Mistral Models

11 modelsGeneral models from $0.5/M inputUp to 1M context

Usage

Last 30 days · 2026-10-02 to 2026-10-31

Tokens

229M

Requests

16.1K

Models in use

11 of 11

Tokens per day, stacked by model

026.6M53.1M10-0210-0910-1610-2310-302026-10-02 — 1,341,040 tokens mistral-large-3: 1,341,0402026-10-03 — 37,053,820 tokens mistral-large-3: 37,053,8202026-10-04 — 2,817,930 tokens mistral-large-3: 2,817,9302026-10-05 — 812,695 tokens mistral-large-3: 812,6952026-10-06 — 124,055 tokens mistral-large-3: 124,0552026-10-07 — 21,879,845 tokens mistral-large-4-0: 21,877,715 mistral-large-3: 2,1302026-10-08 — 13,347,505 tokens mistral-large-4-0: 13,344,455 mistral-large-3: 3,0502026-10-09 — 26,341,950 tokens mistral-large-4-0: 26,103,060 mistral-large-3: 238,8902026-10-10 — 53,116,025 tokens mistral-large-4-0: 49,726,230 mistral-large-3: 3,389,7952026-10-11 — 3,846,340 tokens mistral-large-3: 3,054,600 mistral-large-4-0: 791,7402026-10-12 — 9,337,655 tokens mistral-large-3: 6,501,920 mistral-large-4-0: 2,835,7352026-10-13 — 8,143,030 tokens mistral-large-3: 7,265,015 mistral-large-4-0: 878,0152026-10-14 — 9,344,370 tokens mistral-large-3: 8,705,240 mistral-large-4-0: 639,1302026-10-15 — 2,570,435 tokens mistral-large-4-0: 1,528,775 mistral-large-3: 1,041,6602026-10-16 — 20,872,050 tokens mistral-large-3: 16,779,780 mistral-large-4-0: 4,092,2702026-10-17 — 4,967,435 tokens mistral-large-3: 4,787,940 mistral-large-4-0: 179,4952026-10-18 — 235,960 tokens mistral-large-3: 197,005 mistral-large-4-0: 38,9552026-10-19 — 5,325,420 tokens mistral-large-3: 4,989,700 mistral-large-4-0: 335,7202026-10-20 — 457,365 tokens mistral-large-3: 393,500 mistral-large-4-0: 63,8652026-10-21 — 1,324,655 tokens mistral-large-3: 1,324,6552026-10-22 — 429,480 tokens mistral-large-3: 429,4802026-10-23 — 280,375 tokens mistral-large-3: 280,3752026-10-24 — 312,245 tokens mistral-large-3: 312,2452026-10-25 — 279,970 tokens mistral-large-3: 279,9702026-10-26 — 1,907,555 tokens mistral-large-3: 1,907,5552026-10-27 — 863,215 tokens mistral-large-3: 863,2152026-10-28 — 297,515 tokens mistral-large-3: 297,5152026-10-29 — 671,855 tokens mistral-large-3: 671,8552026-10-30 — 362,225 tokens mistral-large-3: 362,2252026-10-31 — 200,485 tokens mistral-large-3: 200,485
  • mistral-large-4-0
  • mistral-large-3

Which models that traffic went to

  1. Mistral Large 4.053.5%122M
  2. Mistral Large 346.5%106M

Share of 229M tokens. 9 models with traffic report no token counts and cannot be ranked here, including aihubmix-Mistral-large-2407 and aihubmix-Mistral-large — they are in the request view.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 30 days, counting the 11 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 11 Mistral Models

Open in model list
Mistral models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
mistral-large-4-0Takes text, vision, returns text.1M—$1.36$4.18/M$0.1399/M——
mistral-large-3Takes text, vision, returns text.256K131K$0.5$1.5/M—122 tok/s2.64 s
mistralai/mistral-7b-instruct:freeTakes , returns text.——$0.002$0.002/M———
chutesai/Mistral-Small-3.1-24B-Instruct-2503Takes , returns text.——$0.2$0.8/M———
aihubmix-Codestral-2501Takes , returns text.——$0.4$1.2/M———
AiHubmix-mistral-mediumTakes , returns text.——$0.4$2/M———
codestral-latestTakes , returns text.——$0.4$1.2/M———
aihubmix-Mistral-Large-2411Takes , returns text.——$2$6/M———
aihubmix-Mistral-large-2407Takes , returns text.——$3$9/M———
Mistral-large-2407Takes , returns text.——$3$9/M———
aihubmix-Mistral-largeTakes , returns text.——$4$12/M———

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

AiHubmix-mistral-medium vs Mistral-large-2407AiHubmix-mistral-medium vs aihubmix-Codestral-2501AiHubmix-mistral-medium vs aihubmix-Mistral-Large-2411AiHubmix-mistral-medium vs qwen3.8-max-previewAiHubmix-mistral-medium vs kimi-k3

Mistral on AIHubMix

Which Mistral model should I start with?

mistral-large-3 at $0.5/M input — the cheapest entry here that declares tool calling, and it carries a 256K context. Move up to aihubmix-Mistral-large when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (chutesai/…), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example mistral-large-4-0 bills cache hits at 10.29% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

Do I need a separate Mistral account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
154 modelsOpenAI
144 modelsGoogle
90 modelsZ.AI
72 modelsLlama
53 models

Start calling Mistral in one line

One key, one endpoint, 941 models across 46 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Company

Terms & Policies