Mistral API Pricing Calculator & Cost Guide
Calculate Mistral AI API costs for 19 models. Compare per-token pricing across Mistral Large, Medium, Small, Ministral, and Pixtral.
Pricing TLDR
- • Pay-per-token with no monthly fees, priced separately for input and output
- • Ministral and Mistral Small are the cheapest tiers; Large is the flagship
- • 19 Mistral models with live rates from the OpenRouter catalog
Mistral API Cost Calculator: Monthly Pricing
Calculate by
Input Tokens
Output Tokens
API Calls / Month
Quick Examples:
Sort:
(mistralai/mistral-medium-3-5)
Context
Quality
Popularity
Per 1M Tokens
In: $1.50
Out: $7.50
Monthly Cost
(mistralai/mistral-small-2603)
Context
Quality
Popularity
Per 1M Tokens
In: $0.15
Out: $0.60
Monthly Cost
(mistralai/devstral-2512)
Context
Quality
Popularity
Per 1M Tokens
In: $0.44
Out: $2.20
Monthly Cost
(mistralai/mistral-large-2512)
Context
Quality
Popularity
Per 1M Tokens
In: $0.50
Out: $1.50
Monthly Cost
(mistralai/mistral-small-3.1-24b-instruct)
Context
Quality
Popularity
Per 1M Tokens
In: $0.35
Out: $0.55
Monthly Cost
(mistralai/mistral-medium-3.1)
Context
Quality
Popularity
Per 1M Tokens
In: $0.40
Out: $2.00
Monthly Cost
(mistralai/mistral-medium-3)
Context
Quality
Popularity
Per 1M Tokens
In: $0.40
Out: $2.00
Monthly Cost
(mistralai/ministral-14b-2512)
Context
Quality
Popularity
Per 1M Tokens
In: $0.20
Out: $0.20
Monthly Cost
(mistralai/mistral-small-3.2-24b-instruct)
Context
Quality
Popularity
Per 1M Tokens
In: $0.08
Out: $0.20
Monthly Cost
(mistralai/ministral-8b-2512)
Context
Quality
Popularity
Per 1M Tokens
In: $0.15
Out: $0.15
Monthly Cost
(mistralai/mistral-large-2407)
Context
Quality
Popularity
Per 1M Tokens
In: $2.00
Out: $6.00
Monthly Cost
(mistralai/mistral-small-24b-instruct-2501)
Context
Quality
Popularity
Per 1M Tokens
In: $0.05
Out: $0.08
Monthly Cost
(mistralai/ministral-3b-2512)
Context
Quality
Popularity
Per 1M Tokens
In: $0.10
Out: $0.10
Monthly Cost
(mistralai/mixtral-8x22b-instruct)
Context
Quality
Popularity
Per 1M Tokens
In: $2.00
Out: $6.00
Monthly Cost
(mistralai/mistral-large)
Context
Quality
Popularity
Per 1M Tokens
In: $2.00
Out: $6.00
Monthly Cost
(mistralai/mistral-nemo)
Context
Quality
Popularity
Per 1M Tokens
In: $0.02
Out: $0.03
Monthly Cost
(mistralai/ministral-8b)
Context
Quality
Popularity
Per 1M Tokens
In: $0.11
Out: $0.11
Monthly Cost
(mistralai/mistral-saba)
Context
Quality
Popularity
Per 1M Tokens
In: $0.20
Out: $0.60
Monthly Cost
(mistralai/codestral-2508)
Context
Quality
Popularity
Per 1M Tokens
In: $0.30
Out: $0.90
Monthly Cost
Spending across LLM providers?
Track your AI API costs across all providers in real-time.
About Mistral
What is Mistral?
Mistral AI is a French lab building both open-weight and commercial large language models. Its API (La Plateforme) offers a family of models from the low-cost Ministral and Mistral Small tiers up to the flagship Mistral Large, plus Pixtral for vision and Codestral for code. Pricing is per token, billed separately for input and output.
- A Model for Every Cost Tier: Ministral and Mistral Small handle high-volume, simple tasks cheaply. Mistral Medium and Large take on complex reasoning and agentic workloads. Pick the smallest model that clears your quality bar.
- Open Weights Available: Several Mistral models (Mistral 7B, Mixtral, and others) ship with open weights, so you can self-host at no per-token cost or use the API for convenience. Few frontier labs offer both.
- Specialized Models: Beyond general chat, Mistral offers Codestral for code generation and Pixtral for multimodal vision tasks, each priced on the same per-token basis.
When to Use Mistral
Mistral is a strong fit when you want frontier-adjacent quality at a lower price than GPT or Claude, or when open weights and European data residency matter.
Ideal for
- Cost-sensitive production workloads at scale
- Teams that want open weights plus a hosted API option
- European projects with data-residency requirements
- High-volume classification, extraction, and routing
- Code generation via Codestral
Not ideal for
- Tasks that need the absolute top of the quality leaderboard
- Workloads dependent on provider-specific features like prompt caching
- Applications requiring the largest available context windows
Mistral Pricing Breakdown
How Mistral API Billing Works
Per-Token Pricing
Each model has separate input (prompt) and output (completion) rates per million tokens. Output is usually priced higher than input. You pay only for tokens processed, with no monthly minimum.
Model Tiers Set the Price
Cost scales with capability: Ministral is the cheapest, then Mistral Small, Medium, and Large. Choosing the right tier for each task is the single biggest lever on your bill.
Free and Open Options
La Plateforme has a rate-limited free experimentation tier, and open-weight models can be self-hosted at no per-token cost. Some Mistral models are also free with rate limits on OpenRouter.
Usage Tracking
Monitor spend per model and per key in the Mistral console. Set alerts so a runaway job or a switch to a pricier model does not surprise you at the end of the month.
Mistral API Monthly Cost Estimates
Hobby / Testing
$0-15/mo
• Ministral / Small
• <1K requests/day
• Single project
Light Use
$15-75/mo
• Mistral Small
• 1-5K requests/day
• Mixed tasks
Medium Use
$75-400/mo
• Mistral Medium
• 5-20K requests/day
• Production apps
Heavy Use
$400+/mo
• Mistral Large
• 20K+ requests/day
• Agentic workloads
5 Mistral Cost Optimization Tips
Match the Model to the Task
Do not run Mistral Large on work that Ministral or Small handles well. Reserve the flagship for genuinely hard reasoning, and route classification, extraction, and simple chat to the cheap tiers.
Self-Host the Open Models
For steady high-volume workloads on Mistral 7B or Mixtral, self-hosting the open weights can undercut per-token API pricing once your usage is predictable enough to fill a GPU.
Trim Input Tokens
Input tokens cost money on every call. Use concise system prompts, summarize long context instead of pasting whole documents, and drop history you do not need.
Cap Output Length
Output tokens usually cost more than input. Set max_tokens, ask for structured or terse responses, and avoid open-ended generations when a short answer will do.
Track Spend with CostGoat
Watch your Mistral credit balance and usage in real time with CostGoat. Get desktop or email alerts before you run low, and see which models drive your spend.
Start Tracking Your LLM API Spending
Monitor spending across OpenAI, Anthropic, Google, and other LLM providers from one menubar app.
Mistral API Pricing FAQ
Common questions about Mistral AI API costs and billing
