Mistral: Mistral Large 3 2512 API Pricing
Mistral: Mistral Large 3 2512 costs $0.500 per 1M input tokens and $1.50 per 1M output tokens (cache reads: $0.050). Context window: 262K. Prices verified 2026-10-21 · source
Alternatives to consider
96% cheaper with nearly identical quality (20.1 vs 9.3)
+35.5 quality points for 12% more
Cheapest mistralai model — 96% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.500 | — |
| Cache read | $0.050 | −90% |
| Output | $1.50 | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
What would Mistral: Mistral Large 3 2512 cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $10.00 |
| Coding agent | 5,000 | 8,000 / 2,000 | $35.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $82.50 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $23.00 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About Mistral: Mistral Large 3 2512
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Compare Mistral: Mistral Large 3 2512 with
- 3 2512 vs OpenAI: GPT-5.6 Terra Pro
- 3 2512 vs Anthropic: Claude Fable 5
- 3 2512 vs Anthropic: Claude Opus 5
- 3 2512 vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does Mistral: Mistral Large 3 2512 cost?
Mistral: Mistral Large 3 2512 costs $0.500 per 1M input tokens and $1.50 per 1M output tokens; cached input tokens cost $0.050 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
262K tokens, with up to 210K output tokens per response. That's roughly 328 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.050/1M, about 90% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
ScaleDown: Summarize saves about 96% on a typical workload with comparable quality.
Official resources
- Mistral: Mistral Large 3 2512 on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis leaderboard → — independent intelligence and performance rankings.
- Mistral models → — first-party model specifications and limits.
- Shred your current bill — paste a CSV and see if switching saves money.