Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 70B | — |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 16k | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.30 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $0.90 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.03 |
| — | $105Mistral list price | |
| These models have no shared benchmark scores. | ||
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 53% | — |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Jan 29 2024 | Jul 30 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Code Llama 70BvsClaude Fable 5.2Codestral 25.08vsClaude Fable 5.2Code Llama 70BvsGPT-6.2 AstraCodestral 25.08vsGPT-6.2 AstraCode Llama 70BvsGemini 4 HydrogenCodestral 25.08vsGemini 4 HydrogenCode Llama 70BvsGrok 4.7Codestral 25.08vsGrok 4.7Code Llama 70BvsDeepSeek-V4.1-Flash-1017Codestral 25.08vsDeepSeek-V4.1-Flash-1017Code Llama 70BvsKimi K3.1 ProCodestral 25.08vsKimi K3.1 ProFrequently asked questions
Code Llama 70B and Codestral 25.08 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Codestral 25.08 has a verified first-party price for an available API: $0.30 per million input tokens and $0.90 per million output tokens. No currently available pay-as-you-go API rate is tracked for Code Llama 70B. Code Llama 70B shipped 548 days before Codestral 25.08, so benchmark comparisons should account for the intervening progress.
Context windows are 16k (Code Llama 70B) vs 128k (Codestral 25.08). Code Llama 70B is open weight, while Codestral 25.08 is closed.
Direct benchmark comparisons are unavailable — Code Llama 70B and Codestral 25.08 don't publish scores on any of the same benchmarks.