North Mini Code (free)
FREEby Cohere · cohere/north-mini-code:free
Prices updated Jul 22, 2026, 1:32 AM UTC · refreshed hourly
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
Free
per 1M tokens
Output
Free
per 1M tokens
Blended (3:1)
Free
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for North Mini Code (free) (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | Free | $0 | — |
| 50% | Free | $0 | −0% |
| 90% | Free | $0 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0 | $0 |
| Document summary | 8,000 | 1,000 | $0 | $0 |
| Codebase question (RAG) | 30,000 | 2,000 | $0 | $0 |
| Long-context analysis | 150,000 | 5,000 | $0 | $0 |
Performance
Intelligence Index
19.8
AA composite quality
Coding Index
36.5
Math Index
—
Agentic Index
3.1
Output speed
96 tok/s
median
Time to first token
0.24s
median
Time to first answer
21.06s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 75.7% |
| Humanity's Last Exam | 10.0% |
| SciCode | 38.2% |
| IFBench | 57.6% |
| AA-LCR (Long Context Reasoning) | 32.3% |
| Terminal-Bench Hard | 31.1% |
| Terminal-Bench 2.1 | 35.6% |
| τ²-Bench (Telecom) | 37.4% |
| τ³-Bench Banking | 6.4% |
Specs
Context window
256K
tokens
Max output
64K
tokens
Input modalities
text
Tokenizer
Cohere