Mistral flagship reasoning and coding model with aggressive 2026 pricing ($0.50/M in)
| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.00125 | $0.00085 |
| Document Summarization | 10,000 | 2,000 | $0.00800 | $0.00400 |
| Codebase & Context Analysis | 100,000 | 20,000 | $0.0800 | $0.0400 |
| Batch Corpus Processing | 1,000,000 | 100,000 | $0.6500 | $0.2500 |
Ideal for production workloads demanding flagship capabilities, deep context depth (128k tokens), and reliability from Mistral AI. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For Mistral Large 3, 1 million input tokens costs $0.50, while 1 million output tokens costs $1.50. If using prompt caching, repetitive input prefixes are discounted to $0.10 per million.
Mistral Large 3 features a maximum context window of 128,000 tokens (~96,000 words), with a maximum output limit of 16,384 tokens per completion.
Mistral Large 3 utilizes the Mistral Tekken Tokenizer (131k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
Yes. Mistral Large 3 supports prompt caching with a cached input rate of $0.10/1M (saving up to 80% on repeated input context).