy id

  Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...

  Tools
  by Poolside262k tokensFree

• Laguna XS 2.1

  poolside/laguna-xs-2.1

  Copy id

  Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

  Tools
  by Poolside262k tokens$0.0654/M in · $0.1308/M out

• Laguna XS 2.1 (free)

  poolside/laguna-xs-2.1:free

  Copy id

  Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...

  Tools
  by Poolside262k tokensFree

• LFM2.5-2.6B (free)

  liquid/lfm-2.5-2.6b:free

  Copy id

  LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

  ToolsJSON
  by Liquid66k tokensFree

• Ling-2.6-1T

  inclusionai/ling-2.6-1t

  Copy id

  Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...

  ToolsJSON
  by Inclusionai262k tokens$0.0818/M in · $0.6813/M out

• Ling-2.6-flash

  inclusionai/ling-2.6-flash

  Copy id

  Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....

  ToolsJSON
  by Inclusionai262k tokens$0.0109/M in · $0.0327/M out

• Ling-3.0-flash

  inclusionai/ling-3.0-flash

  Copy id

  *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

  ToolsJSON
  by Inclusionai262k tokens$0.0229/M in · $0.0687/M out

• Llama 3 8B Lunaris

  sao10k/l3-lunaris-8b

  Copy id

  Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

  JSON
  by Sao10k8k tokens$0.0436/M in · $0.0545/M out

• Llama 3.1 70B Instruct

  meta-llama/llama-3.1-70b-instruct

  Copy id

  Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

  ToolsJSON
  by Meta131k tokens$0.436/M in · $0.436/M out

• Llama 3.1 8B Instruct

  meta-llama/llama-3.1-8b-instruct

  Copy id

  Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

  ToolsJSON
  by Meta131k tokens$0.0545/M in · $0.0872/M out

• Llama 3.1 Euryale 70B v2.2

  sao10k/l3.1-euryale-70b

  Copy id

  Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).

  ToolsJSON
  by Sao10k131k tokens$0.9266/M in · $0.9266/M out

• Llama 3.2 1B Instruct

  meta-llama/llama-3.2-1b-instruct

  Copy id

  Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

  by Meta60k tokens$0.0294/M in · $0.2191/M out

• Llama 3.2 3B Instruct

  meta-llama/llama-3.2-3b-instruct

  Copy id

  Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

  JSON
  by Meta131k tokens$0.0545/M in · $0.3597/M out

• Llama 3.3 70B Instruct

  meta/llama-3.3-70b-instruct

  Copy id

  Meta Llama 3.3 70B via Meta Llama API (first-party). General chat and instruct.

  ToolsVisionJSON
  by Meta128k tokens$0.6431/M in · $0.8611/M out

• Llama 3.3 70B Instruct

  meta-llama/llama-3.3-70b-instruct

  Copy id

  The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

  ToolsJSON
  by Meta131k tokens$0.109/M in · $0.3488/M out

• Llama 3.3 Euryale 70B

  sao10k/l3.3-euryale-70b

  Copy id

  Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).

  JSON
  by Sao10k131k tokens$0.7085/M in · $0.8175/M out

• Llama 4 Maverick

  meta-llama/llama-4-maverick

  Copy id

  Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

  ToolsVisionJSON
  by Meta1M tokens$0.218/M in · $0.872/M out

• Llama 4 Scout

  meta-llama/llama-4-scout

  Copy id

  Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

  ToolsVisionJSON
  by Meta1M tokens$0.109/M in · $0.327/M out

• Llama Guard 4 12B

  meta-llama/llama-guard-4-12b

  Copy id

  Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

  VisionJSON
  by Meta1M tokens$0.1962/M in · $0.1962/M out

• LongCat 2.0

  meituan/longcat-2.0

  Copy id

  LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...

  Tools
  by Meituan1M tokens$0.327/M in · $1.3081/M out

• Luma Ray 2

  fal/luma-ray-2

  Copy id

  Cinematic quality. Frame-to-frame coherence better than Kling and Hailuo.

  by fal.ai—$0.218 / s

• Lyria 3 Clip Preview

  google/lyria-3-clip-preview

  Copy id

  30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...

  VisionJSON
  by Google—$0.00 / 1M chars

• Lyria 3 Pro Preview

  google/lyria-3-pro-preview

  Copy id

  Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...

  VisionJSON
  by Google—$0.00 / 1M chars

• Magnum v4 72B

  anthracite-org/magnum-v4-72b

  Copy id

  This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet( and Opus( The model is fine-tuned on top of Qwen2.5 72B.

  JSON
  by Anthracite Org33k tokens$3.2702/M in · $5.4503/M out

• Mercury 2

  inception/mercury-2

  Copy id

  Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...

  ToolsJSON
  by Inception128k tokens$0.2725/M in · $0.8175/M out

• MiMo-V2.5

  xiaomi/mimo-v2.5

  Copy id

  MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

  ToolsVisionJSONAudio
  by Xiaomi—$0.1526 / min

• MiMo-V2.5-Pro

  xiaomi/mimo-v2.5-pro

  Copy id

  MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

  ToolsJSON
  by Xiaomi1M tokens$0.4742/M in · $0.9484/M out

• MiniMax M1

  minimax/minimax-m1

  Copy id

  MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

  Tools
  by MiniMax1M tokens$0.5995/M in · $2.3981/M out

• MiniMax M2

  minimax/minimax-m2

  Copy id

  MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

  ToolsJSON
  by MiniMax205k tokens$0.278/M in · $1.1119/M out

• MiniMax M2-her

  minimax/minimax-m2-her

  Copy id

  MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...

  by MiniMax66k tokens$0.327/M in · $1.3081/M out

• MiniMax M2.1

  minimax/minimax-m2.1

  Copy id

  MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...

  ToolsJSON
  by MiniMax205k tokens$0.327/M in · $1.3081/M out

• MiniMax M2.5

  minimax/minimax-m2.5

  Copy id

  MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

  ToolsJSON
  by MiniMax205k tokens$0.2943/M in · $1.1773/M out

• MiniMax M2.7

  minimax/minimax-m2.7

  Copy id

  MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...

  ToolsJSON
  by MiniMax205k tokens$0.2616/M in · $1.0465/M out

• MiniMax M3

  minimax/minimax-m3

  Copy id

  MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

  ToolsVisionJSON
  by MiniMax1M tokens$0.327/M in · $1.3081/M out

• MiniMax M3 (batch)

  minimax/minimax-m3:batch

  Copy id

  MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

  ToolsVisionJSON
  by MiniMax524k tokens$0.327/M in · $1.3081/M out

• MiniMax-01

  minimax/minimax-01

  Copy id

  MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

  Vision
  by MiniMax1M tokens$0.218/M in · $1.1991/M out

• Ministral 3 14B 2512

  mistralai/ministral-14b-2512

  Copy id

  The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

  ToolsVisionJSON
  by Mistral262k tokens$0.218/M in · $0.218/M out

• Ministral 3 3B 2512

  mistralai/ministral-3b-2512

  Copy id

  The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

  ToolsVisionJSON
  by Mistral131k tokens$0.109/M in · $0.109/M out

• Ministral 3 8B 2512

  mistralai/ministral-8b-2512

  Copy id

  A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

  ToolsVisionJSON
  by Mistral262k tokens$0.1635/M in · $0.1635/M out

• Ministral 8B

  mistral/ministral-8b-latest

  Copy id

  Mistral edge/cheap tier. Ideal for classification and drafts.

  Tools
  by Mistral128k tokens$0.109/M in · $0.109/M out

• Ministral 8B

  mistralai/ministral-8b

  Copy id

  Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length...

  JSON
  by Mistral128k tokens$0.1199/M in · $0.1199/M out

• Mistral Large

  mistral/mistral-large-latest

  Copy id

  Mistral flagship. Strong reasoning and multilingual.

  ToolsVisionJSON
  by Mistral128k tokens$2.1801/M in · $6.5404/M out

• Mistral Large

  mistralai/mistral-large

  Copy id

  This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

  ToolsJSON
  by Mistral128k tokens$2.1801/M in · $6.5404/M out

• Mistral Large 2407

  mistralai/mistral-large-2407

  Copy id

  This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

  ToolsJSON
  by Mistral131k tokens$2.1801/M in · $6.5404/M out

• Mistral Large 3 2512

  mistralai/mistral-large-2512

  Copy id

  Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

  ToolsVisionJSON
  by Mistral262k tokens$0.545/M in · $1.6351/M out

• Mistral Medium 3

  mistralai/mistral-medium-3

  Copy id

  Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

  ToolsVisionJSON
  by Mistral131k tokens$0.436/M in · $2.1801/M out

• Mistral Medium 3.1

  mistralai/mistral-medium-3.1

  Copy id

  Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

  ToolsVisionJSON
  by Mistral131k tokens$0.436/M in · $2.1801/M out

• Mistral Medium 3.5

  mistralai/mistral-medium-3-5

  Copy id

  Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

  ToolsVisionJSON
  by Mistral262k tokens$1.6351/M in · $8.1754/M out

• Mistral Nemo

  mistralai/mistral-nemo

  Copy id

  A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

  ToolsJSON
  by Mistral131k tokens$0.0207/M in · $0.0327/M out

• Mistral Small

  mistral/mistral-small-latest

  Copy id

  Mistral Small first-party. Strong cost/latency for general chat.

  ToolsVisionJSON
  by Mistral128k tokens$0.109/M in · $0.327/M out

• Mistral Small 3

  mistralai/mistral-small-24b-instruct-2501

  Copy id

  Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

  JSON
  by Mistral33k tokens$0.0545/M in · $0.0872/M out

• Mistral Small 3.1 24B

  mistralai/mistral-small-3.1-24b-instruct

  Copy id

  Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...

  Vision
  by Mistral128k tokens$0.3826/M in · $0.605/M out

• Mistral Small 3.2 24B

  mistralai/mistral-small-3.2-24b-instruct

  Copy id

  Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

  ToolsVisionJSON
  by Mistral131k tokens$0.0818/M in · $0.218/M out

• Mistral Small 4

  mistralai/mistral-small-2603

  Copy id

  Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

  ToolsVisionJSON
  by Mistral262k tokens$0.1635/M in · $0.654/M out

• Mixtral 8x22B Instruct

  mistralai/mixtral-8x22b-instruct

  Copy id

  Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...

  ToolsJSON
  by Mistral66k tokens$2.1801/M in · $6.5404/M out

• Morph V3 Fast

  morph/morph-v3-fast

  Copy id

  Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

  by Morph82k tokens$0.872/M in · $1.3081/M out

• Morph V3 Large

  morph/morph-v3-large

  Copy id

  Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

  JSON
  by Morph262k tokens$0.9811/M in · $2.0711/M out

• Muse Glimmer 30B

  meta/muse-glimmer-30b

  Copy id

  Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...

  ToolsVisionJSON
  by Meta131k tokens$0.3815/M in · $1.6351/M out

• Muse Spark 1.1

  meta/muse-spark-1.1

  Copy id

  Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...

  ToolsVisionJSONAudio
  by Meta—$1.3626 / min

• Muse Spark 1.2

  meta/muse-spark-1.2

  Copy id

  Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...

  ToolsVisionJSONAudio
  by Meta—$1.3626 / min

• Muse Spark 1.2 Contributor

  meta/muse-spark-1.2-contributor

  Copy id

  Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...

  ToolsVisionJSONAudio
  by Meta—$0.109 / min

• MythoMax 13B

  gryphe/mythomax-l2-13b

  Copy id

  One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge

  JSON
  by Gryphe8k tokens$0.0654/M in · $0.0654/M out

• Nano Banana 2 (Gemini 3.1 Flash Image Preview)

  google/gemini-3.1-flash-image-preview

  Copy id

  Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...

  VisionJSON
  by Google66k tokens$0.545/M in · $3.2702/M out

• Nano Banana 2 (Gemini 3.1 Flash Image)

  google/gemini-3.1-flash-image

  Copy id

  Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

  VisionJSON
  by Google131k tokens$0.545/M in · $3.2702/M out

• Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

  google/gemini-3.1-flash-lite-image

  Copy id

  Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

  VisionJSON
  by Google66k tokens$0.2725/M in · $1.6351/M out

• Nano Banana Pro (Gemini 3 Pro Image Preview)

  google/gemini-3-pro-image-preview

  Copy id

  Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

  VisionJSON
  by Google66k tokens$2.1801/M in · $13.0807/M out

• Nano Banana Pro (Gemini 3 Pro Image)

  google/gemini-3-pro-image

  Copy id

  Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

  ToolsVisionJSON
  by Google131k tokens$2.1801/M in · $13.0807/M out

• Nemotron 3 Nano 30B A3B

  nvidia/nemotron-3-nano-30b-a3b

  Copy id

  NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

  ToolsJSON
  by NVIDIA262k tokens$0.0545/M in · $0.218/M out

• Nemotron 3 Nano 30B A3B (free)

  nvidia/nemotron-3-nano-30b-a3b:free

  Copy id

  NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...

  Tools
  by NVIDIA256k tokensFree

• Nemotron 3 Nano Omni (free)

  nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

  Copy id

  NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

  ToolsVisionAudio
  by NVIDIA—$0.00 / min

• Nemotron 3 Super

  nvidia/nemotron-3-super-120b-a12b

  Copy id

  NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

  ToolsJSON
  by NVIDIA1M tokens$0.0927/M in · $0.436/M out

• Nemotron 3 Super (free)

  nvidia/nemotron-3-super-120b-a12b:free

  Copy id

  NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

  ToolsJSON
  by NVIDIA262k tokensFree

• Nemotron 3 Ultra

  nvidia/nemotron-3-ultra-550b-a55b

  Copy id

  NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

  ToolsJSON
  by NVIDIA512k tokens$0.654/M in · $3.9242/M out

• Nemotron 3 Ultra (batch)

  nvidia/nemotron-3-ultra-550b-a55b:batch

  Copy id

  NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

  ToolsJSON
  by NVIDIA512k tokens$0.654/M in · $3.9242/M out

• Nemotron 3 Ultra (free)

  nvidia/nemotron-3-ultra-550b-a55b:free

  Copy id

  NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

  Tools
  by NVIDIA1M tokensFree

• Nemotron 3.5 Content Safety (free)

  nvidia/nemotron-3.5-content-safety:free

  Copy id

  NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

  Vision
  by NVIDIA128k tokensFree

• Nemotron 3.5 Lightning

  nvidia/nemotron-3.5-lightning

  Copy id

  NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

  ToolsJSON
  by NVIDIA262k tokens$0.0872/M in · $0.218/M out

• Nemotron 3.5 Lightning (free)

  nvidia/nemotron-3.5-lightning:free

  Copy id

  NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

  Tools
  by NVIDIA1M tokensFree

• Nemotron Nano 12B 2 VL (free)

  nvidia/nemotron-nano-12b-v2-vl:free

  Copy id

  NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

  ToolsVision
  by NVIDIA128k tokensFree

• Nemotron Nano 9B V2 (free)

  nvidia/nemotron-nano-9b-v2:free

  Copy id

  NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

  ToolsJSON
  by NVIDIA128k tokensFree

• Nex-N2-Mini

  nex-agi/nex-n2-mini

  Copy id

  Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...

  ToolsVisionJSON
  by Nex Agi262k tokens$0.0273/M in · $0.109/M out

• Nex-N2-Pro

  nex-agi/nex-n2-pro

  Copy id

  Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...

  ToolsVision
  by Nex Agi262k tokens$0.2725/M in · $1.0901/M out

• North Mini Code (free)

  cohere/north-mini-code:free

  Copy id

  North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

  Tools
  by Cohere256k tokensFree

• Nova 2 Lite

  amazon/nova-2-lite-v1

  Copy id

  Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...

  ToolsVision
  by Amazon1M tokens$0.327/M in · $2.7251/M out

• Nova Lite 1.0

  amazon/nova-lite-v1

  Copy id

  Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

  ToolsVision
  by Amazon300k tokens$0.0654/M in · $0.2616/M out

• Nova Micro 1.0

  amazon/nova-micro-v1

  Copy id

  Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

  Tools
  by Amazon128k tokens$0.0382/M in · $0.1526/M out

• Nova Premier 1.0

  amazon/nova-premier-v1

  Copy id

  Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

  ToolsVision
  by Amazon1M tokens$2.7251/M in · $13.6257/M out

• Nova Pro 1.0

  amazon/nova-pro-v1

  Copy id

  Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

  ToolsVision
  by Amazon300k tokens$0.872/M in · $3.4882/M out

• o1

  openai/o1

  Copy id

  The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

  ToolsVisionJSON
  by OpenAI200k tokens$16.3509/M in · $65.4036/M out

• o1 (batch)

  openai/o1:batch

  Copy id

  The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

  ToolsVisionJSON
  by OpenAI200k tokens$8.1754/M in · $32.7018/M out

• o1-pro

  openai/o1-pro

  Copy id

  The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...

  VisionJSON
  by OpenAI200k tokens$163.509/M in · $654.0358/M out

• o1-pro (batch)

  openai/o1-pro:batch

  Copy id

  The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...

  VisionJSON
  by OpenAI200k tokens$81.7545/M in · $327.0179/M out

• o3

  openai/o3

  Copy id

  o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

  ToolsVisionJSON
  by OpenAI200k tokens$2.1801/M in · $8.7205/M out

• o3 (batch)

  openai/o3:batch

  Copy id

  o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

  ToolsVisionJSON
  by OpenAI200k tokens$1.0901/M in · $4.3602/M out

• o3 Mini (batch)

  openai/o3-mini:batch

  Copy id

  OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

  ToolsJSON
  by OpenAI200k tokens$0.5995/M in · $2.3981/M out

• o3 Mini High

  openai/o3-mini-high

  Copy id

  OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

  ToolsJSON
  by OpenAI200k tokens$1.1991/M in · $4.7963/M out

• o3 Mini High (batch)

  openai/o3-mini-high:batch

  Copy id

  OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

  ToolsJSON
  by OpenAI200k tokens$0.5995/M in · $2.3981/M out

• o3 Pro

  openai/o3-pro

  Copy id

  The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

  ToolsVisionJSON
  by OpenAI200k tokens$21.8012/M in · $87.2048/M out

• o3 Pro (batch)

  openai/o3-pro:batch

  Copy id

  The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

  ToolsVisionJSON
  by OpenAI200k tokens$10.9006/M in · $43.6024/M out

• o3-mini (reasoning)

  openai/o3-mini

  Copy id

  Reasoning model (Chain of Thought). Thinks internally before answering. Ideal for math problems and hard code.

  ZDRToolsVisionJSON
  by OpenAI200k tokens$1.1991/M in · $4.7963/M out

• o4 Mini

  openai/o4-mini

  Copy id

  OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

  ToolsVisionJSON
  by OpenAI200k tokens$1.1991/M in · $4.7963/M out

• o4 Mini (batch)

  openai/o4-mini:batch

  Copy id

  OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

  ToolsVisionJSON
  by OpenAI200k tokens$0.5995/M in · $2.3981/M out

• o4 Mini High

  openai/o4-mini-high

  Copy id

  OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

  ToolsVisionJSON
  by OpenAI200k tokens$1.1991/M in · $4.7963/M out

• o4 Mini High (batch)

  openai/o4-mini-high:batch

  Copy id

  OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

  ToolsVisionJSON
  by OpenAI200k tokens$0.5995/M in · $2.3981/M out

• Olmo 3 32B Think

  allenai/olmo-3-32b-think

  Copy id

  Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...

  JSON
  by AllenAI66k tokens$0.1635/M in · $0.545/M out

• OpenAI text-embedding-3-large

  openai/text-embedding-3-large

  Copy id

  Higher dimensional (3072) and higher quality embeddings. Recommended when the corpus is diverse or ranking demands precision.

  by OpenAI8k tokens$0.1417 / 1M tokens

• OpenAI text-embedding-3-small

  openai/text-embedding-3-small

  Copy id

  OpenAI's general-purpose embeddings. Fast, cheap, good enough for retrieval, clustering and classification in most cases.

  by OpenAI8k tokens$0.0218 / 1M tokens

• OpenAI text-embedding-ada-002

  openai/text-embedding-ada-002

  Copy id

  Legacy OpenAI embeddings. Still supported for compatibility.

  by OpenAI8k tokens$0.109 / 1M tokens

• OpenAI Whisper-1

  openai/whisper-1

  Copy id

  OpenAI speech-to-text. POST /v1/audio/transcriptions (multipart).

  by OpenAI—$0.0065 / min

• Ox Alpha

  stealth/ox-alpha

  Copy id

  Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...

  ToolsVisionJSON
  by Stealth1M tokensFree

• Palmyra X5

  writer/palmyra-x5

  Copy id

  Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...

  by Writer1M tokens$0.654/M in · $6.5404/M out

• Perceptron Mk1

  perceptron/perceptron-mk1

  Copy id

  Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...

  VisionJSON
  by Perceptron33k tokens$0.1635/M in · $1.6351/M out

• Phi 4

  microsoft/phi-4

  Copy id

  [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

  JSON
  by Microsoft16k tokens$0.0763/M in · $0.1526/M out

• Qwen Plus 0728

  qwen/qwen-plus-2025-07-28

  Copy id

  Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

  ToolsJSON
  by Qwen1M tokens$0.2834/M in · $0.8502/M out

• Qwen Plus 0728 (thinking)

  qwen/qwen-plus-2025-07-28:thinking

  Copy id

  Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

  ToolsJSON
  by Qwen1M tokens$0.2834/M in · $0.8502/M out

• Qwen-Plus

  qwen/qwen-plus

  Copy id

  Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

  ToolsJSON
  by Qwen1M tokens$0.2834/M in · $0.8502/M out

• Qwen2.5 72B Instruct

  qwen/qwen-2.5-72b-instruct

  Copy id

  Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

  ToolsJSON
  by Qwen33k tokens$0.3924/M in · $0.436/M out

• Qwen2.5 7B Instruct

  qwen/qwen-2.5-7b-instruct

  Copy id

  Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

  ToolsJSON
  by Qwen33k tokens$0.109/M in · $0.218/M out

• Qwen2.5 Coder 32B Instruct

  qwen/qwen-2.5-coder-32b-instruct

  Copy id

  Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...

  by Qwen33k tokens$0.7194/M in · $1.0901/M out

• Qwen2.5 VL 72B Instruct

  qwen/qwen2.5-vl-72b-instruct

  Copy id

  Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

  VisionJSON
  by Qwen128k tokens$0.872/M in · $1.0901/M out

• Qwen3 14B

  qwen/qwen3-14b

  Copy id

  Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

  ToolsJSON
  by Qwen131k tokens$0.1308/M in · $0.2616/M out

• Qwen3 235B A22B

  qwen/qwen3-235b-a22b

  Copy id

  Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

  ToolsJSON
  by Qwen131k tokens$0.496/M in · $1.9839/M out

• Qwen3 235B A22B Instruct 2507

  qwen/qwen3-235b-a22b-2507

  Copy id

  Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

  ToolsJSON
  by Qwen262k tokens$0.0981/M in · $0.5995/M out

• Qwen3 235B A22B Thinking 2507

  qwen/qwen3-235b-a22b-thinking-2507

  Copy id

  Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

  ToolsJSON
  by Qwen262k tokens$0.2507/M in · $2.5071/M out

• Qwen3 30B A3B

  qwen/qwen3-30b-a3b

  Copy id

  Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

  ToolsJSON
  by Qwen131k tokens$0.1308/M in · $0.545/M out

• Qwen3 30B A3B Instruct 2507

  qwen/qwen3-30b-a3b-instruct-2507

  Copy id

  Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

  ToolsJSON
  by Qwen262k tokens$0.0525/M in · $0.2104/M out

• Qwen3 30B A3B Thinking 2507

  qwen/qwen3-30b-a3b-thinking-2507

  Copy id

  Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

  ToolsJSON
  by Qwen82k tokens$0.218/M in · $2.6161/M out

• Qwen3 32B

  qwen/qwen3-32b

  Copy id

  Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

  ToolsJSON
  by Qwen131k tokens$0.0872/M in · $0.3052/M out

• Qwen3 8B

  qwen/qwen3-8b

  Copy id

  Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

  ToolsJSON
  by Qwen131k tokens$0.1275/M in · $0.496/M out

• Qwen3 Coder 30B A3B Instruct

  qwen/qwen3-coder-30b-a3b-instruct

  Copy id

  Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

  ToolsJSON
  by Qwen262k tokens$0.0763/M in · $0.3052/M out

• Qwen3 Coder 480B A35B

  qwen/qwen3-coder

  Copy id

  Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

  ToolsJSON
  by Qwen262k tokens$0.327/M in · $1.0901/M out

• Qwen3 Coder Flash

  qwen/qwen3-coder-flash

  Copy id

  Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

  ToolsJSON
  by Qwen1M tokens$0.2126/M in · $1.0628/M out

• Qwen3 Coder Next

  qwen/qwen3-coder-next

  Copy id

  Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

  ToolsJSON
  by Qwen262k tokens$0.1308/M in · $0.872/M out

• Qwen3 Coder Plus

  qwen/qwen3-coder-plus

  Copy id

  Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...

  ToolsJSON
  by Qwen1M tokens$0.7085/M in · $3.5427/M out

• Qwen3 Max

  qwen/qwen3-max

  Copy id

  Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...

  ToolsJSON
  by Qwen262k tokens$0.8502/M in · $4.2512/M out

• Qwen3 Max Thinking

  qwen/qwen3-max-thinking

  Copy id

  Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...

  ToolsJSON
  by Qwen262k tokens$0.8502/M in · $4.2512/M out

• Qwen3 Next 80B A3B Instruct

  qwen/qwen3-next-80b-a3b-instruct

  Copy id

  Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

  ToolsJSON
  by Qwen262k tokens$0.109/M in · $1.1991/M out

• Qwen3 Next 80B A3B Thinking

  qwen/qwen3-next-80b-a3b-thinking

  Copy id

  Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

  ToolsJSON
  by Qwen262k tokens$0.1635/M in · $1.3081/M out

• Qwen3 VL 235B A22B Instruct

  qwen/qwen3-vl-235b-a22b-instruct

  Copy id

  Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

  ToolsVisionJSON
  by Qwen262k tokens$0.2289/M in · $2.0711/M out

• Qwen3 VL 235B A22B Thinking

  qwen/qwen3-vl-235b-a22b-thinking

  Copy id

  Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

  ToolsVisionJSON
  by Qwen131k tokens$0.436/M in · $4.3602/M out

• Qwen3 VL 30B A3B Instruct

  qwen/qwen3-vl-30b-a3b-instruct

  Copy id

  Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

  ToolsVisionJSON
  by Qwen262k tokens$0.1417/M in · $0.5668/M out

• Qwen3 VL 30B A3B Thinking

  qwen/qwen3-vl-30b-a3b-thinking

  Copy id

  Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

  ToolsVisionJSON
  by Qwen262k tokens$0.218/M in · $2.6161/M out

• Qwen3 VL 32B Instruct

  qwen/qwen3-vl-32b-instruct

  Copy id

  Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...

  ToolsVisionJSON
  by Qwen131k tokens$0.1134/M in · $0.4535/M out

• Qwen3 VL 8B Instruct

  qwen/qwen3-vl-8b-instruct

  Copy id

  Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

  ToolsVisionJSON
  by Qwen262k tokens$0.1275/M in · $0.496/M out

• Qwen3 VL 8B Thinking

  qwen/qwen3-vl-8b-thinking

  Copy id

  Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...

  ToolsVisionJSON
  by Qwen131k tokens$0.1962/M in · $2.2891/M out

• Qwen3.5 397B A17B

  qwen/qwen3.5-397b-a17b

  Copy id

  The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

  ToolsVisionJSON
  by Qwen262k tokens$0.545/M in · $3.9242/M out

• Qwen3.5 Plus 2026-02-15

  qwen/qwen3.5-plus-02-15

  Copy id

  The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...

  ToolsVisionJSON
  by Qwen1M tokens$0.2834/M in · $1.7005/M out

• Qwen3.5 Plus 2026-04-20

  qwen/qwen3.5-plus-20260420

  Copy id

  Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...

  ToolsVisionJSON
  by Qwen1M tokens$0.327/M in · $1.9621/M out

• Qwen3.5-122B-A10B

  qwen/qwen3.5-122b-a10b

  Copy id

  The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...

  ToolsVisionJSON
  by Qwen262k tokens$0.2834/M in · $2.2673/M out

• Qwen3.5-27B

  qwen/qwen3.5-27b

  Copy id

  The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...

  ToolsVisionJSON
  by Qwen262k tokens$0.2126/M in · $1.7005/M out

• Qwen3.5-35B-A3B

  qwen/qwen3.5-35b-a3b

  Copy id

  The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...

  ToolsVisionJSON
  by Qwen262k tokens$0.2725/M in · $1.3626/M out

• Qwen3.5-9B

  qwen/qwen3.5-9b

  Copy id

  Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

  ToolsVisionJSON
  by Qwen262k tokens$0.109/M in · $0.1635/M out

• Qwen3.5-Flash

  qwen/qwen3.5-flash-02-23

  Copy id

  The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...

  ToolsVisionJSON
  by Qwen1M tokens$0.0709/M in · $0.2834/M out

• Qwen3.6 27B

  qwen/qwen3.6-27b

  Copy id

  Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

  ToolsVisionJSON
  by Qwen262k tokens$0.3488/M in · $3.4882/M out

• Qwen3.6 35B A3B

  qwen/qwen3.6-35b-a3b

  Copy id

  Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

  ToolsVisionJSON
  by Qwen262k tokens$0.1526/M in · $1.0901/M out

• Qwen3.6 Flash

  qwen/qwen3.6-flash

  Copy id

  Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...

  ToolsVisionJSON
  by Qwen1M tokens$0.2044/M in · $1.2263/M out

• Qwen3.6 Max Preview

  qwen/qwen3.6-max-preview

  Copy id

  Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...

  ToolsJSON
  by Qwen262k tokens$1.1195/M in · $6.7169/M out

• Qwen3.6 Plus

  qwen/qwen3.6-plus

  Copy id

  Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

  ToolsVisionJSON
  by Qwen1M tokens$0.3543/M in · $2.1256/M out

• Qwen3.7 Flash

  qwen/qwen3.7-flash

  Copy id

  Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

  ToolsVisionJSON
  by Qwen1M tokens$0.0327/M in · $0.1417/M out

• Qwen3.7 Max

  qwen/qwen3.7-max

  Copy id

  Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...

  ToolsJSON
  by Qwen1M tokens$1.6078/M in · $4.8235/M out

• Qwen3.7 Plus

  qwen/qwen3.7-plus

  Copy id

  Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

  ToolsVisionJSON
  by Qwen1M tokens$0.3488/M in · $1.3953/M out

• Qwen3.8 2.4T A95B

  qwen/qwen3.8-2.4t-a95b

  Copy id

  Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

  ToolsJSON
  by Qwen1M tokens$2.1801/M in · $6.5404/M out

• Qwen3.8 27B

  qwen/qwen3.8-27b

  Copy id

  Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

  ToolsVisionJSON
  by Qwen1M tokens$0.436/M in · $3.2702/M out

• Qwen3.8 Max

  qwen/qwen3.8-max

  Copy id

  Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...

  ToolsVisionJSON
  by Qwen1M tokens$2.1801/M in · $6.5404/M out

• R1

  deepseek/deepseek-r1

  Copy id

  DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

  ToolsJSON
  by DeepSeek64k tokens$0.763/M in · $2.7251/M out

• R1 0528

  deepseek/deepseek-r1-0528

  Copy id

  May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

  ToolsJSON
  by DeepSeek164k tokens$0.545/M in · $2.3436/M out

• R1 Distill Llama 70B

  deepseek/deepseek-r1-distill-llama-70b

  Copy id

  DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

  by DeepSeek8k tokens$0.872/M in · $0.872/M out

• Recraft V3

  fal/recraft-v3

  Copy id

  Leader in branding and illustration. Consistent variants in a defined style.

  by fal.ai—$0.0436 / image

• Reka Edge

  rekaai/reka-edge

  Copy id

  Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...

  ToolsVisionJSON
  by Reka16k tokens$0.109/M in · $0.109/M out

• Reka Flash 3

  rekaai/reka-flash-3

  Copy id

  Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

  JSON
  by Reka66k tokens$0.109/M in · $0.218/M out

• Relace Apply 3

  relace/relace-apply-3

  Copy id

  Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

  by Relace256k tokens$0.9266/M in · $1.3626/M out

• Relace Search

  relace/relace-search

  Copy id

  The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...

  ToolsJSON
  by Relace256k tokens$1.0901/M in · $3.2702/M out

• ReMM SLERP 13B

  undi95/remm-slerp-l2-13b

  Copy id

  A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge

  JSON
  by Undi956k tokens$0.4905/M in · $0.7085/M out

• Ring-2.6-1T

  inclusionai/ring-2.6-1t

  Copy id

  Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...

  ToolsJSON
  by Inclusionai262k tokens$0.0818/M in · $0.6813/M out

• Rocinante 12B

  thedrummer/rocinante-12b

  Copy id

  Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...

  JSON
  by Thedrummer66k tokens$0.2725/M in · $0.545/M out

• Runway Gen-4 Turbo

  fal/runway-gen-4

  Copy id

  Good price/quality balance. Excellent prompt-following and temporal coherence.

  by fal.ai—$0.0545 / s

• Saba

  mistralai/mistral-saba

  Copy id

  Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

  ToolsJSON
  by Mistral33k tokens$0.218/M in · $0.654/M out

• Sakana Namazu

  sakana/sakana-namazu

  Copy id

  Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...

  ToolsVisionJSON
  by Sakana262k tokens$1.0356/M in · $4.3602/M out

• Seed 1.6

  bytedance-seed/seed-1.6

  Copy id

  Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.

  ToolsVisionJSON
  by ByteDance262k tokens$0.2725/M in · $2.1801/M out

• Seed 1.6 Flash

  bytedance-seed/seed-1.6-flash

  Copy id

  Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...

  ToolsVisionJSON
  by ByteDance262k tokens$0.0818/M in · $0.327/M out

• Seed 2.1 Turbo

  bytedance-seed/seed-2-1-turbo

  Copy id

  Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...

  ToolsVisionJSON
  by ByteDance262k tokens$0.545/M in · $2.7251/M out

• Seed-2.0-Code

  bytedance-seed/seed-2.0-code

  Copy id

  Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...

  ToolsVisionJSON
  by ByteDance262k tokens$0.545/M in · $3.2702/M out

• Seed-2.0-Lite

  bytedance-seed/seed-2.0-lite

  Copy id

  Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...

  ToolsVisionJSON
  by ByteDance262k tokens$0.2725/M in · $2.1801/M out

• Seed-2.0-Mini

  bytedance-seed/seed-2.0-mini

  Copy id

  Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...

  ToolsVisionJSON
  by ByteDance262k tokens$0.109/M in · $0.436/M out

• Skyfall 36B V2

  thedrummer/skyfall-36b-v2

  Copy id

  Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

  JSON
  by Thedrummer33k tokens$0.5995/M in · $0.872/M out

• Solar Pro 3

  upstage/solar-pro-3

  Copy id

  Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...

  ToolsJSON
  by Upstage131k tokens$0.1635/M in · $0.654/M out

• Solar Pro 4

  upstage/solar-pro4

  Copy id

  Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...

  ToolsJSON
  by Upstage524k tokens$0.0327/M in · $0.1308/M out

• Sonar

  perplexity/sonar

  Copy id

  Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

  Vision
  by Perplexity127k tokens$1.0901/M in · $1.0901/M out

• Sonar Deep Research

  perplexity/sonar-deep-research

  Copy id

  Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

  by Perplexity128k tokens$2.1801/M in · $8.7205/M out

• Sonar Pro

  perplexity/sonar-pro

  Copy id

  Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

  Vision
  by Perplexity200k tokens$3.2702/M in · $16.3509/M out

• Sonar Pro Search

  perplexity/sonar-pro-search

  Copy id

  It is designed for deeper reasoning and analysis. Pricing is based...

  VisionJSON
  by Perplexity200k tokens$3.2702/M in · $16.3509/M out

• Sonar Reasoning Pro

  perplexity/sonar-reasoning-pro

  Copy id

  Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

  Vision
  by Perplexity128k tokens$2.1801/M in · $8.7205/M out

• Sora 2

  openai/sora-2

  Copy id

  OpenAI's Sora 2. Realistic physics and long temporal coherence. With audio.

  by OpenAI—$0.109 / s

• Sora 2 Pro

  openai/sora-2-pro

  Copy id

  Sora 2 Pro. Maximum quality. Tiered pricing $0.30-$0.70/sec depending on resolution.

  by OpenAI—$0.545 / s

• Stable Diffusion 3.5 Large

  fal/sd-3.5-large

  Copy id

  Stability AI's latest generation. Open-weight with strong prompt-following.

  by fal.ai—$0.0709 / image

• Step 3.5 Flash

  stepfun/step-3.5-flash

  Copy id

  Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

  Tools
  by StepFun262k tokens$0.109/M in · $0.327/M out

• Step 3.7 Flash

  stepfun/step-3.7-flash

  Copy id

  Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...

  ToolsVisionJSON
  by StepFun262k tokens$0.218/M in · $1.2536/M out

• Trinity Large Thinking

  arcee-ai/trinity-large-thinking

  Copy id

  Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...

  ToolsJSON
  by Arcee Ai262k tokens$0.2398/M in · $0.9266/M out

• TTS 1

  openai/tts-1

  Copy id

  OpenAI's standard TTS. Low latency, good quality for assistants and notifications. 6 voices.

  by OpenAI—$16.3509 / 1M chars

• TTS 1 HD

  openai/tts-1-hd

  Copy id

  HD version: better fidelity and intonation at double the price. Recommended for podcasts and audiobooks.

  by OpenAI—$32.7018 / 1M chars

• UI-TARS 7B

  bytedance/ui-tars-1.5-7b

  Copy id

  UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

  VisionJSON
  by ByteDance128k tokens$0.109/M in · $0.218/M out

• Uncensored

  cognitivecomputations/dolphin-mistral-24b-venice-edition

  Copy id

  Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

  JSON
  by Cognitivecomputations128k tokens$0.218/M in · $0.9811/M out

• UnslopNemo 12B

  thedrummer/unslopnemo-12b

  Copy id

  UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

  ToolsJSON
  by Thedrummer1M tokens$0.436/M in · $0.436/M out

• Veo 3.1

  google/veo-3.1

  Copy id

  The only video model with natively generated foley + ambience. Cinematic and with audio.

  by Google—$0.436 / s

• Veo 3.1 Fast

  google/veo-3.1-fast

  Copy id

  Accelerated Veo 3.1. 4x cheaper with audio included. Ideal for iterating.

  by Google—$0.109 / s

• Veo 3.1 Lite

  google/veo-3.1-lite

  Copy id

  The cheapest Veo. No audio, for rapid prototyping and draft frames.

  by Google—$0.0545 / s

• Virtuoso Large

  arcee-ai/virtuoso-large

  Copy id

  Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

  Tools
  by Arcee Ai131k tokens$0.8175/M in · $1.3081/M out

• Voxtral Small 24B 2507

  mistralai/voxtral-small-24b-2507

  Copy id

  Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...

  ToolsJSONAudio
  by Mistral—$0.109 / min

• Wan 2.5

  fal/wan-2.5

  Copy id

  Alibaba's model. Very competitive price, good T2V quality.

  by fal.ai—$0.0545 / s

• Weaver (alpha)

  mancer/weaver

  Copy id

  An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

  JSON
  by Mancer8k tokens$0.545/M in · $0.8175/M out

• WizardLM-2 8x22B

  microsoft/wizardlm-2-8x22b

  Copy id

  WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...

  JSON
  by Microsoft66k tokens$0.6758/M in · $0.6758/M out