Overview
Provider Type
APIAPI Endpoint
https://api.runcrate.ai/v1
Free Tier Highlights
Why Choose Runcrate (free inference)?
Free weekly allowance on strong open models including DeepSeek V4.1 Flash and GLM 5.3, sign-up with GitHub and no card needed.
Quick Start Guide
Sign in at https://www.runcrate.ai/inference/free with a GitHub account at least 30 days old
Create an API key in the console
Point your client at https://api.runcrate.ai/v1 and use one of the free model ids
Available Models
5 free models| Model Name | ID | Context | |
|---|---|---|---|
| DeepSeek V4.1 Flash (deepseek-ai/DeepSeek-V4.1-Flash) Free | - |
See provider |
|
| GLM 5.3 Flash (zai-org/GLM-5.3-Flash) Free | - |
See provider |
|
| GLM 5.3 (zai-org/GLM-5.3) Free | - |
See provider |
|
| gpt-oss 120B (openai/gpt-oss-120b) Free | - |
See provider |
|
| Qwen3.8 Flash (Qwen/Qwen3.8-Flash) Free | - |
See provider |
Free Tier Pricing & Limits
Rate Limit
Requests per minute
Daily Quota
Requests per day
Token Limit
Tokens per minute
Monthly Quota
Per month limit
Use Cases
Coding agents (Claude Code, Codex, OpenCode, Cline, Roo Code, Kilo Code)
Prototyping with open models
Limitations & Considerations
Free usage is capped per week and only resets on Monday
One allowance per GitHub account; Google sign-ups need a card on file
Free capacity is shared and can return overload errors when busy
Exact free limits are not published; they're shown in the dashboard
Community Hub
LiveJoin the discussion, share tips, and rate Runcrate (free inference).
Quick Reactions
Add Discussion
Comments are moderated. Be helpful and respectful.