Mistral Medium 3.5 API pricing
Token prices on OpenRouter and at the provider’s list price, and what your own workload would cost per month.
- Input
- $1.50
- Output
- $7.50
- Cached input
- —
OpenRouter, per 1M tokens. A dash means no listed price.
Your monthly cost
- Input not in cache
- $135
- Output
- $135
- Total per month
- $270
- Per day
- $9.00
- Per request
- $0.009
No cache-read price is published for this model, so a cached share is billed as normal input. Compare this bill with other models.
Every price, with its source
OpenRouter price, per 1M tokens
- Input
- $1.50
- Output
- $7.50
- Cached input (read)
- not listed
- Batch (input / output)
- $0.75 / $3.75
- Context window
- 262,144 tokens
- Maximum output
- 209,715 tokens
- Accepts
- text, image, file
- Reasoning mode
- yes
- Intelligence Indexby Artificial Analysis, relayed by OpenRouter
- 14.2
- Listed since
- 30 Apr 2026
Provider list price, per 1M tokens
- Input / output
- $1.50 / $7.50
- Cached input (read)
- $0.15
As recorded in the LiteLLM price table under mistral/mistral-medium-3-5, which cites the provider’s pricing page. It matches the OpenRouter price.
Collected from the OpenRouter models API (466 entries). 99 models are cross-checked against provider list prices in the LiteLLM price table.
About Mistral Medium 3.5
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Description supplied by OpenRouter. Model id for the API: mistralai/mistral-medium-3-5
Mistral Medium 3.5 against other models
Other Mistral models
Questions and answers
How much does Mistral Medium 3.5 cost per million tokens?
At the collection of 3 Oct 2026, 08:40 UTC, OpenRouter listed Mistral Medium 3.5 at $1.50 per million input tokens and $7.50 per million output tokens. The provider list price recorded by LiteLLM is $1.50 for input and $7.50 for output.
What would Mistral Medium 3.5 cost per month?
For 1,000 requests a day with 3,000 input and 600 output tokens each, over a 30-day month and with no caching, the bill is $270. Change the numbers in the simulator on this page to match your own traffic.
Does Mistral Medium 3.5 have a cheaper price for cached input?
The sources list no cache-read price for this model, so this site applies no caching discount to it.
What is the context window of Mistral Medium 3.5?
262,144 tokens, with a maximum output of 209,715 tokens, as reported by OpenRouter.
Is there a batch price for Mistral Medium 3.5?
Yes. OpenRouter lists a batch variant at $0.75 per million input tokens and $3.75 per million output tokens, for requests that can wait for an asynchronous answer.
Keep going
- Price tableEvery model and its price, sorted by your monthly bill.
- Cost calculatorYour monthly bill on up to four models, line by line.
- Cheapest modelsThe five lowest-cost models in each category.
- Free modelsModels listed at zero price, kept apart from the paid ones.
- Price changesA dated log of every price that went up or down.
- Caching and batch discountsHow the two discounts work and what you save.
- Long-context pricingModels that read very long prompts, and what they charge.