everyapi
Get a free key
Model catalog30 models live

Every model, one endpoint, live prices

The model catalog and prices come directly from EveryAPI's live billing API.

Live pricing version: e351df1fad178532cd202e38ae959ee8cc97bbe32d96d0f94bfb458341da35ee

Open Dashboard for your personalized pricingSee plans / credit rules

Anthropic

9 models
claude-haiku-4-5
Input$1.00/1MOutput$5.00/1M
anthropicopenaiprompt-cache 90% off
claude-haiku-5-5
Input$0.10/1MOutput$0.50/1M
anthropicopenaiprompt-cache 90% off
claude-fable-5
Input$10.00/1MOutput$50.00/1M
anthropicopenaiprompt-cache 90% off
claude-opus-5
Input$5.00/1MOutput$25.00/1M
anthropicopenaiprompt-cache 90% off
claude-opus-5-5
Input$4.00/1MOutput$16.00/1M
anthropicopenaiprompt-cache 95% off
claude-sonnet-5-5
Input$2.00/1MOutput$10.00/1M
anthropicopenaiprompt-cache 95% off
claude-opus-4-8
Input$5.00/1MOutput$25.00/1M
anthropicopenaiprompt-cache 90% off
claude-fable-5-1
Input$10.00/1MOutput$50.00/1M
anthropicopenaiprompt-cache 98% off
claude-sonnet-5
Input$2.00/1MOutput$10.00/1M
anthropicopenaiprompt-cache 90% off

OpenAI

8 models
gpt-6.1-sol
Input$2.00/1MOutput$10.00/1M
openai-responseprompt-cache 95% off
gpt-6-astra
Input$10.00/1MOutput$250.00/1M
openai-responseprompt-cache 50% off
gpt-5.6-luna
Input$0.20/1MOutput$1.20/1M
openai-responseprompt-cache 90% off
gpt-5.6-sol
Input$5.00/1MOutput$30.00/1M
openai-responseprompt-cache 90% off
gpt-6-sol
Input$2.00/1MOutput$10.00/1M
openai-responseprompt-cache 90% off
gpt-5.6-terra
Input$2.00/1MOutput$12.00/1M
openai-responseprompt-cache 90% off
gpt-6-luna
Input$0.10/1MOutput$0.50/1M
openai-responseprompt-cache 90% off
gpt-5.5
Input$5.00/1MOutput$30.00/1M
openai-responseprompt-cache 90% off

MiniMax

1 model
MiniMax-M3
Input$0.30/1MOutput$1.20/1M
openaianthropicprompt-cache 80% off

DeepSeek

3 models
deepseek-v4.1-flash
Input$0.30/1MOutput$1.20/1M
openaianthropicprompt-cache 98% off
deepseek-v4-pro
Input$0.30/1MOutput$1.20/1M
openaianthropicprompt-cache 98% off
deepseek-v4-flash
Input$0.30/1MOutput$1.20/1M
openaianthropicprompt-cache 98% off

Moonshot

2 models
kimi-k2.7-code
Input$0.95/1MOutput$4.00/1M
openaianthropicprompt-cache 80% off
kimi-k3
Input$3.00/1MOutput$15.00/1M
openaianthropicprompt-cache 90% off

Other

7 models
volc.seedasr.sauc.duration
Input$2.00/1MOutput$2.00/1M
audio-transcriptionaudio-stream
doubao-seed-2.0-lite
Input$0.08/1MOutput$0.49/1M
openaianthropicprompt-cache 80% off
glm-5.3-flash
Input$0.15/1MOutput$0.50/1M
openaianthropicprompt-cache 75% off
doubao-seed-2.0-mini
Input$0.03/1MOutput$0.27/1M
openaianthropicprompt-cache 80% off
doubao-embedding-vision
Input$0.10/1MOutput$0.10/1M
embeddings
seed-tts-2.0
Input$36.99/1MOutput$0.00/1M
audio-speech
glm-5.3
Input$0.77/1MOutput$2.68/1M
openaianthropicprompt-cache 75% off

How to call

OpenAI-compatible / chat completions. Just point any OpenAI SDK's baseURL at EveryAPI:

For China-first routing, use https://api-cn.everyapi.ai/v1

curl https://api.everyapi.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-everyapi-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.7-code",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

To switch models, set the model field to any id from the catalog above. Anthropic models can alternatively go through the /v1/messages (Anthropic protocol) endpoint, and Gemini models can go through /v1beta/models/{model}:generateContent. See the /integrations page for details.

Live pricing version: e351df1fad178532cd202e38ae959ee8cc97bbe32d96d0f94bfb458341da35ee