Fugu vs North Mini Code
Fugu comes out ahead, 66 to 41 on our weighted score.
- Our pick
Sakana AI
Fugu
66/100- ECI—
- Price—
- Context1M
CohereNorth Mini Code
41/100- ECI—
- PriceFree / Free
- Context256K
Add a model
Make it a three-way comparison.
Fugu is our pick
Fugu is the better all-round choice, scoring 66/100 against North Mini Code (41). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNorth Mini CodeNorth Mini Code Free per 1M tokens (3:1 blend) · Fugu unpriced
- Longest contextFuguFugu 1,000,000 · North Mini Code 256,000 tokens
- Widest inputsFuguFugu: Text, Images · North Mini Code: Text
- Self-hostingNorth Mini CodePublishes downloadable weights
| Measure | Weight | Fugu | North Mini Code |
|---|---|---|---|
| Inputs & features | 60% | 70 | 45 |
| Context window | 40% | 60 | 36 |
| Overall | 100% | 66/100 | 41/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | FuguSakana AI | North Mini CodeCohere |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | — | Free |
| Output | — | Free |
| Cached input | — | — |
| Blended (3:1) | — | Free |
| Long-context rate | — | Same rate |
| Price source | — | Official Cohere API |
| Limits | ||
| Context window | 1,000,000 tokens (best) | 256,000 tokens |
| Max output | — | 64,000 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yeshigh · xhigh | Yeshigh |
| Tool calling | Yes | Yes |
| Structured output | Yes | Yes |
| Availability | ||
| Weights | Proprietary | Open |
| API model ID | fugu | north-mini-code-1-0 |
| API providers | 1 | 2 (best) |
| Released | Jun 15, 2026 | Jun 9, 2026 |
| Knowledge cutoff | — | Sep 23, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Fugu—
- North Mini CodeFree
Which should you choose?
Which is better: Fugu or North Mini Code?
Fugu is the better all-round choice, scoring 66/100 against North Mini Code (41). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Fugu or North Mini Code?
North Mini Code is cheaper at Free input / Free output per million tokens (official Cohere API price). . North Mini Code is listed as free. Fugu has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Fugu has not been scored yet and North Mini Code has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Fugu and North Mini Code yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.
Which has the bigger context window?
Fugu has the largest context window at 1,000,000 tokens, against 256,000 for North Mini Code. Maximum output per response: North Mini Code up to 64,000 tokens.
Which can read images, PDFs, audio or video?
Fugu accepts text and images; North Mini Code accepts text. Fugu handles the widest range of inputs.
Are any of these open source?
North Mini Code publishes its weights and can be self-hosted; Fugu is proprietary.
Which is newer?
Fugu is the newest, released Jun 15, 2026. North Mini Code came out Jun 9, 2026. Knowledge cutoff: North Mini Code Sep 23, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
