Overview
Provider Type
ProxyAPI Endpoint
https://router.requesty.ai/v1
Free Tier Highlights
Why Choose Requesty?
Requesty is an AI gateway with automatic fallback, caching and load balancing, and a built-in free tier of 200 requests per day on free models such as Gemma 4 31B, Nemotron 3 Nano and Mistral Leanstral, with no card.
Best for: apps that want routing and fallback features from day one.
Watch out: 20 requests/minute and 200 a day for new organizations, shared across free models.
Quick Start Guide
Visit https://requesty.ai/
Sign up for free account
Add your provider API keys
Get Requesty API key
Use as OpenAI-compatible proxy
Available Models
8 free models| Model Name | ID | Context | Capabilities | |
|---|---|---|---|---|
| Gemma 4 31B IT Free |
google/gemma-4-31b-it
|
262 000 Context |
- | |
| Nemotron 3 Nano Omni Reasoning Free |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
|
131 000 Context |
- | |
| Nemotron 3 Nano 30B A3B Free |
nvidia/nemotron-3-nano-30b-a3b
|
262 000 Context |
- | |
| Mistral Leanstral 1.5 Free |
mistral/leanstral-1-5
|
262 000 Context |
- | |
| Meta Muse Glimmer 30B Free |
nvidia/muse-glimmer-30b
|
131 000 Context |
- | |
| inclusionAI Ling 3.1 Flash Free |
novita/ling-3.1-flash
|
262 000 Context |
- | |
| Nemotron 3.5 Lightning 30B A3B Free |
nvidia/nemotron-3.5-lightning-30b-a3b
|
1 000 000 Context |
- | |
| NVIDIA Nemotron 3 Ultra Free |
nvidia/nemotron-3-ultra-550b-a55b
|
1 000 000 Context |
- |
Integration Examples
Ready-to-use code snippets for your applications.
Select Model
Free Tier Pricing & Limits
Rate Limit
Requests per minute
Daily Quota
Requests per day
Token Limit
Tokens per minute
Use Cases
High-availability AI applications
Cost optimization across providers
Multi-model comparison
Production AI infrastructure
Limitations & Considerations
Requires underlying provider API keys
Free credit amount is limited
Routing adds minimal latency
Some models require paid provider keys
Community Hub
LiveJoin the discussion, share tips, and rate Requesty.
Quick Reactions
Add Discussion
Comments are moderated. Be helpful and respectful.