Models & protocols
Model IDs, tiers, and which endpoint serves which family.
Model IDs
Send one of these IDs as model. IDs are case-sensitive. You can also fetch the live list from GET /v1/models, or browse rates on the Models page.
| Model ID | Family | Tier | Context |
|---|---|---|---|
| claude-fable-5-1 | Claude | Frontier | 262K |
| claude-fable-5 | Claude | Frontier | 262K |
| claude-mythos-5 | Claude | Frontier | 262K |
| claude-opus-5.5 | Claude | Frontier | 262K |
| claude-opus-5 | Claude | Frontier | 262K |
| claude-opus-4.8 | Claude | Frontier | 262K |
| claude-opus-4.7 | Claude | Frontier | 262K |
| claude-opus-4.6 | Claude | Frontier | 262K |
| claude-opus-4.5 | Claude | Frontier | 262K |
| claude-opus-4.1 | Claude | Frontier | 262K |
| claude-opus-4 | Claude | Frontier | 262K |
| claude-sonnet-5 | Claude | Balanced | 131K |
| claude-sonnet-4.6 | Claude | Balanced | 131K |
| claude-sonnet-4.5 | Claude | Balanced | 131K |
| claude-sonnet-4 | Claude | Balanced | 131K |
| claude-haiku-4.5 | Claude | Speed | 131K |
| claude-haiku-3.5 | Claude | Speed | 131K |
| gpt-astra-6 | ChatGPT | Frontier | 262K |
| gpt-5 | ChatGPT | Frontier | 262K |
| gpt-5-mini | ChatGPT | Balanced | 131K |
| gpt-4.1 | ChatGPT | Balanced | 131K |
| gpt-4.1-mini | ChatGPT | Speed | 131K |
| gpt-4o | ChatGPT | Balanced | 131K |
| gpt-4o-mini | ChatGPT | Speed | 131K |
Protocol support
Claude models are native to the Anthropic Messages API; GPT models are native to the OpenAI Responses API. Chat Completions works with every model, which is what most third-party tools use.
| Endpoint | Claude models | GPT models |
|---|---|---|
| POST /v1/messages | Yes | No |
| POST /v1/responses | No | Yes |
| POST /v1/chat/completions | Yes | Yes |
| GET /v1/models | Yes | Yes |
Choosing a tier
Every model in a tier bills at the same rate, so choose by capability:
Frontier
The most capable models, for deep reasoning and long-horizon agent work.
e.g. claude-fable-5-1, claude-mythos-5, claude-opus-5.5, gpt-astra-6, gpt-5
Balanced
Strong everyday models that trade a little depth for speed and cost.
e.g. claude-sonnet-5, gpt-5-mini
Speed
Fast, lightweight models for high-volume and latency-sensitive work.
e.g. claude-haiku-4.5
A common pattern: plan and review with a Frontier model, do the bulk of the work with a Balanced one, and fan out sub-agents or classification on a Speed model. Claude and ChatGPT models can be mixed freely.
Simple prompts may be served by a lighter model of the same family. See How routing works.