Codestral 2 vs GPT-5
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 · GPT-5 specs- PriceCodestral 2
Codestral 2 is roughly 11.1× cheaper on output tokens ($0.90 vs $10.00 per 1M).
- Context windowGPT-5
GPT-5 accepts 400K tokens vs 256K, 1.6× the room for long documents and codebases.
- BenchmarksGPT-5
GPT-5 leads in 1 of 1 shared benchmarks; the biggest gap is on HumanEval (Python coding), where it scores 96.2 vs 92.0.
- ModalitiesGPT-5
GPT-5 supports 3 modalities (text, vision, audio) vs 1 for Codestral 2.
- OpennessCodestral 2
Codestral 2 ships open weights (Mistral Non-Production License); GPT-5 is API-only.
On balance GPT-5 edges ahead, winning 3 of 5 categories against Codestral 2's 2. Codestral 2 is roughly 11.1× cheaper on output tokens ($0.90 vs $10.00 per 1M). GPT-5 accepts 400K tokens vs 256K, 1.6× the room for long documents and codebases.
GPT-5 leads in 1 of 1 shared benchmarks; the biggest gap is on HumanEval (Python coding), where it scores 96.2 vs 92.0. They differ in modality coverage, Codestral 2 handles text while GPT-5 handles text, vision, audio, which can be the deciding factor before you even look at benchmarks. Codestral 2 ships open weights (Mistral Non-Production License); GPT-5 is API-only.
GPT-5 is the newer of the two, released 7 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 GPT-5 sees more deployments in coding llm and agents. 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 | GPT-5 |
|---|---|---|
| Provider | Mistral | OpenAI |
| Released | Jan 2025 | Aug 2025 |
| Modalities | text | text, vision, audio |
| Context window | 256K tokens | 400K tokens |
| Max output | , | 128K tokens |
| Input · 1M | $0.30 / 1M tokens | $1.25 / 1M tokens |
| Output · 1M | $0.90 / 1M tokens | $10.00 / 1M tokens |
| Knowledge cutoff | , | 2024-09 |
| 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 $18.75
- Heavy usage, 1M in / 500k out per day$22.50 vs $188
- RAG workload, 5M in / 200k out per day$50.40 vs $248
Light usage, 100k in / 50k out per day: $2.25 vs $18.75 per month, model A comes out ahead. Heavy usage, 1M in / 500k out per day: $22.50 vs $188 per month, model A comes out ahead. RAG workload, 5M in / 200k out per day: $50.40 vs $248 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
- GPT-5$0.625
Benchmarks compared
Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.
- MMLU,91.4
- HumanEval92.096.2
- GPQA,89.4
- SWE-bench Verified,74.9
Codestral 2 fits when…
- Fast inline completion
- FIM support
- Self-hostable for IP-sensitive teams
- Cost-sensitive workloads, 11.1× cheaper than GPT-5 on output tokens.
- Self-hosting and on-prem requirements, open weights (Mistral Non-Production License).
GPT-5 fits when…
- Unified model, reasoning routed automatically per query
- Excellent tool-use and JSON-mode discipline
- Strong agent performance on SWE-bench Verified
- Long-context tasks, handles 400K tokens vs 256K for Codestral 2.
- Multimodal needs covering vision, audio.
Consider Mistral Large 2
Mistral's flagship API model, strong on code and reasoning, EU-friendly hosting.
Frequently asked
Is Codestral 2 or GPT-5 cheaper?
Codestral 2 is cheaper at $0.90 / 1M tokens per million output tokens, vs $10.00 / 1M tokens for GPT-5.Which has the larger context window?
GPT-5 accepts 400K tokens vs 256K for Codestral 2.Is Codestral 2 or GPT-5 better for coding?
Both Codestral 2 and GPT-5 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). GPT-5 is API-only.When were Codestral 2 and GPT-5 released?
Codestral 2 was released by Mistral on 2025-01-14. GPT-5 was released by OpenAI on 2025-08-07.
The week's AI launches, in your inbox.
One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.