Claude Sonnet 4 vs Codestral 2
A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.
Updated
Claude Sonnet 4 specs · Codestral 2 specs- PriceCodestral 2
Codestral 2 is roughly 16.7× cheaper on output tokens ($0.90 vs $15.00 per 1M).
- Context windowCodestral 2
Codestral 2 accepts 256K tokens vs 200K, 1.3× the room for long documents and codebases.
- BenchmarksTie
No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.
- ModalitiesClaude Sonnet 4
Claude Sonnet 4 supports 2 modalities (text, vision) vs 1 for Codestral 2.
- OpennessCodestral 2
Codestral 2 ships open weights (Mistral Non-Production License); Claude Sonnet 4 is API-only.
On balance Codestral 2 edges ahead, winning 3 of 5 categories against Claude Sonnet 4's 1. Codestral 2 is roughly 16.7× cheaper on output tokens ($0.90 vs $15.00 per 1M). Codestral 2 accepts 256K tokens vs 200K, 1.3× the room for long documents and codebases.
No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. They differ in modality coverage, Claude Sonnet 4 handles text, vision while Codestral 2 handles text, which can be the deciding factor before you even look at benchmarks. Codestral 2 ships open weights (Mistral Non-Production License); Claude Sonnet 4 is API-only.
Claude Sonnet 4 is the newer of the two, released 4 months after Codestral 2, which usually means a more recent knowledge cutoff and updated safety post-training. Claude Sonnet 4 is usually picked for coding llm and rag workloads, while Codestral 2 sees more deployments in code completion and coding llm. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.
Side-by-side specs
| Spec | Claude Sonnet 4 | Codestral 2 |
|---|---|---|
| Provider | Anthropic | Mistral |
| Released | May 2025 | Jan 2025 |
| Modalities | text, vision | text |
| Context window | 200K tokens | 256K tokens |
| Max output | , | , |
| Input · 1M | $3.00 / 1M tokens | $0.30 / 1M tokens |
| Output · 1M | $15.00 / 1M tokens | $0.90 / 1M tokens |
| Knowledge cutoff | 2025-03 | , |
| Open weights | No | Yes (Mistral Non-Production License) |
| API available | Yes | Yes |
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$31.50 vs $2.25
- Heavy usage, 1M in / 500k out per day$315 vs $22.50
- RAG workload, 5M in / 200k out per day$540 vs $50.40
Light usage, 100k in / 50k out per day: $31.50 vs $2.25 per month, model B comes out ahead. Heavy usage, 1M in / 500k out per day: $315 vs $22.50 per month, model B comes out ahead. RAG workload, 5M in / 200k out per day: $540 vs $50.40 per month, model B comes out ahead.
Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.
- Claude Sonnet 4$1.05
- Codestral 2$0.075
Benchmarks compared
Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.
- HumanEval,92.0
- SWE-bench Verified65.0
Claude Sonnet 4 fits when…
- Solid all-rounder
- Mature deployment ecosystem
- Multimodal needs covering vision.
Codestral 2 fits when…
- Fast inline completion
- FIM support
- Self-hostable for IP-sensitive teams
- Cost-sensitive workloads, 16.7× cheaper than Claude Sonnet 4 on output tokens.
- Self-hosting and on-prem requirements, open weights (Mistral Non-Production License).
Consider Claude Opus 4.7
Anthropic's mid-2026 flagship, ahead on SWE-bench, agent reliability, and writing quality.
Frequently asked
Is Claude Sonnet 4 or Codestral 2 cheaper?
Codestral 2 is cheaper at $0.90 / 1M tokens per million output tokens, vs $15.00 / 1M tokens for Claude Sonnet 4.Which has the larger context window?
Codestral 2 accepts 256K tokens vs 200K for Claude Sonnet 4.Is Claude Sonnet 4 or Codestral 2 better for coding?
Both Claude Sonnet 4 and Codestral 2 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). Claude Sonnet 4 is API-only.When were Claude Sonnet 4 and Codestral 2 released?
Claude Sonnet 4 was released by Anthropic on 2025-05-22. Codestral 2 was released by Mistral on 2025-01-14.
The week's AI launches, in your inbox.
One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.