LLM·Dex
Newsletter

Codestral 2 vs Grok 4

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Updated

Codestral 2 specs · Grok 4 specs
Verdict by category
  • PriceCodestral 2

    Codestral 2 is roughly 16.7× cheaper on output tokens ($0.90 vs $15.00 per 1M).

  • Context windowTie

    Both ship a 256K-token context window.

  • BenchmarksTie

    No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.

  • ModalitiesGrok 4

    Grok 4 supports 2 modalities (text, vision) vs 1 for Codestral 2.

  • OpennessCodestral 2

    Codestral 2 ships open weights (Mistral Non-Production License); Grok 4 is API-only.

On balance Codestral 2 edges ahead, winning 2 of 5 categories against Grok 4's 1. Codestral 2 is roughly 16.7× cheaper on output tokens ($0.90 vs $15.00 per 1M). Both ship a 256K-token context window.

No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. They differ in modality coverage, Codestral 2 handles text while Grok 4 handles text, vision, which can be the deciding factor before you even look at benchmarks. Codestral 2 ships open weights (Mistral Non-Production License); Grok 4 is API-only.

Grok 4 is the newer of the two, released 6 months after Codestral 2, which usually means a more recent knowledge cutoff and updated safety post-training. Codestral 2 is usually picked for code completion and coding llm workloads, while Grok 4 sees more deployments in reasoning and research agent. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecCodestral 2Grok 4
ProviderMistralxAI
ReleasedJan 2025Jul 2025
Modalitiestexttext, vision
Context window256K tokens256K tokens
Max output,,
Input · 1M$0.30 / 1M tokens$3.00 / 1M tokens
Output · 1M$0.90 / 1M tokens$15.00 / 1M tokens
Knowledge cutoff,2024-11
Open weightsYes (Mistral Non-Production License)No
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day$2.25 vs $31.50
  • Heavy usage, 1M in / 500k out per day$22.50 vs $315
  • RAG workload, 5M in / 200k out per day$50.40 vs $540

Light usage, 100k in / 50k out per day: $2.25 vs $31.50 per month, model A comes out ahead. Heavy usage, 1M in / 500k out per day: $22.50 vs $315 per month, model A comes out ahead. RAG workload, 5M in / 200k out per day: $50.40 vs $540 per month, model A comes out ahead.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Codestral 2$0.075
  • Grok 4$1.05

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Codestral 2Grok 4
  • HumanEval92.0
  • GPQA,87.5
Pick Codestral 2 if

Codestral 2 fits when…

  • Fast inline completion
  • FIM support
  • Self-hostable for IP-sensitive teams
  • Cost-sensitive workloads, 16.7× cheaper than Grok 4 on output tokens.
  • Self-hosting and on-prem requirements, open weights (Mistral Non-Production License).
Pick Grok 4 if

Grok 4 fits when…

  • Real-time X data access
  • Strong on benchmarks at launch
  • Less restrictive content policy than peers
  • Multimodal needs covering vision.
Don't want either?

Consider Mistral Large 2

Mistral's flagship API model, strong on code and reasoning, EU-friendly hosting.

See Mistral Large 2 specsCodestral 2 vs Mistral Large 2Grok 4 vs Mistral Large 2

Frequently asked

  • Is Codestral 2 or Grok 4 cheaper?
    Codestral 2 is cheaper at $0.90 / 1M tokens per million output tokens, vs $15.00 / 1M tokens for Grok 4.
  • Which has the larger context window?
    Both Codestral 2 and Grok 4 ship a 256K-token context window.
  • Is Codestral 2 or Grok 4 better for coding?
    Both Codestral 2 and Grok 4 are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Codestral 2 ships open weights (Mistral Non-Production License). Grok 4 is API-only.
  • When were Codestral 2 and Grok 4 released?
    Codestral 2 was released by Mistral on 2025-01-14. Grok 4 was released by xAI on 2025-07-09.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.