Mistral Large 3
Mistral AIReleased Dec 2, 2025Open weights · Apache 2.0mistral-large
- Context
- 128k tokens
- Max output
- 32k tokens
- Mistral AI's API
- yes, as mistral-large-2512
Read Sep 3, 00:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Mistral AI
Run it yourself
open weights, Apache 2.0 · too large for the 6 workstations in our guideSelf-host guide ›- Parameters
- 675B
- 41B active per token (MoE)
- Memory needed
- 405 GB
- in INT4 · 810 GB in INT8
- Smallest cloud setup
- 8× H100
- 640 GB · $17.20/h, about $12,556 a month
- Worth it above
- 6B tokens
- a month, against the cheapest API at $2.00 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 405 GB | 8× H100 · $17.20/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 810 GB | multi-node, over 640 GB | near-lossless |
| FP16 (full) | 1620 GB | multi-node, over 640 GB | reference quality |
At home: 405 GB in INT4 is beyond any desktop or Mac in our machines table, so it means a multi-GPU server.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | Checked |
|---|---|---|---|---|
| Mistral AI128K ctx · 32K out | $0.50 | $1.50 | — | Sep 3 |
1 provider · prices per million tokens, read Sep 3, 00:00 UTC · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Mistral AI | not checked yet | 128K | 32K | — | — | — |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Mistral Large 3 spec sheet, field by field, with sources
Mistral Large 3 spec sheetmaker-declared
What Mistral AI declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- to verify
- Parameters
- to verify
- Active experts
- to verify
- Weight precision
- to verify
- License
- Apache 2.0 — open weights, permissiveScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker
- Modalities
- to verify
- Max output (official)
- to verify
- Release date
- December 2, 2025
- Maker lifecycle status
- General availability
docs.mistral.ai · maker's documentation · read 2026-09-07 · 3 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Mistral AI | $1.25 | $4.75 | $3.50 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Mistral AI models · all its models, hosts and history ›
- Mistral Nemo6 providers · from $0.038
- Mistral Small 3.2 24B4 providers · from $0.28
- Mistral Small 42 providers · from $0.75
- Codestral 25081 provider · from $1.20
- Devstral 2 25121 provider · from $2.40
- Ministral 3 14B 25121 provider · from $0.40