Skip to content
Inference

Models and pricing

Token pricing

Prices are in USD per million tokens. Cached input is charged at the cached rate instead of the regular input rate. There is no separate cache-write fee.

Model IDInputCached inputOutput
Loading prices…

Capabilities and limits

All models support streaming, reasoning, and function calling. Output is also bounded by the remaining context after input.

Model IDContext (input + output)Maximum output
moonshotai/Kimi-K3.1-Pro1,048,576 tokens1,048,575 tokens
moonshotai/Kimi-K31,048,576 tokens1,048,575 tokens
deepseek-ai/DeepSeek-V4.1-Flash-10171,048,576 tokens393,216 tokens
deepseek-ai/DeepSeek-V4.1-Flash1,048,576 tokens393,216 tokens
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP41,048,576 tokens1,048,575 tokens
zai-org/GLM-5.3-Flash1,048,576 tokens128K tokens
Qwen/Qwen3.8-27B-FP8262,144 tokens262,143 tokens
GLM-5.31,048,576 tokens128K tokens

See the quickstart to make your first request.

Usage and billing

Token countChat Completions usageResponses usage
All input tokens, including cached inputprompt_tokensinput_tokens
Cached subset of inputprompt_tokens_details.cached_tokensinput_tokens_details.cached_tokens
All generated tokens, including reasoningcompletion_tokensoutput_tokens
Reasoning subset of outputcompletion_tokens_details.reasoning_tokensoutput_tokens_details.reasoning_tokens