Home › Models › Mistral Large
Mistral Large API pricing
Mistral Large is a flagship model from Mistral AI with a 128,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026.
Price list
| Token class | Rate / 1M | Notes |
|---|---|---|
| Input | $2 | Prompt tokens not served from cache |
| Cached input | $0.20 | 90% below base input |
| Cache write |  | Not billed per token |
| Output | $6 | 3.0× the input rate |
| Batch API | −50% | Input and output, results within 24 h |
Flagship. European provider. Priced via Mistral API.
What Mistral Large costs at three real workloads
Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.
| Workload | Requests | Tokens | Estimated cost |
|---|---|---|---|
| Support chat | 1,000 | 4K in / 600 out | $11.60 |
| RAG with caching | 1,000 | 50K in (45K cached) / 1K out | $25.08 |
| Nightly batch job | 10,000 | 10K in / 2K out | $160 |
Caching the 45K-token prefix saves about 76% on the RAG workload versus sending it uncached every call ($106 → $25.08). Batch mode halves the nightly job.
Where Mistral Large sits in the market
Out of 37 models in this dataset, Mistral Large ranks #30 cheapest by input rate, #21 by output rate, and #21 on a blended 1M-input-plus-250K-output workload.
| Model | Provider | Input | Output | Blended |
|---|---|---|---|---|
| Mistral Large | Mistral AI | $2 | $6 | $3.50 |
| Grok 4.6 | xAI Grok | $2 | $6 | $3.50 |
| Gemini 3.5 Flash | Google Gemini | $1.50 | $9 | $3.75 |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $3.96 | $2.31 |
Blended cost = 1M input tokens + 250K output tokens at list price.
FAQ
How much does Mistral Large cost per 1M tokens?
$2 per 1M input tokens and $6 per 1M output tokens on the standard tier.
Is prompt caching cheaper on Mistral Large?
Yes. Cached input bills at $0.20 per 1M tokens, 90.0% below the $2 base input rate, with no separate cache-write rate published.
Does Mistral Large support the Batch API?
Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $320 at list price and about $160 in batch mode.
Keep reading
- All Mistral AI models and rates
- Every model in the dataset, ranked by price
- Mistral Large vs Mistral Nemo
- GPT-6 Astra vs Mistral Large
- Claude Fable 5.1 vs Mistral Large
- Calculate your own monthly cost with the free estimator
Run these numbers in the calculator