​
Chat

The chat models charge based on input and output tokens. Different models have different costs.
Token calculation rules vary by model. Please rely on the usage field in the response.
Model NameModel keyPricing
gpt-5gpt-5$1.25 / 1M input tokens
$10.00 / 1M output tokens
gpt-4.1gpt-4.1$2.00 / 1M input tokens
$8.00 / 1M output tokens
gpt-4.1-minigpt-4.1-mini$0.40 / 1M input tokens
$1.60 / 1M output tokens
gpt-4.1-nanogpt-4.1-nano$0.10 / 1M input tokens
$0.40 / 1M output tokens
gpt-4ogpt-4o
gpt-4o-2024-11-20		$2.50 / 1M input tokens
$10.00 / 1M output tokens
gpt-4o-minigpt-4o-mini
gpt-4o-mini-2024-07-18		$0.15 / 1M input tokens
$0.60 / 1M output tokens
o4-minio4-mini$0.55 / 1M input tokens
$2.20 / 1M output tokens
o3o3$2.00 / 1M input tokens
$8.00 / 1M output tokens
Claude Opus 4claude-opus-4-20250514
claude-opus-4-20250514-thinking		$15.00 / 1M input tokens
$75.00 / 1M output tokens
Claude Sonnet 4claude-4-sonnet
claude-sonnet-4-20250514
claude-sonnet-4-20250514-thinking		$3.00 / 1M input tokens
$15.00 / 1M output tokens
Claude Sonnet 3.7claude-3-7-sonnet-latest$3.00 / 1M input tokens
$15.00 / 1M output tokens
Claude Sonnet 3.5 v2claude-3-5-sonnet-20241022
claude-3-5-sonnet-latest		$3.00 / 1M input tokens
$15.00 / 1M output tokens
Claude Sonnet 3.5claude-3-5-sonnet-20240620$3.00 / 1M input tokens
$15.00 / 1M output tokens
Claude Haiku 3.5claude-3-5-haiku-latest
claude-3-5-haiku-20241022		$0.80 / 1M input tokens
$4.00 / 1M output tokens
Claude Opus 3claude-3-opus-20240229$15.00 / 1M input tokens
$75.00 / 1M output tokens
Claude Haiku 3claude-3-haiku-20240307
claude-3-haiku		$0.25 / 1M input tokens
$1.25 / 1M output tokens
Gemini 2.5 Progemini-2.5-pro$1.25 / 1M input tokens
$10.00 / 1M output tokens
Gemini 2.5 Flash-Litegemini-2.5-flash-lite$0.10 / 1M input tokens
$0.40 / 1M output tokens
Gemini 2.5 Flashgemini-2.5-flash$0.30 / 1M input tokens
$2.50 / 1M output tokens
Gemini 2.0 Flashgemini-2.0-flash-001
gemini-2.0-flash-thinking-exp-01-21
gemini-2.0-flash-exp		$0.10 / 1M input tokens
$0.40 / 1M output tokens
Gemini 1.5 Progemini-1.5-pro-002
gemini-1.5-pro-preview-0409
gemini-1.5-pro		$1.25 / 1M input tokens
$5.00 / 1M output tokens
Gemini 1.5 Flashgemini-1.5-flash
gemini-1.5-flash-002
gemini-1.5-flash-001		$0.075 / 1M input tokens
$0.30 / 1M output tokens
xAI: Grok 3 Betax-ai/grok-3-beta$3.00 / 1M input tokens
$15.00 / 1M output tokens
xAI: Grok Betax-ai/grok-beta$5.00 / 1M input tokens
$15.00 / 1M output tokens
DeepSeek Reasonerdeepseek-reasoner$0.55 / 1M input tokens
$2.21 / 1M output tokens
DeepSeek Chatdeepseek-chat$0.28 / 1M input tokens
$1.10 / 1M output tokens
Meta: Llama 3 8B Instructmeta-llama/llama-3-8b-instruct$0.28 / 1M input tokens
$0.83 / 1M output tokens
Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct$0.025 / 1M input tokens
$0.06 / 1M output tokens
Meta: Llama 3.3 70B Instructllama-3.3-70b-instruct$0.13 / 1M input tokens
$0.40 / 1M output tokens
NVIDIA: Llama 3.1 Nemotron 70B Instructnvidia/llama-3.1-nemotron-70b-instruct$1.00 / 1M input tokens
$1.00 / 1M output tokens
Meta: Llama 3 70B Instructmeta-llama/llama-3-70b-instruct$0.88 / 1M input tokens
$0.88 / 1M output tokens
Meta: Llama 3.1 405B Instructmeta-llama/llama-3.1-405b-instruct
llama-3.1-405b-instruct		$4.00 / 1M input tokens
$4.00 / 1M output tokens
Mistral: Mistral 7B Instructmistralai/mistral-7b-instruct$0.20 / 1M input tokens
$0.20 / 1M output tokens

​
Image generation

Different image generation models have varying pricing methods. See the table below for details:
ModelPricing
Stable Diffusion XL 1.0$0.005 / image
Stable Diffusion 3 Large$0.035 / image
Stable Diffusion 3.5 Large$0.065 / image
Flux Schnell 1.0$0.003 / image
Flux Dev 1.0$0.025 / image
Flux Pro 1.0$0.055 / image
DALL·E 3$0.040 / image (Standard, 1024×1024)
$0.080 / image (Standard, 1024×1792, 1792×1024)
$0.080 / image (HD, 1024×1792)
$0.120 / image (HD, 1024×1792, 1792×1024)
Playground V2.5$0.0039 / image
Ideogram V2$0.08 / image

​
Image tools

APIPricing
/v1/image/upscale$0.004 / image
/v1/image/remove-object$0.004 / image