DeepSeek V4 Flash 0731 (batch)
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. This is the GA release of DeepSeek V4 Flash.
deepseek/deepseek-v4-flash-0731:batch
- Context
- 1M tokens
- Completion cap
- 943,718
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-07-31
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash-0731:batch",
"messages": [{"role": "user", "content": "Hola"}]
}'Get an API keyFrequently asked questions
- What is DeepSeek V4 Flash 0731 (batch)?
- 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. This is the GA release of DeepSeek V4 Flash. DeepSeek V4 Flash 0731 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-v4-flash-0731:batch.
- Is DeepSeek V4 Flash 0731 (batch) free?
- No. Input is $0.1526 per 1M tokens and output is $0.3052 per 1M tokens on Geek Hub (markup included).
- What is the context length of DeepSeek V4 Flash 0731 (batch)?
- DeepSeek V4 Flash 0731 (batch) has a 1M tokens context window. It supports up to 943,718 completion tokens.
- Does DeepSeek V4 Flash 0731 (batch) support tool calling and structured outputs?
- DeepSeek V4 Flash 0731 (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was DeepSeek V4 Flash 0731 (batch) released?
- DeepSeek V4 Flash 0731 (batch) was released on 2026-07-31.
More models from DeepSeek
DeepSeek V4 FlashV4 Flash open-weight, aggressive pricing with 1M context. Cache hit drops input to $0.0028. Replaces DeepSeek Chat V3.
DeepSeek V4 ProV4 Pro with reasoning + non-reasoning modes. Cache hit $0.003625. Replaces DeepSeek Reasoner R1.
DeepSeek V3DeepSeek-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 tok
DeepSeek V3 0324DeepSeek 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/d
DeepSeek V3.1DeepSeek-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 ba
DeepSeek V3.1 TerminusDeepSeek-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, inc