Model · Mistral
Mistral Large 4: price, limits and messages on every plan
Mistral's Mistral Large 4 in llmwise: how many Mistral Large 4 messages each plan gives, what counts against them, what Mistral Large 4 reads, where your messages go, and what it costs at Mistral's API prices.
Prices and limits checked against OpenRouter's Mistral Large 4 page. Updated .
Short answer
Mistral Large 4 is in llmwise's one-time free trial of 5 messages. A paid plan gives up to 250 Mistral Large 4 messages a month on Pro ($20), 800 on Max ($50), 1,800 on Ultra ($100) and 4,000 on Studio ($200). Each Mistral Large 4 message's price is shown before you send it.
Mistral Large 4 on every plan
What Mistral Large 4 costs in llmwise is a count, not a token bill: up to 250 a month on Pro, and it's one of the models in the 5-message free trial.
| Plan | Price | Mistral Large 4 messages | Each, if all go to Mistral Large 4 |
|---|---|---|---|
| Free | $0 | In the one-time trial of 5 messages | — |
| Pro | $20 a month | Up to 250 a month | $0.08 |
| Max | $50 a month | Up to 800 a month | $0.06 |
| Ultra | $100 a month | Up to 1,800 a month | $0.06 |
| Studio | $200 a month | Up to 4,000 a month | $0.05 |
Prices don't include tax, which is added where it applies and shown before you pay. A paid plan's month is one allowance every model shares, so each Mistral Large 4 count is the most you get if all of it goes to Mistral Large 4, and "each" is the plan's price divided by that count. How pricing works.
Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.
Mistral Large 4 usage limits, explained
Every limit on Mistral Large 4 in llmwise is published. Here's each one, in Mistral Large 4 messages.
Mistral Large 4 draws on the monthly allowance every model shares: 250 Mistral Large 4 messages on Pro if nothing else uses it. Each message on a smaller model leaves fewer Mistral Large 4 messages, each Mistral Large 4 message leaves fewer for them, and unused Mistral Large 4 messages don't carry over when the billing period renews.
Long Mistral Large 4 chats count more, because each Mistral Large 4 reply resends the whole conversation. Past 64k tokens a Mistral Large 4 reply counts as 2 messages, so Pro's 250 Mistral Large 4 messages become up to 125 such replies; past 128k it counts as 4 (up to 62 Mistral Large 4 replies); past 200k the Mistral Large 4 chat is full.
Mistral Large 4's native context window is 1.05M tokens; llmwise stops a Mistral Large 4 chat at 200k tokens, so a Mistral Large 4 chat uses at most 200k of its 1.05M tokens.
A Mistral Large 4 reply can run to 8,000 tokens on Pro and 16,000 on Max, Ultra, and Studio, at the same Mistral Large 4 price however long it runs.
On a paid plan each web search or link read in a Mistral Large 4 reply counts as 1 more Mistral Large 4 message.
A $10 top-up adds up to 200 more Mistral Large 4 messages, valid 12 months, spent once the plan's own Mistral Large 4 count is gone.
Mistral Large 4 replies share every plan's soft cap of 100 replies an hour with the other models.
What Mistral Large 4 reads and does
| Made by | Mistral |
|---|---|
| Model at OpenRouter | mistralai/mistral-large-4-0 |
| Context window | 1.05M tokens |
| Longest chat in llmwise | 200k tokens |
| Images you attach | Reads them |
| PDFs you attach | Gets the text only |
| Tools (search, documents, code, apps) | Yes |
| Reasoning | On, at high effort |
| API price, per million tokens | $0.68 in, $2.09 out (a sale price, half its list price of $1.36 / $4.18) |
| A typical message at API prices | $0.0042 |
| On Pro | Up to 250 a month |
Where your Mistral Large 4 messages go
llmwise doesn't call Mistral for Mistral Large 4: every Mistral Large 4 message goes through OpenRouter, which routes it to a company hosting Mistral Large 4.
Each Mistral Large 4 request asks OpenRouter only for endpoints that, according to OpenRouter, don't store prompts for their own use or train on them. Mistral is Mistral Large 4's only host, so OpenRouter has no other Mistral Large 4 host to pick.
The Privacy Policy lists every company a Mistral Large 4 message can reach.
Mistral Large 4's API price, and what a message costs
Mistral Large 4's API price is $0.68 per million tokens in and $2.09 out: Mistral's price, served through OpenRouter, a sale price, half its list price of $1.36 / $4.18. At that price a typical Mistral Large 4 message (4,000 tokens in, 700 out) costs about $0.0042.
In llmwise a Mistral Large 4 message isn't billed by the token: it's one of up to 250 Mistral Large 4 messages a month on Pro, however long the Mistral Large 4 reply runs.
What Mistral Large 4's replies cost in our test runs, job by job, and Mistral Large 4 beside the rest of its family: Mistral Large 4 pricing: API price, cost per message and plans.
When to use Mistral Large 4, and when a cheaper model will do
llmwise's catalog describes Mistral Large 4 as “Mistral's flagship for reasoning, coding and agentic work”. No benchmark scores here: ask Mistral Large 4 your own question, then switch the picker to another model in the same chat, which sees Mistral Large 4's answer too.
When a question doesn't need Mistral Large 4, these read the same attachments and leave more of the month for Mistral Large 4:
Claude Haiku 5.5 (Anthropic): 60 a day on Pro, against Mistral Large 4's 250.
GPT-6 Luna (OpenAI): 60 a day on Pro, against Mistral Large 4's 250.
DeepSeek V4.1 Flash (DeepSeek): 60 a day on Pro, against Mistral Large 4's 250.
GLM 5.3 Flash (Z.ai): 60 a day on Pro, against Mistral Large 4's 250.
Same count as Mistral Large 4 on every plan: Claude Haiku 4.5, Gemini 3.8 Flash, DeepSeek V4 Pro, Grok 4.7 and GLM 5.3.
Mistral Large 4 in our test runs
Mistral Large 4 passed 47 of our 50 test prompts, sent through llmwise's own pipeline and checked the same way for every model.
- Coding4 of 5 passed
- Writing4 of 5 passed
- Math5 of 5 passed
- Summarization5 of 5 passed
- Data analysis5 of 5 passed
- Customer support4 of 5 passed
- Translation5 of 5 passed
- SQL5 of 5 passed
- RAG and answering from documents5 of 5 passed
- Agents and tool use5 of 5 passed
How Mistral Large 4 began its reply to our first writing prompt, “Write a LinkedIn post of 100 to 150 words announcing that our small bakery, Crumb & Co., opens a second shop in Leeds on 14 November. Mention the free coffee…”:
Something warm is coming to Leeds. On 14 November, Crumb & Co. opens the doors of our second bakery, and we could not be happier to finally be part of your neighbourhood. We started Crumb & Co. with a simple belief: good bread, made properly, brings people together. Seeing that belief grow from one small shop into a second home means everything to us — and to the wonderful team who bake, serve, and smile every single morning. To say thank you for all the support, we're offering free coffee to everyone who visits us on opening day. Come say hello, meet the team, and help us settle in. 14 November. We'll save you a seat by the window.
Questions
Is Mistral Large 4 free in llmwise?
Mistral Large 4 is in llmwise's one-time free trial of 5 messages, with no card. After that it needs a paid plan: Pro ($20 a month) gets up to 250 Mistral Large 4 messages a month.
What are Mistral Large 4's usage limits in llmwise?
Mistral Large 4 has a published monthly count on each paid plan (up to 250 Mistral Large 4 messages a month on Pro), shared with the other models. A long Mistral Large 4 chat counts each reply as 2 Mistral Large 4 messages past 64k tokens and 4 past 128k.
What happens when my Mistral Large 4 messages run out?
Your Mistral Large 4 count resets when your billing period renews. Until then, the everyday models keep answering on their own daily count, and a $10 top-up adds up to 200 more Mistral Large 4 messages.
How much context does Mistral Large 4 have in llmwise?
1.05M tokens is Mistral Large 4's native context window. A Mistral Large 4 chat in llmwise stops at 200k tokens, and past 64k each Mistral Large 4 reply counts as more than one message, so a new Mistral Large 4 chat for each new task goes further.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.