Cohere coding model for practical software engineering and agentic edits
https://openrouter.ai/api/v1 cohere/north-mini-code:free | Benchmark | Score | Metric | Date |
|---|---|---|---|
| SWE-Bench Verified | 67.6 | resolved | 2026-06-09 |
| SWE-Bench Pro | 40.2 | resolve rate | 2026-06-09 |
| Artificial Analysis Intelligence Index | 27.6 | index score | 2026-06-09 |
| Artificial Analysis Coding Index | 33.4 | index score | 2026-06-09 |
Cohere: North Mini Code (free) is listed for chat, coding workloads and supports a 256K context window.
Use it when OpenRouter's free tier is enough for evaluation, demos, or light production traffic.
We found 2 provider listings for north-mini-code. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Cohere: North Mini Code (free) | Free tier | 256K | OpenAI-style | 200 req/day (free tier) |
| | cohere/north-mini-code:free | Free tier | 256K | OpenAI-style | ~200 req/hr |
| Model | Provider | Context | Access |
|---|---|---|---|
| cohere/north-mini-code:free | Kilo Code | 256K | Free tier |
| Poolside: Laguna S 2.1 (free) | OpenRouter | 262K | Free tier |
| Poolside: Laguna XS 2.1 (free) | OpenRouter | 262K | Free tier |
| NVIDIA: Nemotron 3.5 Content Safety (free) | OpenRouter | 128K | Free tier |
| NVIDIA: Nemotron 3 Ultra (free) | OpenRouter | 1.0M | Free tier |
Cohere: North Mini Code (free) is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Cohere: North Mini Code (free) is tagged for coding in this catalog and works with OpenAI-compatible client libraries.
Cohere: North Mini Code (free) is listed with free API access on OpenRouter, subject to the provider's quota and account policy.
The model ID shown in this catalog is cohere/north-mini-code:free.
The listed free tier limit is 200 req/day (free tier). Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 256K tokens with up to 64K output tokens.
Cohere coding model for practical software engineering and agentic edits
For API keys, setup steps, and provider-level limits, see the OpenRouter provider page.