Model catalog

Call LLMs on /v1/messages, /v1/responses or /v1/chat/completions, and media models with POST /api/v1/jobs/createTask. Fields marked * are required in input. See the API reference.

Model pricing

Prices in USD. 1 credit = $0.001. LLMs are billed per token; media tasks are charged their actual cost when they finish, and failed tasks are refunded. Percentages compare with the reference list price.

ModelEndpointInput / 1MOutput / 1MCached input / 1M
Claude Fable 5
claude-fable-5
/v1/messages$5.20$26.00$0.52
Claude Haiku 4.5
claude-haiku-4-5
/v1/messages$0.413−59%$2.14−57%$0.041
Claude Opus 4.5
claude-opus-4-5
/v1/messages$2.14−57%$10.73−57%$0.214
Claude Opus 4.6
claude-opus-4-6
/v1/messages$2.14−57%$10.73−57%$0.214
Claude Opus 4.7
claude-opus-4-7
/v1/messages$2.14−57%$10.73−57%$0.214
Claude Opus 4.8
claude-opus-4-8
/v1/messages$3.00−40%$15.00−40%$0.3
Claude Opus 5
claude-opus-5
/v1/messages$3.00−40%$15.00−40%$0.3
Claude Opus 5.5
claude-opus-5-5
/v1/messages$2.40−40%$12.00−40%$0.24
Claude Sonnet 4.5
claude-sonnet-4-5
/v1/messages$1.27−57%$6.41−57%$0.128
Claude Sonnet 4.6
claude-sonnet-4-6
/v1/messages$1.27−57%$6.41−57%$0.128
Claude Sonnet 5
claude-sonnet-5
/v1/messages$1.27−36%$6.41−36%$0.128
Claude Sonnet 5.5
claude-sonnet-5-5
/v1/messages$1.20−40%$6.00−40%$0.12
DeepSeek V4.1 Flash
deepseek-v4-1-flash
/v1/responses$0.144$0.57$0.003
Gemini 2.5 Pro
gemini-2-5-pro
/v1/chat/completions$0.57−54%$4.50−55%$0.057
Gemini 3.1 Pro
gemini-3-1-pro
/v1/chat/completions$0.75−63%$5.25−56%$0.075
Gemini 3.5 Flash
gemini-3-5-flash
/v1/chat/completions$0.675−55%$4.05−55%$0.068
Gemini 3.6 Flash
gemini-3-6-flash
/v1/chat/completions$0.338−55%$1.69−55%$0.034
Gemini 3.7 Flash
gemini-3-7-flash
/v1/chat/completions$0.338−55%$1.69−55%$0.034
Gemini 3.8 Flash
gemini-3-8-flash
/v1/chat/completions$0.338−55%$1.69−55%$0.034
Gemini 3 Pro
gemini-3-pro
/v1/chat/completions$0.75−63%$5.25−56%$0.075
GPT Codex
gpt-5-1-codex
/v1/responses$0.75−40%$6.00−40%$0.075
GPT 5.2
gpt-5-2
/v1/chat/completions$0.66−62%$5.25−63%$0.066
GPT Codex
gpt-5-2-codex
/v1/responses$1.05−40%$8.40−40%$0.105
GPT Codex
gpt-5-3-codex
/v1/responses$1.05−40%$8.40−40%$0.105
GPT 5.4
gpt-5-4
/v1/responses$1.05−58%$8.40−44%$0.105
GPT Codex
gpt-5-4-codex
/v1/responses$1.05−58%$8.40−44%$0.105
GPT 5.5
gpt-5-5
/v1/responses$2.10−58%$12.60−58%$0.21
GPT 5.6 Luna
gpt-5-6-luna
/v1/responses$0.084−58%$0.504−58%$0.0084
GPT 5.6 Sol
gpt-5-6-sol
/v1/responses$2.10−58%$12.60−58%$0.21
GPT 5.6 Terra
gpt-5-6-terra
/v1/responses$0.84−58%$5.04−58%$0.084
GPT Codex
gpt-5-codex
/v1/responses$0.75−40%$6.00−40%$0.075
GPT 6.1 Sol
gpt-6-1-sol
/v1/responses$0.9−55%$4.50−55%$0.045
Gpt 6 Astra
gpt-6-astra
/v1/responses$4.20−58%$21.00−58%$0.42
GPT 6 Luna
gpt-6-luna
/v1/responses$0.045−55%$0.225−55%$0.0045
GPT 6 Sol
gpt-6-sol
/v1/responses$0.9−55%$4.50−55%$0.09