Mistral Models API Cost Calculator & Comparison

Every Mistral model, side by side — current API rates, context window, benchmarks, and a live calculator that ranks them at your exact workload. 22 active models, 22 with public pricing. Prices refreshed daily.

Models tracked

22

Active

22

With public pricing

22

Cheapest input

$0.02/1M

Calculate your Mistral API cost at your workload.

Set your workload — every priced model ranks in real time.

Adjust the workload

Every model below updates in real time.

1,00010,00050,000250,0001M10M

Ranked by your monthly bill

No models with public pricing available to compare right now.

Pricing at a glance

Blended $/1M tokens across the lineup.

Blended price uses a 3-to-1 input/output ratio. Green bar = cheapest.

Quick picks

Best Mistral model for your use case.

As of April 2026, Mistral offers 22 active models via API, ranging from $0.020/1M to $2.00/1M input tokens. The most context-rich model handles up to 262K tokens. Models support vision, tool use. All prices are USD per 1 million tokens.

Lowest cost

Mistral Nemo

$0.020/1M input

Largest context

Mistral Small 4

262K tokens

Vision / multimodal

Ministral 3 14B 2512

Image input

Tool use / agents

Mistral Small Creative

Function calling

Quality vs price

Mistral benchmarks at a glance.

Each point is one model — X is blended $/1M tokens, Y is the average of available quality benchmarks. Larger bubbles mean larger context windows.

Per-model benchmark scores

ModelAvgScores
Codestral 250881.0
HumanEval81
Mistral Small 3.2 24B81.0
MMLU81
Mistral Small 381.0
MMLU81
Mistral Medium 3.180.0
MMLU80
Mistral Medium 378.0
MMLU78
Devstral 2 251272.2
SWE-Bench Verified72.2
Mistral Small 3.1 24B70.2
MMLU80.6MMLU Pro66.8GPQA Diamond46.0HumanEval88.4MATH69.3
Devstral Medium61.6
SWE-Bench Verified61.6
Devstral Small 1.153.6
SWE-Bench Verified53.6
Mixtral 8x22B Instruct47.9
MMLU77.8HumanEval45.1AA Intelligence Index10IFEval71.8BBH44.1MMLU Pro38.7
Mistral Nemo40.5
IFEval63.8BBH29.7MMLU Pro28.0
Mixtral 8x7B Instruct38.8
MMLU70.6AA Intelligence Index8IFEval56.0BBH29.7MMLU Pro29.9
Mistral 7B Instruct v0.132.1
MMLU60.1IFEval44.9BBH7.7MMLU Pro15.7
Pixtral Large 241114.0
AA Intelligence Index14

Open weights

Open Models from Mistral

Mistral ships 14 open-source or open-weights models you can self-host or fine-tune. Each links to its Hugging Face card.

Every model

Every Mistral model — pricing, context & capabilities.

ModelContextInput /1MOutput /1M
Mistral Small 4262K$0.15$0.6
Mistral Small Creative33K$0.1$0.3
Devstral 2 2512262K$0.4$2.00
Ministral 3 14B 2512262K$0.2$0.2
Ministral 3 3B 2512131K$0.1$0.1
Ministral 3 8B 2512262K$0.15$0.15
Mistral Large 3 2512262K$0.5$1.50
Codestral 2508256K$0.3$0.9
Mistral Medium 3.1131K$0.4$2.00
Voxtral Small 24B 250732K$0.1$0.3
Devstral Medium131K$0.4$2.00
Devstral Small 1.1131K$0.1$0.3
Mistral Small 3.2 24B128K$0.075$0.2
Mistral Medium 3131K$0.4$2.00
Mistral Small 3.1 24B128K$0.35$0.56
Saba33K$0.2$0.6
Mistral Small 333K$0.05$0.08
Pixtral Large 2411131K$2.00$6.00
Mistral Nemo131K$0.02$0.04
Mixtral 8x22B Instruct66K$2.00$6.00
Mixtral 8x7B Instruct33K$0.54$0.54
Mistral 7B Instruct v0.13K$0.11$0.19

FAQ

Preguntas frecuentes

Pricing patterns, best-known use cases, and how this provider stacks up.

Get instant answers from our AI agent

Mistral API pricing ranges from $0.020 to $2.00 per 1M input tokens. Output tokens cost more than input on every model. Prices are per 1 million tokens (1M ≈ 750,000 words). Use the calculator above to estimate your monthly spend at your actual workload.
Mistral Nemo is the lowest-priced Mistral model with public pricing at $0.020/1M input tokens. It suits high-volume tasks where cost matters most — classification, extraction, summarization, and similar workloads that don't need frontier reasoning.
Pixtral Large 2411 is Mistral's highest-tier model at $2.00/1M input. It delivers the most sophisticated reasoning, instruction-following, and nuance. For workloads that don't require frontier performance, a mid-tier model typically cuts inference costs substantially.
Mistral Small 4, Mistral Small Creative, Devstral 2 2512 and 19 more support function calling (tool use), required for agentic workflows. Agents need a model that reliably follows structured output schemas — test with your specific tool definitions before committing to production volumes.
Yes — Mistral Small 4, Ministral 3 14B 2512, Ministral 3 3B 2512, Ministral 3 8B 2512 and 6 more accept image input alongside text. You can pass screenshots, photos, charts, and documents for analysis. Vision adds no separate line-item on most Mistral models — you're billed for the token equivalent of the image.
Yes — Mistral supports prompt caching (discounts for repeated context) and batch processing (accept a delay, cut costs ~50%). These rates appear in the table above under "Cached /1M" and "Batch /1M." Caching pays off quickly if your prompts share a long system prompt or document prefix across many calls.
Mistral has historically adjusted prices when launching new model generations, often cutting rates to stay competitive. Buzzi.ai snapshots pricing daily — you can subscribe to price-drop alerts on any Mistral model using the "Alert me" button on its detail page.
Use the main comparison wizard to run the same calculator across Mistral, Anthropic, Google, Meta, Mistral, and 20+ other providers. Set your exact workload and get a ranked cost chart in under a minute.

Look wider

Compare Mistral against other providers.

Open the full wizard — pick a use case, set your usage, and cross-compare against OpenAI, Anthropic, Google, and 20+ more.

Open the comparison wizard