StackLift
Mistral · updated Nov 22, 2026, 4:07 PM UTC

Mistral Medium 3.5 API pricing.

Mistral Medium 3.5 by Mistral costs $1.50 per million input tokens and $7.50 per million output tokens, with a 262K-token context window. That puts it in the premium range of the models we track. A support chatbot handling 10,000 conversations a month would cost about $60.00 a month in API fees.

Price

What Mistral Medium 3.5 costs per token

List prices, checked every hour. Blended assumes three input tokens for every output token. This model sits in the premium range of the models we track.

ModelProviderInput / 1MOutput / 1MBlended / 1MContext
Mistral Medium 3.5Mistral$1.50$7.50$3.00262K

Source: Mistral Medium 3.5 in the OpenRouter model catalog. Check it against Mistral AI's pricing.

Specs

What Mistral Medium 3.5 can do

From Mistral Medium 3.5's entry in the OpenRouter model catalog.

Reads
text, images and files (PDFs and documents)
Writes
text
Context window
262K tokens
Longest answer
210K tokens
Tool calling
Yes: it can call functions and APIs you define
Structured output
Yes: answers can follow a JSON schema
Reasoning
Yes: it can think through steps before answering
Open weights
Yes: you can also run it on your own servers

Monthly cost

What common workloads cost on Mistral Medium 3.5

API fees only, at list price. The assumptions are shown, so you can scale them to your own volume.

Customer support chatbot

$60.00 / month

10,000 conversations a month, ~1,500 in and ~500 out each: 15M input and 5M output tokens.

Knowledge-base Q&A (RAG)

$180 / month

20,000 questions a month, ~4,000 in and ~400 out each: 80M input and 8M output tokens.

Document summaries and extraction

$48.00 / month

2,000 documents a month, ~12,000 in and ~800 out each: 24M input and 1.6M output tokens.

Coding assistant for a team of 10

$90.00 / month

10 developers a month, 3.0M in and 0.6M out each: 30M input and 6M output tokens.

Hosting, a vector database, monitoring and the build itself are extra. The free StackLift estimate adds them for your exact scope.

Per request

What one request costs on Mistral Medium 3.5

A request costs its input tokens times the input price plus its output tokens times the output price. A typical assistant turn of 2,000 input and 500 output tokens on Mistral Medium 3.5: 2,000 × $1.50 ÷ 1M + 500 × $7.50 ÷ 1M = $0.0067.

RequestInput / output tokensOne request1,000 requests
Short chat reply500 / 200$0.0022$2.25
Typical assistant turn2,000 / 500$0.0067$6.75
Long document task20,000 / 1,500$0.041$41.25

As you grow

Mistral Medium 3.5 cost at ten times less and ten times more

The same workloads at a tenth and at ten times the volume, at Mistral Medium 3.5's list price.

WorkloadA tenthTypicalTen times
Customer support chatbot$6.001,000 conversations$60.0010,000 conversations$600100,000 conversations
Knowledge-base Q&A (RAG)$18.002,000 questions$18020,000 questions$1,800200,000 questions
Document summaries and extraction$4.80200 documents$48.002,000 documents$48020,000 documents

Fit

When Mistral Medium 3.5 is the right choice

Mistral Medium 3.5 is priced for hard work: multi-step reasoning, careful writing and complex code, where a better answer saves a person's time. For high-volume routine requests, a cheaper model usually does as well.

Mistral Medium 3.5 reads images and files (PDFs and documents) as well as text and can call tools and APIs, return structured JSON and reason through multi-step problems, so it can drive agents that act in your systems.

Its weights are published, so Mistral Medium 3.5 can also run on your own servers when data must stay in-house; the API price above is for hosted use.

Many products mix models: a cheaper one for simple steps and a stronger one where quality matters. Test a shortlist on your own examples before you commit.

Save

Ways to pay less for Mistral Medium 3.5

  1. 1. Cache repeated instructions

    Most providers discount input that repeats across requests, such as a long system prompt or shared context.

  2. 2. Route by difficulty

    Mistral Large 4 costs 65% less per token than Mistral Medium 3.5. Send simple requests there and keep Mistral Medium 3.5 for the steps that need it.

  3. 3. Batch what can wait

    Overnight or bulk jobs often qualify for batch pricing, at a lower rate than live requests.

  4. 4. Ask for shorter answers

    Output costs 5 times as much as input on Mistral Medium 3.5, so a tight answer format (bullet points, JSON, a word limit) cuts the bill more than a shorter prompt.

Alternatives

Models priced closest to Mistral Medium 3.5

From other providers, nearest on blended price. Quality and speed differ by task: test the shortlist on your own examples.

ModelProviderInput / 1MOutput / 1MBlended / 1MContext
Mistral Medium 3.5Mistral$1.50$7.50$3.00262K
Gemini 4 HydrogenGoogle$1.50$7.50$3.001M
Qwen3.8 2.4T A95BQwen$2.00$6.00$3.001M
Gemini Omni 1.2 FlashGoogle$1.50$9.00$3.38131K
Gemini Omni 1.1 FlashGoogle$1.50$9.00$3.38131K
Claude Sonnet 5.5Anthropic$2.00$10.00$4.001M

Mistral

Other Mistral models

The same provider's newest models, for a quicker or more capable option.

ModelProviderInput / 1MOutput / 1MBlended / 1MContext
Mistral Large 4Mistral$0.70$2.10$1.051M
Mistral Medium 3.1Mistral$0.44$2.20$0.88131K
Mistral Small 3.2 24BMistral$0.075$0.20$0.106256K

Questions about Mistral Medium 3.5 pricing

How much does Mistral Medium 3.5 cost per 1,000 tokens?

$0.0015 per 1,000 input tokens and $0.0075 per 1,000 output tokens, from the list price of $1.50 and $7.50 per million.

Is Mistral Medium 3.5 cheaper than Gemini 4 Hydrogen?

They cost the same on list price: $3.00 per million tokens on average (3 parts input to 1 output). Quality and speed differ by task, so test both on your own examples.

What is Mistral Medium 3.5's context window?

262K tokens: the most text the model reads and writes in one request. Long documents beyond that are split, or retrieved in parts with RAG.

How much would a chatbot cost on Mistral Medium 3.5?

About $60.00 a month for 10,000 conversations a month, ~1,500 in and ~500 out each. Caching repeated instructions and routing simple questions to a cheaper model lower it further.

Does Mistral Medium 3.5 support tool calling?

Yes. Mistral Medium 3.5 can call functions and APIs you describe to it, which is what lets an AI agent look up data or take actions. It can also return answers that follow a JSON schema.

Can Mistral Medium 3.5 read images or documents?

Yes. Besides text, Mistral Medium 3.5 reads images and files (PDFs and documents).

How long can Mistral Medium 3.5's answers be?

Up to 210K tokens per answer (about 157,000 words), within a 262K tokens context window.

How do I estimate the AI cost of my own product?

Count the requests a month and the tokens in and out of each, then multiply by the prices here. StackLift's free estimate does this for your exact scope, alongside the cost to build it.

Build with it

Scope a product on Mistral Medium 3.5

Pick your features and integrations; the estimate returns the build cost, timeline and team, and the model's monthly running cost. Free, no signup.