ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral 25.08 vs Laguna XS 2.1 vs North Mini Code

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    34/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  2. Poolside

    Laguna XS 2.1

    Released Jul 2, 2026

    38/100
    • ECI—
    • PriceFree / Free
    • Context262K
  3. Cohere

    North Mini Code

    Released Jun 9, 2026

    38/100
    • ECI—
    • PriceFree / Free
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Laguna XS 2.1 38/100, North Mini Code 38/100, Codestral 25.08 34/100) compare the available specifications only. 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 priceLaguna XS 2.1 and North Mini CodeLaguna XS 2.1 Free · North Mini Code Free · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextLaguna XS 2.1Laguna XS 2.1 262,144 · North Mini Code 256,000 · Codestral 25.08 128,000 tokens
  • Widest inputsSame inputsCodestral 25.08: Text · Laguna XS 2.1: Text · North Mini Code: Text
  • Self-hostingLaguna XS 2.1 and North Mini CodePublishes downloadable weights
How the score is built
MeasureWeightCodestral 25.08Laguna XS 2.1North Mini Code
Inputs & features60%353535
Context window40%324343
Specs only100%34/10038/10038/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Codestral 25.08 vs Laguna XS 2.1 vs North Mini Code specifications side by side
SpecificationCodestral 25.08Mistral AILaguna XS 2.1PoolsideNorth Mini CodeCohere
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30Free (best)Free (best)
Output$0.90Free (best)Free (best)
Cached input$0.03——
Blended (3:1)$0.45Free (best)Free (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Poolside APIOfficial Cohere API
Limits
Context window128,000 tokens262,144 tokens (best)256,000 tokens
Max output8,192 tokens32,768 tokens64,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesYeshigh
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenOpen
API model IDcodestral-2508poolside/laguna-xs-2.1north-mini-code-1-0
API providers11 (best)34
ReleasedJul 30, 2025Jul 2, 2026Jun 9, 2026
Knowledge cutoff——Sep 23, 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Codestral 25.08$4.80
  • Laguna XS 2.1Free
  • North Mini CodeFree
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, Laguna XS 2.1 or North Mini Code?

There is not enough shared capability evidence to name an overall winner. The scores (Laguna XS 2.1 38/100, North Mini Code 38/100, Codestral 25.08 34/100) compare the available specifications only. 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, Codestral 25.08, Laguna XS 2.1 or North Mini Code?

Laguna XS 2.1 is cheaper at Free input / Free output per million tokens (official Poolside API price). North Mini Code costs Free input / Free output per million tokens (official Cohere API price); Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price). Laguna XS 2.1 is listed as free.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, Laguna XS 2.1 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 Codestral 25.08, Laguna XS 2.1 and North Mini Code 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 128,000 for Codestral 25.08. Maximum output per response: Codestral 25.08 up to 8,192, Laguna XS 2.1 up to 32,768, North Mini Code up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; Laguna XS 2.1 accepts text; North Mini Code accepts text. They handle the same number of input types.

Are any of these open source?

Laguna XS 2.1 and North Mini Code publishes its weights and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Laguna XS 2.1 is the newest, released Jul 2, 2026. North Mini Code came out Jun 9, 2026; Codestral 25.08 came out Jul 30, 2025. Knowledge cutoff: North Mini Code Sep 23, 2025.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 18, 2026.