Chat & Reasoning
General-purpose chat, reasoning, and agentic models.
Endpoints: /v1/chat/completions · /v1/responses · /v1/messages
Live catalogue
Availability is a generated snapshot from 2026-10-15. Prices are intentionally not copied into static pages because Admin-reviewed rates can change independently of a docs release. Read the public catalogue for current billing units, availability, and customer prices.
Available (45)
| Model | ID | Context | Protocols | Capabilities |
|---|---|---|---|---|
| GPT-6 Astra | gpt-6-astra | 922K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +3 |
| GPT-6.1 Sol | gpt-6.1-sol | 1.1M | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-6 Sol | gpt-6-sol | 1.1M | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-6 Luna | gpt-6-luna | 1.1M | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5.6 Sol | gpt-5.6-sol | 922K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5.6 Terra | gpt-5.6-terra | 922K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5.6 Luna | gpt-5.6-luna | 922K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5.5 | gpt-5.5 | 1.1M | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5 Mini | gpt-5-mini | 400K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5.4 Mini | gpt-5.4-mini | 272K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-5.4 Nano | gpt-5.4-nano | 272K | Chat · Responses | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-4o | gpt-4o | 128K | Chat | streaming, function_calling, structured_output, prompt_caching, vision |
| GPT-5 | gpt-5 | 400K | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GPT-4.1 | gpt-4.1 | 300K | Chat | streaming, function_calling, structured_output, prompt_caching, vision |
| Claude Fable 5.1 | claude-fable-5-1 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Opus 5.5 | claude-opus-5-5 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Fable 5 | claude-fable-5 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Opus 5 | claude-opus-5 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Sonnet 5 | claude-sonnet-5 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Claude Opus 4.8 | claude-opus-4-8 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Grok 4.6 | grok-4.6 | 200K | Chat | streaming, reasoning |
| Grok 4.3 | grok-4.3 | 200K | Chat | streaming, reasoning |
| DeepSeek V4 Pro | DeepSeek-V4-Pro | 1M | Chat | streaming, reasoning |
| DeepSeek V4 Flash | DeepSeek-V4-Flash | 1M | Chat | streaming, reasoning |
| DeepSeek V3.2 Speciale | DeepSeek-V3.2-Speciale | 128K | Chat | streaming, reasoning |
| Llama 4 Maverick | Llama-4-Maverick | 1M | Chat | streaming |
| Llama 4 Scout | Llama-4-Scout | 1M | Chat | streaming |
| Llama 3.3 70B Instruct | Llama-3.3-70B-Instruct | 128K | Chat | streaming |
| model-router | model-router | 200K | Chat | streaming, routing |
| Phi-4 | Phi-4 | 16K | Chat | streaming |
| Phi-4 Mini Instruct | Phi-4-mini-instruct | 131K | Chat | streaming |
| Mistral Large 3 | Mistral-Large-3 | 256K | Chat | streaming |
| Mistral Medium 3.5 | mistral-medium-3-5 | 128K | Chat | streaming |
| Kimi K2.6 | Kimi-K2.6 | 262K | Chat | streaming |
| Cohere Command A | cohere-command-a | 256K | Chat | streaming |
| Claude Haiku 5.5 | claude-haiku-5-5 | 1M | Chat · Messages | streaming, reasoning, function_calling, prompt_caching, vision |
| Grok 4.7 | grok-4.7 | 500K | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching, +1 |
| GLM 5.3 Flash | GLM-5.3-Flash | 1M | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching |
| MiniMax M3 | MiniMax-M3 | 524K | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching |
| GLM 5.3 | GLM-5.3 | 1M | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching |
| Nemotron 3 Ultra | Nemotron-3-Ultra | 262K | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching |
| GLM 5.2 Fast | GLM-5.2-Fast | 1M | Chat | streaming, reasoning, function_calling, structured_output, prompt_caching |
Coming soon (5)
| Model | ID | Context | Protocols |
|---|---|---|---|
| Grok 4.1 Fast (Reasoning) | grok-4-1-fast-reasoning | 200K | Chat |
| Grok 4.1 Fast (Non-reasoning) | grok-4-1-fast-non-reasoning | 200K | Chat |
| DeepSeek V3.2 | DeepSeek-V3.2 | 128K | Chat |
| Cohere Command A Plus | Cohere-command-a-plus-05-2026 | 256K | Chat |
| Nemotron Lightning 3.5 | Nemotron-Lightning-3.5 | 262K | Chat |