Models with tool calling and function calling
Without tool calling you do not have a real agent — only chat. This list prioritizes models with stable function calling / tools to orchestrate APIs, SQL, browsers, and MCP — via Geek Hub’s OpenAI-compatible API.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 GPT-5.4 miniOpenAI | Chat | 272k tokens | $0.8175/M in · $4.9053/M out |
 Claude Sonnet 5Anthropic | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
 Gemini 2.5 FlashGoogle | Chat | 1M tokens | $0.327/M in · $2.7251/M out |
| GPT-5.5OpenAI | Chat | 272k tokens | $5.4503/M in · $32.7018/M out |
| Claude Haiku 4.5Anthropic | Chat | 200k tokens | $1.0901/M in · $5.4503/M out |
 Mistral LargeMistral | Chat | 128k tokens | $2.1801/M in · $6.5404/M out |
| Gemini 2.5 ProGoogle | Chat | 2M tokens | $1.3626/M in · $10.9006/M out |
| GPT-4.1 mini (legacy)OpenAI | Chat | 1M tokens | $0.436/M in · $1.7441/M out |
Why these models
GPT and Claude are the de-facto tools standard; Gemini Flash/Pro for volume; Mistral Large and Haiku/mini when you want low cost without losing the tool loop.
Use them with Geek Hub
One OpenAI-compatible base URL and API key. Swap any model id from this list without rewriting your client.
Get an API keyFAQ
- Is tool calling the same as structured outputs?
- Related but different. Tools = call functions. Structured outputs = JSON schema on the reply. Many models here do both.
- Works with LangGraph / CrewAI?
- Yes if the client speaks OpenAI-compatible. Point base URL and key to Geek Hub and pick a model id from this list.
- Best for the tools hot path?
- GPT-5.4-mini, Gemini Flash, or Haiku for the router; Sonnet/GPT-5.5/Pro for critical steps.