Cohere: North Mini Code (free) vs DeepSeek: DeepSeek V4 Flash 0731
Based on weekly OpenRouter usage tracked by AI Tier List, DeepSeek: DeepSeek V4 Flash 0731 ranks #1 overall — ahead of Cohere: North Mini Code (free) at #38. Cohere: North Mini Code (free) is cheaper on input tokens at Free/1M vs $0.14/1M for DeepSeek: DeepSeek V4 Flash 0731. DeepSeek: DeepSeek V4 Flash 0731 offers the larger context window at 1M tokens.
Cohere: North Mini Code (free) vs DeepSeek: DeepSeek V4 Flash 0731: which should you use?
Choose Cohere: North Mini Code (free) if…
- Cheaper to read — Free vs $0.14 per 1M input tokens, which is what dominates long-prompt and RAG workloads.
- Cheaper to write — Free vs $0.28 per 1M output tokens, the line item that decides generation-heavy costs.
Choose DeepSeek: DeepSeek V4 Flash 0731 if…
- It sees more real traffic — #1 overall on OpenRouter's weekly ranking, against #38 for Cohere: North Mini Code (free).
- Bigger context window — 1M vs 256K tokens.
- Higher Artificial Analysis intelligence index — 51.8 vs 20.2.
- Higher Artificial Analysis coding score — 69.1 vs 36.5.
- Higher Artificial Analysis agentic score — 48.4 vs 3.1.
- It is the newer model — released Jul 2026 against Jun 2026.
Spec Comparison
| Spec | Cohere: North Mini Code (free) | DeepSeek: DeepSeek V4 Flash 0731 |
|---|---|---|
| Author | cohere | deepseek |
| Input price (per 1M tokens) | Free | $0.14 |
| Output price (per 1M tokens) | Free | $0.28 |
| Context window | 256K | 1M |
| Input modalities | text | text |
| Output modalities | text | text |
| AA Intelligence | 20.2 | 51.8 |
| AA Coding | 36.5 | 69.1 |
| AA Agentic | 3.1 | 48.4 |
| Released | Jun 2026 | Jul 2026 |
What Cohere: North Mini Code (free) and DeepSeek: DeepSeek V4 Flash 0731 actually cost to run
On a read-heavy job — 1M tokens in, 100K out — Cohere: North Mini Code (free) costs $0.00 and DeepSeek: DeepSeek V4 Flash 0731 costs $0.17.
Flip the shape — 100K in, 1M out — and it becomes $0.00 for Cohere: North Mini Code (free) versus $0.29 for DeepSeek: DeepSeek V4 Flash 0731.
Both figures are the published per-token rates multiplied out; caching and batch discounts are not included.
Usage Rank by Task
| Task | Cohere: North Mini Code (free) | DeepSeek: DeepSeek V4 Flash 0731 |
|---|---|---|
| Overall | #38 | #1 |
| Memory Extraction | — | #6 |
| Multi-step Planning | — | #2 |
| Tool Dispatch | — | #2 |
| Web Search | — | #4 |
| Agent Workflows | — | #5 |
| Classification & Tagging | — | #9 |
| Debugging | — | #3 |
| DevOps Config | — | #2 |
| File Read/Write | — | #3 |
| Frontend UI | — | #2 |
| Code Implementation | — | #3 |
| Repo Analysis | — | #3 |
| Code Review & Security | — | #3 |
| Shell Execution | — | #6 |
About Cohere: North Mini Code (free) and DeepSeek: DeepSeek V4 Flash 0731
Cohere: North Mini Code (free)
Built by cohere · released Jun 2026 · 256K-token context
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...
DeepSeek: DeepSeek V4 Flash 0731
Built by deepseek · released Jul 2026 · 1M-token context
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Related comparisons
- Cohere: North Mini Code (free) vs Tencent: Hy3
- Cohere: North Mini Code (free) vs OpenAI: GPT-5.6 Luna (batch)
- Cohere: North Mini Code (free) vs DeepSeek: DeepSeek V4 Flash 0423
- DeepSeek: DeepSeek V4 Flash 0731 vs Tencent: Hy3
- DeepSeek: DeepSeek V4 Flash 0731 vs OpenAI: GPT-5.6 Luna (batch)
- DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4 Flash 0423
Get notified when Cohere: North Mini Code (free) or DeepSeek: DeepSeek V4 Flash 0731 moves
Usage ranks and prices refresh weekly. We email you when they move — once a week, no spam.
FAQ
Which is better, Cohere: North Mini Code (free) or DeepSeek: DeepSeek V4 Flash 0731?
Based on weekly OpenRouter usage tracked by AI Tier List, DeepSeek: DeepSeek V4 Flash 0731 ranks #1 overall — ahead of Cohere: North Mini Code (free) at #38. Cohere: North Mini Code (free) is cheaper on input tokens at Free/1M vs $0.14/1M for DeepSeek: DeepSeek V4 Flash 0731. DeepSeek: DeepSeek V4 Flash 0731 offers the larger context window at 1M tokens.
Which is cheaper, Cohere: North Mini Code (free) or DeepSeek: DeepSeek V4 Flash 0731?
Cohere: North Mini Code (free) is cheaper at Free per 1M input tokens. Output pricing: Cohere: North Mini Code (free) Free, DeepSeek: DeepSeek V4 Flash 0731 $0.28.
Which is better for coding, Cohere: North Mini Code (free) or DeepSeek: DeepSeek V4 Flash 0731?
DeepSeek: DeepSeek V4 Flash 0731. Artificial Analysis coding scores: Cohere: North Mini Code (free) 36.5, DeepSeek: DeepSeek V4 Flash 0731 69.1. Best coding-task usage rank this week: Cohere: North Mini Code (free) —, DeepSeek: DeepSeek V4 Flash 0731 #2.
Is DeepSeek: DeepSeek V4 Flash 0731 still ahead of Cohere: North Mini Code (free) right now?
Yes. For the week of 2026-08-10, DeepSeek: DeepSeek V4 Flash 0731 ranks #1 overall on OpenRouter usage against #38 for Cohere: North Mini Code (free). Ranks refresh weekly, and the verdict on this page flips if they cross.
Usage ranks are weekly data aggregated by OpenRouter. Prices are USD per 1M tokens.