Codestral 2 vs Grok 3
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 3 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 128K, 2.0× 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.
- ModalitiesGrok 3
Grok 3 supports 2 modalities (text, vision) vs 1 for Codestral 2.
- OpennessCodestral 2
Codestral 2 ships open weights (Mistral Non-Production License); Grok 3 is API-only.
On balance Codestral 2 edges ahead, winning 3 of 5 categories against Grok 3'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 128K, 2.0× 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, Codestral 2 handles text while Grok 3 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 3 is API-only.
Grok 3 is the newer of the two, released 1 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 3 sees more deployments in chatbots 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
| Spec | Codestral 2 | Grok 3 |
|---|---|---|
| Provider | Mistral | xAI |
| Released | Jan 2025 | Feb 2025 |
| Modalities | text | text, vision |
| Context window | 256K tokens | 128K 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 | , | 2024-08 |
| Open weights | Yes (Mistral Non-Production License) | No |
| 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$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.
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 3$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.
- HumanEval92.0
Codestral 2 fits when…
- Fast inline completion
- FIM support
- Self-hostable for IP-sensitive teams
- Cost-sensitive workloads, 16.7× cheaper than Grok 3 on output tokens.
- Long-context tasks, handles 256K tokens vs 128K for Grok 3.
Grok 3 fits when…
- Real-time X access
- Reasoning modes
- Multimodal needs covering vision.
Consider Mistral Large 2
Mistral's flagship API model, strong on code and reasoning, EU-friendly hosting.
Frequently asked
Is Codestral 2 or Grok 3 cheaper?
Codestral 2 is cheaper at $0.90 / 1M tokens per million output tokens, vs $15.00 / 1M tokens for Grok 3.Which has the larger context window?
Codestral 2 accepts 256K tokens vs 128K for Grok 3.Is Codestral 2 or Grok 3 better for coding?
Both Codestral 2 and Grok 3 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 3 is API-only.When were Codestral 2 and Grok 3 released?
Codestral 2 was released by Mistral on 2025-01-14. Grok 3 was released by xAI on 2025-02-17.
The week's AI launches, in your inbox.
One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.