North Mini Code vs Voxtral Mini 3B 2507 vs Laguna XS 2.1
Too close to call on our weighted score (Laguna XS 2.1 68, North Mini Code 68, Voxtral Mini 3B 2507 61). The right pick depends on what you value most.
CohereNorth Mini Code
68/100- ECI—
- PriceFree / Free
- Context256K
Mistral AIVoxtral Mini 3B 2507
61/100- ECI—
- Price$0.04 / $0.04
- Context33K
PoolsideLaguna XS 2.1
68/100- ECI—
- PriceFree / Free
- Context262K
Too close to call
It is close. Our weighted score puts them within a point (Laguna XS 2.1 68/100, North Mini Code 68/100, Voxtral Mini 3B 2507 61/100), so choose by what matters most for your work: North Mini Code on price and Laguna XS 2.1 for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. 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 Code and Laguna XS 2.1North Mini Code Free · Laguna XS 2.1 Free · Voxtral Mini 3B 2507 $0.04 per 1M tokens (3:1 blend)
- Longest contextLaguna XS 2.1Laguna XS 2.1 262,144 · North Mini Code 256,000 · Voxtral Mini 3B 2507 32,768 tokens
- Widest inputsVoxtral Mini 3B 2507North Mini Code: Text · Voxtral Mini 3B 2507: Text, Audio · Laguna XS 2.1: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | North Mini Code | Voxtral Mini 3B 2507 | Laguna XS 2.1 |
|---|---|---|---|---|
| Price | 50% | 100 | 100 | 100 |
| Inputs & features | 30% | 35 | 35 | 35 |
| Context window | 20% | 36 | 0 | 37 |
| Overall | 100% | 68/100 | 61/100 | 68/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | North Mini CodeCohere | Voxtral Mini 3B 2507Mistral AI | Laguna XS 2.1Poolside |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | Free (best) | $0.04 | Free (best) |
| Output | Free (best) | $0.04 | Free (best) |
| Cached input | — | — | — |
| Blended (3:1) | Free (best) | $0.04 | Free (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Median of 2 providers | Official Poolside API |
| Limits | |||
| Context window | 256,000 tokens | 32,768 tokens | 262,144 tokens (best) |
| Max output | 64,000 tokens (best) | 32,768 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | Yes | No |
| Video | No | No | No |
| Reasoning | Yeshigh | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenApache 2.0 | Open |
| API model ID | north-mini-code-1-0 | — | poolside/laguna-xs-2.1 |
| API providers | 4 (best) | 3 | 3 |
| Released | Jun 9, 2026 | Jul 15, 2025 | Jul 2, 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.
- North Mini CodeFree
- Voxtral Mini 3B 2507$0.48
- Laguna XS 2.1Free
Which should you choose?
Which is better: North Mini Code, Voxtral Mini 3B 2507 or Laguna XS 2.1?
It is close. Our weighted score puts them within a point (Laguna XS 2.1 68/100, North Mini Code 68/100, Voxtral Mini 3B 2507 61/100), so choose by what matters most for your work: North Mini Code on price and Laguna XS 2.1 for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, North Mini Code, Voxtral Mini 3B 2507 or Laguna XS 2.1?
North Mini Code is cheaper at Free input / Free output per million tokens (official Cohere API price). Laguna XS 2.1 costs Free input / Free output per million tokens (official Poolside API price); Voxtral Mini 3B 2507 costs $0.04 input / $0.04 output per million tokens (median across 2 API providers). North Mini Code is listed as free.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. North Mini Code has not been scored yet, Voxtral Mini 3B 2507 has not been scored yet and Laguna XS 2.1 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for North Mini Code, Voxtral Mini 3B 2507 and Laguna XS 2.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Laguna XS 2.1 has the largest context window at 262,144 tokens, against 256,000 for North Mini Code and 32,768 for Voxtral Mini 3B 2507. Maximum output per response: North Mini Code up to 64,000, Voxtral Mini 3B 2507 up to 32,768, Laguna XS 2.1 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
North Mini Code accepts text; Voxtral Mini 3B 2507 accepts text and audio; Laguna XS 2.1 accepts text. Voxtral Mini 3B 2507 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
Laguna XS 2.1 is the newest, released Jul 2, 2026. North Mini Code came out Jun 9, 2026; Voxtral Mini 3B 2507 came out Jul 15, 2025. 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 Nov 2, 2026.
