Cohere coding model for practical software engineering and agentic editsNorth Mini Code by cohere is offered by 2 providers on this page. Its official list price is $0 per 1M tokens. It also has 2 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 3.4 on the Intelligence Index, with 9.9 for Engineering, its strongest domain. Median output speed is 212 tokens per second, with 0.37s to the first token.
The context window is 256,000 tokens, with an output limit of 64,000 tokens. It supports reasoning and tool use. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2025-09-23.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 2 providers.
This model is $0 across all listed channels (Cohere, OpenCode).
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | harness: SWE-agent | 67.6 | resolved | Source ↗ |
| SWE-Bench Pro | harness: SWE-agent | 40.2 | resolve rate | Source ↗ |
| Artificial Analysis Intelligence Index | — | 27.6 | index score | Source ↗ |
| Artificial Analysis Coding Index | — | 33.4 | index score | Source ↗ |
| GDPval-AA | — | 14 | win rate | Source ↗ |
| τ²-Bench Telecom | — | 37 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.