Guides
Send any chat model ID below as the model field, on any chat endpoint. These tables are read from the gateway every minute, so they list only models that are routed right now.
| Model ID | Name | Context | Input / 1M | Output / 1M | Discount |
|---|---|---|---|---|---|
claude-fable-5.1 | Claude Fable 5.1 | 1M | $8.00 | $40.00 | 20% off |
claude-haiku-5.5 | Claude Haiku 5.5 | 1M | $0.35 | $1.75 | 30% off |
claude-opus-5.5 | Claude Opus 5.5 | 1M | $2.80 | $14.00 | 30% off |
claude-sonnet-5.5 | Claude Sonnet 5.5 | 1M | $1.40 | $7.00 | 30% off |
deepseek-v4-pro-0813 | DeepSeek v4.1 Pro 0813 | 1M | $1.32 | $3.96 | – |
deepseek-v4.1-flashFree | DeepSeek v4.1 Flash 1017 | 1M | $0.15 | $1.20 | – |
deepseek-v4.1-flash-uncensored | DeepSeek v4.1 Flash Uncensored | 1M | $0.40 | $1.20 | – |
gemini-3.8-flash | Gemini 3.8 Flash | 1M | $0.53 | $2.63 | 30% off |
gemini-4-argon | Gemini 4 Argon | 1M | $1.00 | $5.00 | 50% off |
glm-5.3 | GLM 5.3 | 1M | $0.03 | $3.84 | 20% off |
glm-5.3-flash | GLM 5.3 Flash | 1M | $0.07 | $0.25 | – |
glm-5.3-flash-uncensored | GLM 5.3 Flash Uncensored | 1M | $0.25 | $1.20 | – |
glm-5.3-uncensored | GLM 5.3 Uncensored | 1M | $0.78 | $2.08 | – |
gpt-5.6-luna | GPT 5.6 Luna | 1M | $0.14 | $0.84 | 30% off |
gpt-5.6-sol | GPT 5.6 Sol | 1M | $1.40 | $7.00 | 30% off |
gpt-5.6-terra | GPT 5.6 Terra | 1M | $1.40 | $8.40 | 30% off |
gpt-6-astra | GPT 6 Astra | 1M | $7.00 | $35.00 | 30% off |
gpt-6-luna | GPT 6 Luna | 1M | $0.07 | $0.35 | 30% off |
gpt-6.1-sol | GPT 6.1 Sol | 1M | $1.40 | $7.00 | 30% off |
gpt-6.1-terra | GPT 6.1 Terra | 1M | $0.50 | $2.50 | 50% off |
kimi-k3 | Kimi K3 | 1M | $0.51 | $10.80 | 20% off |
kimi-k3.1-pro | Kimi K3.1 Pro | 1M | $1.60 | $8.00 | 20% off |
mimo-v2.6-flash | MiMo v2.6 Flash | 1M | $0.14 | $0.28 | – |
mimo-v2.6-pro | MiMo v2.6 Pro | 1M | $0.43 | $0.87 | – |
minimax-m3.1-flash | MiniMax M3.1 Flash | 1M | $0.15 | $0.60 | – |
muse-spark-1.3 | Muse Spark 1.3 | 1M | $0.63 | $2.13 | 50% off |
Prices are in USD per million tokens and are what you are charged. Discount is how much lower the input price is than the provider's own published rate, where one is recorded. Free marks a model with no per-token price, or one that free credit (sign-up bonus and free-credit codes) can pay for. Cached-input prices and model details are on each model's page in the model catalog. To see how many tokens a plan buys on each model, read Plans.
These make a typed judgement instead of chatting: send the current state and the questions to answer to /v1/systemone, and get the answers back as JSON. The chat endpoints cannot carry the state and questions they need. They are also left out of the token estimates on Plans.
| Model ID | Name | Context | Input / 1M | Output / 1M | Discount |
|---|---|---|---|---|---|
drex-maxFree | Drex Max | 262K | $0.009 | $0 | 70% off |
solar-decideFree | Solar Decide | 256K | $0.001 | $0 | – |
You do not need to match the model to its provider's format. Call the path your client already speaks; the gateway converts. The one case where it matters is a format-only feature: see Other fields.
Any model ID above can take the :online suffix, such as deepseek-v4.1-flash:online, to let the model search the web while it answers. See Web search for how it works and what a search costs.