AIHubMixAIHubMix

Mistral Models

10 modelsGeneral models from $0.5/M inputUp to 256K context

Usage

Last 28 days · 2026-08-09 to 2026-09-07

Tokens

48.3M

Requests

6.7K

Models in use

2 of 10

Tokens per day, stacked by model

012.2M24.5M08-0908-1708-2509-012026-08-09 — 892,830 tokens mistral-large-3: 892,8302026-08-10 — 847,375 tokens mistral-large-3: 847,3752026-08-11 — 3,104,890 tokens mistral-large-3: 3,104,8902026-08-12 — 205 tokens mistral-large-3: 2052026-08-14 — 195 tokens mistral-large-3: 1952026-08-15 — 100 tokens mistral-large-3: 1002026-08-16 — 12,790 tokens mistral-large-3: 12,7902026-08-17 — 4,790 tokens mistral-large-3: 4,7902026-08-18 — 80,210 tokens mistral-large-3: 80,2102026-08-19 — 116,535 tokens mistral-large-3: 116,5352026-08-20 — 1,555 tokens mistral-large-3: 1,5552026-08-22 — 3,830 tokens mistral-large-3: 3,8302026-08-23 — 11,480 tokens mistral-large-3: 11,4802026-08-24 — 135,085 tokens mistral-large-3: 135,0852026-08-25 — 40,815 tokens mistral-large-3: 40,8152026-08-26 — 150 tokens mistral-large-3: 1502026-08-27 — 44,245 tokens mistral-large-3: 44,2452026-08-28 — 1,108,260 tokens mistral-large-3: 1,108,2602026-08-29 — 2,186,740 tokens mistral-large-3: 2,186,7402026-08-30 — 2,971,775 tokens mistral-large-3: 2,971,7752026-08-31 — 3,519,285 tokens mistral-large-3: 3,519,2852026-09-01 — 1,585 tokens mistral-large-3: 1,5852026-09-02 — 3,588,340 tokens mistral-large-3: 3,588,3402026-09-03 — 5,039,340 tokens mistral-large-3: 5,039,3402026-09-04 — 57,010 tokens mistral-large-3: 57,0102026-09-05 — 1,265 tokens mistral-large-3: 1,2652026-09-06 — 12,745 tokens mistral-large-3: 12,7452026-09-07 — 24,485,770 tokens mistral-large-3: 24,485,770

Which models that traffic went to

  1. Mistral Large 3100.0%48.3M

Share of 48.3M tokens. 1 models with traffic report no token counts and cannot be ranked here, including mistralai/mistral-7b-instruct:free — 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 28 days, counting the 10 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 10 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-3Takes text, vision, returns text.256K$0.5$1.5/M47 tok/s1.68 s
mistralai/mistral-7b-instruct:free—$0.002$0.002/M——
chutesai/Mistral-Small-3.1-24B-Instruct-2503—$0.2$0.8/M——
aihubmix-Codestral-2501—$0.4$1.2/M——
AiHubmix-mistral-medium—$0.4$2/M——
codestral-latest—$0.4$1.2/M——
aihubmix-Mistral-Large-2411—$2$6/M——
aihubmix-Mistral-large-2407—$3$9/M——
Mistral-large-2407—$3$9/M——
aihubmix-Mistral-large—$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.

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.

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
144 modelsOpenAI
134 modelsGoogle
85 modelsZ.AI
71 modelsLlama
53 models

Start calling Mistral in one line

One key, one endpoint, 880 models across 38 model authors.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect