OpenRouter Free AI Models
Free :free chat, embedding and rerank models at $0 through OpenRouter's API
What you get from OpenRouter Free AI Models for free
OpenRouter offers a rotating collection of zero-cost model variants (IDs ending in :free) accessible via a unified OpenAI-compatible API for developer experimentation and prototyping.
Currently Listed Free Models
As of 2026-10-21, 24 free variants are listed: 17 text chat models, including MiniMax M3.1 Flash, Xing4.0 29B A4B, Dots3-Note Preview, LFM2.5-2.6B, Nemotron 3.5 (Lightning, Super VL, Content Safety), Nemotron 3 (Ultra, Super, Nano Omni), Inkling and Inkling Small, Laguna S and XS 2.1, North Mini Code, and Gemma 4 26B/31B, plus 3 embedding models, 1 reranker, 2 decision models and 1 text-to-speech model.
Rate Limits
Per OpenRouter's limits documentation, free variants are capped at 20 requests per minute. Daily caps depend on lifetime credit purchases: 50 requests/day for accounts that have bought fewer than 10 credits, and 1,000 requests/day once at least 10 credits have been purchased. Limits are per account and enforced globally.
Notes
The free lineup rotates frequently as models are added and removed; check the free models page for the current set.
Models served free
Limits as the provider publishes them; a dash means none is published.
| Model | Context | RPM | RPD | TPM | Tools | Vision |
|---|---|---|---|---|---|---|
| NVIDIA: Nemotron 3 Ultra (free)All :free variants: 20 RPM; 50 RPD without credits, 1,000 RPD after 10+ credits | 1,000k | 20 | 50 | — | yes | no |
| MiniMax: MiniMax M3.1 Flash (free)Shared free-variant limits | 1,000k | 20 | 50 | — | yes | yes |
| XingChen: Xing4.0 29B A4B (free)Shared free-variant limits | 262k | 20 | 50 | — | yes | no |
| NVIDIA: Nemotron 3.5 Super VL (free)Shared free-variant limits | 1,000k | 20 | 50 | — | yes | yes |
| Dots Studio: Dots3-Note Preview (free)Shared free-variant limits | 512k | 20 | 50 | — | yes | yes |
| LiquidAI: LFM2.5-2.6B (free)Shared free-variant limits | 66k | 20 | 50 | — | yes | no |
| NVIDIA: Nemotron 3.5 Lightning (free)Shared free-variant limits | 1,000k | 20 | 50 | — | yes | no |
| Thinking Machines: Inkling Small (free)Shared free-variant limits | 1,049k | 20 | 50 | — | yes | yes |
| Poolside: Laguna S 2.1 (free)Shared free-variant limits; free use may train provider models | 262k | 20 | 50 | — | yes | no |
| Thinking Machines: Inkling (free)Shared free-variant limits | 1,049k | 20 | 50 | — | yes | yes |
| Poolside: Laguna XS 2.1 (free)Shared free-variant limits | 262k | 20 | 50 | — | yes | no |
| Cohere: North Mini Code (free)Shared free-variant limits | 256k | 20 | 50 | — | yes | no |
| NVIDIA: Nemotron 3.5 Content Safety (free)Shared free-variant limits | 128k | 20 | 50 | — | no | yes |
| NVIDIA: Nemotron 3 Nano Omni (free)Shared free-variant limits | 256k | 20 | 50 | — | yes | yes |
| Google: Gemma 4 26B A4B (free)Shared free-variant limits | 262k | 20 | 50 | — | yes | yes |
| Google: Gemma 4 31B (free)Shared free-variant limits | 262k | 20 | 50 | — | yes | yes |
| NVIDIA: Nemotron 3 Super (free)Shared free-variant limits | 262k | 20 | 50 | — | yes | no |
History
Verified by a person on · last automated check : no change found. Automated findings never change this page until a person confirms them (how we verify).
- Change detectedby the monitor · -1 pricing sentences
- Change detectedby the monitor · +6 pricing sentences
- Terms updatedby a person · Content updated from https://openrouter.ai/api/v1/models (checked 2026-10-21).
- Change detectedby the monitor · -1 pricing sentences
- Change detectedby the monitor · +1 pricing sentences
- Change detectedby the monitor · +59 pricing sentences
Still works?
Work at openrouter.ai? Add an aifree.dev badge
<a href="https://aifree.dev/offer/openrouter-free-models"><img src="https://aifree.dev/badge/openrouter-free-models" alt="OpenRouter Free AI Models on aifree.dev" height="20"></a>[](https://aifree.dev/offer/openrouter-free-models)Step-by-step guide
Understand it
A few minutes of play-along, no sign-up.
- Why does it miscount the r’s in "strawberry"? · Tokens · 3 min
- Why does the same prompt give different answers? · Temperature and sampling · 3 min
Compared in
More free coding tools
Related offers
Free tier - No expiration
$19.99 - 1 year
Free tier - Free text models: agnes-2.5-flash, agnes-3.0-flash
30,000,000 tokens/month - 30M tokens/month on the free tier (input + output, incl. reasoning)
6 months - 6 months of Pro-resources access, one-time per account
12 months - One-year license via the GitHub Student Pack