Mistral AI language model
Mistral Large 4
Mistral's mixture-of-experts model with about 1T total parameters (52B active): a hybrid instruct-and-reasoning model with a vision encoder and a 1M-token context. it entered public preview on 2026-10-06; Mistral says the open weights ship later.
01
price
input tokens
output tokens
cached input
per 1M tokens. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
02
what real work costs
| workload | cost |
|---|---|
| one chat reply 3,000 tokens in, 500 out | $0.0062 |
| summarise a 100-page report 50,000 tokens in, 1,500 out, one request | $0.07 |
| 1,000 classification calls 500 tokens in, 20 out, per call | $0.76 |
| coding-agent session 2M tokens in across ~60 turns, 60,000 out, no cache | $2.97 |
| same session, cached 85% of input read from the prompt cache, the rest written to it | $0.89 |
at the listed rate. token counts are typical sizes, not measurements.
03
specs
- provider
- Mistral AI
- context window
- 1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
- input
- text, images
- output
- text
- structured output
- yes — JSON schema
- reasoning mode
- yes
- prompt caching
- yes — cache hits at $0.136/M
- weights
- closed
- released
- October 6, 2026
- status
- live
- model id
mistral-large-4
integration notes
- reasoning is set with reasoning_effort: "high" or "none"; "none" still thinks minimally but omits the thinking chunk.
- with reasoning_effort "high", message.content is a list of ThinkChunk and TextChunk items, not a string.
- replay the full assistant message, including ThinkChunk, in multi-turn calls; Mistral says dropping the reasoning trace degrades performance.
04
benchmarks
as published by the maker; not measured by octomind.
05
when to pick it
pick it if
- want a Mistral model that takes text and image input
- need a 1M-token context with function calling and structured outputs
- resend long prompts: cache hits bill $0.136 per 1M versus $1.36
skip it if
- you need downloadable weights today; Mistral says they ship later
- you need a stable release rather than a public preview
06
where it sits on price
blended price $2.065/M at 3 input tokens per output token: 28 live language models cost less, 15 cost more.
- GPT-6.1 Terra $2/M
- Muse Spark 1.3 $2/M
- Mistral Large 4 $2.065/M
- GLM-5.3 $2.15/M
- Qwen4 Max $2.25/M
07
use Mistral Large 4 in octomind
one octohub login reaches every model in the catalog. pick this one per run, per session, or as your default.
octomind login
octomind run -m octohub:mistral-large-4/model octohub:mistral-large-4[model]
name = "octohub:mistral-large-4"08
compare Mistral Large 4
09
similar models
nearest live models by listed input price.
view all models →10
Mistral Large 4 faq
how much does Mistral Large 4 cost?
Mistral Large 4 lists at $1.36/M input, $4.18/M output, $0.136/M cached input per 1M tokens. a typical coding-agent session (2M tokens in, 60,000 out) comes to $2.97, or $0.89 when 85% of the input is read from the prompt cache. octomind bills the listed provider price, with no markup, on every plan, including the free one (pay as you go from credits).
what is the context window of Mistral Large 4?
1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code.
does Mistral Large 4 accept images?
yes. it takes text and images as input and returns text.
is Mistral Large 4 open source?
no. Mistral Large 4 is a closed-weights model, available only through Mistral AI's api and hosted gateways such as octohub.
when was Mistral Large 4 released?
October 6, 2026, by Mistral AI.
is Mistral Large 4 free?
no. Mistral Large 4 bills per token at $1.36/M input, $4.18/M output, $0.136/M cached input per 1M. octomind's free plan reaches it pay as you go from credits, so you pay only for the tokens you use, at the provider price. credits carry a 3% top-up fee.
how do i use Mistral Large 4 in octomind?
run octomind login once, then octomind run -m octohub:mistral-large-4. inside a running session, /model octohub:mistral-large-4 switches to it without losing context.
use Mistral Large 4 in octomind
choose a model when you start, then switch mid-session when the work changes.