model field.
This page is regenerated from the live model catalog. The authoritative source is GET /v1/models.
Available now
gpt-oss-20b
OpenAI open-weight 20B. 131k context, MXFP4. Cheapest tokens on Tera.
gpt-oss-120b
OpenAI open-weight 120B. 131k context, MXFP4. Reasoning + tool calling.
DeepSeek-V4-Flash
DeepSeek’s fast 1M-context model. Tools, JSON mode, reasoning.
DeepSeek-V4-Pro
DeepSeek’s flagship 1M-context model. Full feature set.
Qwen3-Coder-480B
480B MoE coding model. 262k context. Structured outputs.
DeepSeek-R1-0528
DeepSeek’s reasoning flagship. 163k context, chain-of-thought output.
Choosing a model
| If you want… | Use |
|---|---|
| Cheapest tokens | gpt-oss-20b |
| Long context (1M tokens) | DeepSeek-V4-Flash |
| Long context, highest quality | DeepSeek-V4-Pro |
| Code generation | Qwen3-Coder-480B |
| Reasoning / math / planning | DeepSeek-R1-0528 |
| OpenAI open-weight, large | gpt-oss-120b |
| Kimi reasoning | kimi-k2-thinking |