OpenAI-compatible models via Claudible
Enterprise-grade reliability with 99.9% uptime. Token-based pricing with cache hit/miss aware billing. Drop-in OpenAI Chat Completions format.
99.9% Uptime
SLA
Cache-aware
Billing
OpenAI
Compatible
100%
Available
Service Status
100%
7-day availability
Send your first request
Endpoint
POST
https://cn.claudible.io/v1/chat/completions
curl https://cn.claudible.io/v1/chat/completions \
-H "Authorization: Bearer YOUR_CLAUDIBLE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Hello"}]}'Models & pricing
| Model | Input miss | Input hit | Output |
|---|---|---|---|
deepseek-flash | 8 | 0.16 | 16 |
deepseek-v4-flash | 8 | 0.16 | 16 |
deepseek-v4-flash-vision-exp | 8 | 0.16 | 16 |
deepseek-v4-pro | 80 | 1 | 160 |
glm-5.1 | 320 | 4 | 640 |
glm-5.2 | 320 | 4 | 640 |
glm-5.3 | 320 | 4 | 640 |
glm-5.3-flash | 34 | 0.46 | 73 |
hy3 | 8 | 2 | 33 |
hy4-preview | 48 | 2.4 | 143 |
kimi-k2.6 | 240 | 3 | 480 |
kimi-k2.7-code | 240 | 3.6 | 480 |
kimi-k3 | 758 | 5.6 | 1800 |
longcat-2.0 | 17 | 0.34 | 69 |
mimo-v2.5 | 8 | 0.16 | 16 |
mimo-v2.5-pro | 80 | 1 | 160 |
minimax-m2.5 | 17 | 3.4 | 69 |
minimax-m3 | 17 | 3.4 | 69 |
qwen3.6-plus | 84 | 1.05 | 168 |
qwen3.7-max | 115 | 23 | 345 |
qwen3.7-plus | 18 | 1.84 | 74 |
qwen3.8-flash | 7 | 0.74 | 22 |
qwen3.8-max | 92 | 11.5 | 276 |
credits / 1M tokens
Provider docs: api-docs.deepseek.com ↗