Granite Provider

Granite is a stealth provider with OpenAI-compatible chat completions endpoints.

Available Models

GLM-5.2

glm
glm-5.2
Streaming
Tools
Reasoning
JSON Output
Granite
Context: 1M
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens

Qwen3.7 Max

alibaba
qwen3.7-max
Streaming
Tools
Reasoning
JSON Output
Granite
Context: 1M
Input
$2.5
/M tokens
Cached
$0.5
/M tokens
Output
$7.5
/M tokens