Mistral Medium 3.1 API pricing.
Mistral Medium 3.1 by Mistral costs $0.44 per million input tokens and $2.20 per million output tokens, with a 131K-token context window. That puts it in the mid-range range of the models we track. A support chatbot handling 10,000 conversations a month would cost about $17.60 a month in API fees.
Price
What Mistral Medium 3.1 costs per token
List prices, checked every hour. Blended assumes three input tokens for every output token. This model sits in the mid-range range of the models we track.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Mistral Medium 3.1 | Mistral | $0.44 | $2.20 | $0.88 | 131K |
Source: Mistral Medium 3.1 in the OpenRouter model catalog. Check it against Mistral AI's pricing.
Specs
What Mistral Medium 3.1 can do
From Mistral Medium 3.1's entry in the OpenRouter model catalog.
- Reads
- text, images and files (PDFs and documents)
- Writes
- text
- Context window
- 131K tokens
- Longest answer
- 105K tokens
- Tool calling
- Yes: it can call functions and APIs you define
- Structured output
- Yes: answers can follow a JSON schema
- Reasoning
- Not listed
- Cached input
- $0.044 per 1M tokens (90% off the input price)
- Open weights
- No: API access only
- Knowledge cutoff
- June 2025
Monthly cost
What common workloads cost on Mistral Medium 3.1
API fees only, at list price. The assumptions are shown, so you can scale them to your own volume.
Customer support chatbot
$17.60 / month
10,000 conversations a month, ~1,500 in and ~500 out each: 15M input and 5M output tokens.
Knowledge-base Q&A (RAG)
$52.80 / month
20,000 questions a month, ~4,000 in and ~400 out each: 80M input and 8M output tokens.
Document summaries and extraction
$14.08 / 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
$26.40 / 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 3.1
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 3.1: 2,000 × $0.44 ÷ 1M + 500 × $2.20 ÷ 1M = $0.0020.
| Request | Input / output tokens | One request | 1,000 requests |
|---|---|---|---|
| Short chat reply | 500 / 200 | $0.0007 | $0.66 |
| Typical assistant turn | 2,000 / 500 | $0.0020 | $1.98 |
| Long document task | 20,000 / 1,500 | $0.012 | $12.10 |
As you grow
Mistral Medium 3.1 cost at ten times less and ten times more
The same workloads at a tenth and at ten times the volume, at Mistral Medium 3.1's list price.
| Workload | A tenth | Typical | Ten times |
|---|---|---|---|
| Customer support chatbot | $1.761,000 conversations | $17.6010,000 conversations | $176100,000 conversations |
| Knowledge-base Q&A (RAG) | $5.282,000 questions | $52.8020,000 questions | $528200,000 questions |
| Document summaries and extraction | $1.41200 documents | $14.082,000 documents | $140.820,000 documents |
Same price
Mistral Medium 3.1 vs Mistral Medium 3
Both cost $0.44 per million input tokens and $2.20 per million output tokens, so every figure above is the same for both. What differs:
- Mistral Medium 3.1 was added to the catalog on Aug 13, 2025, Mistral Medium 3 on May 7, 2025, so Mistral Medium 3.1 is the newer of the two.
Fit
When Mistral Medium 3.1 is the right choice
Mistral Medium 3.1 sits in the middle on price, a common default for assistants and agents that need solid reasoning at a predictable monthly cost.
Mistral Medium 3.1 reads images and files (PDFs and documents) as well as text and can call tools and APIs and return structured JSON, so it can drive agents that act in your systems.
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 3.1
1. Cache repeated instructions
Mistral Medium 3.1 charges $0.044 per million cached input tokens instead of $0.44. A 4,000-token system prompt sent with 10,000 requests a month costs $17.60 at the list price and about $1.76 when cached.
2. Route by difficulty
Mistral Small 3.1 24B costs 54% less per token than Mistral Medium 3.1. Send simple requests there and keep Mistral Medium 3.1 for the steps that need it.
3. Batch what can wait
Overnight or bulk jobs often qualify for batch pricing, at a lower rate than live requests.
4. Ask for shorter answers
Output costs 5 times as much as input on Mistral Medium 3.1, 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 3.1
From other providers, nearest on blended price. Quality and speed differ by task: test the shortlist on your own examples.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Mistral Medium 3.1 | Mistral | $0.44 | $2.20 | $0.88 | 131K |
| DeepSeek V4 Pro 0423 | DeepSeek | $0.90 | $1.50 | $1.05 | 1M |
| Llama 3.1 70B Instruct | Meta | $0.72 | $0.72 | $0.72 | 131K |
| Llama 3.3 70B Instruct | Meta | $0.71 | $0.71 | $0.71 | 131K |
| Llama 4 Maverick | Meta | $0.35 | $1.00 | $0.513 | 524K |
| Gemini 3.8 Flash | $0.825 | $4.13 | $1.65 | 1M |
Mistral
Other Mistral models
The same provider's newest models, for a quicker or more capable option.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Mistral Large 4 | Mistral | $0.70 | $2.10 | $1.05 | 1M |
| Mistral Medium 3.5 | Mistral | $1.50 | $7.50 | $3.00 | 262K |
| Mistral Small 3.2 24B | Mistral | $0.075 | $0.20 | $0.106 | 256K |
Questions about Mistral Medium 3.1 pricing
How much does Mistral Medium 3.1 cost per 1,000 tokens?
$0.0004 per 1,000 input tokens and $0.0022 per 1,000 output tokens, from the list price of $0.44 and $2.20 per million.
Is Mistral Medium 3.1 cheaper than DeepSeek V4 Pro 0423?
Yes, on list price. Mistral Medium 3.1 averages $0.88 per million tokens (3 parts input to 1 output) against $1.05 for DeepSeek V4 Pro 0423. Quality and speed differ by task, so test both on your own examples.
What is Mistral Medium 3.1's context window?
131K 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 3.1?
About $17.60 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 3.1 support tool calling?
Yes. Mistral Medium 3.1 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 3.1 read images or documents?
Yes. Besides text, Mistral Medium 3.1 reads images and files (PDFs and documents).
How long can Mistral Medium 3.1's answers be?
Up to 105K tokens per answer (about 79,000 words), within a 131K tokens context window.
Does Mistral Medium 3.1 have prompt caching?
Yes. Input read from the cache costs $0.044 per million tokens, 90% less than the $0.44 list price, which suits long system prompts and shared context.
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 3.1
Pick your features and integrations; the estimate returns the build cost, timeline and team, and the model's monthly running cost. Free, no signup.