Devstral Medium API Pricing

Mistral has deprecated this model. The price is kept here for reference; check the provider's documentation before building on it.

Mistral · released Jul 10, 2025 · 128K context · API model ID devstral-medium-2507

Devstral Medium by Mistral API pricing: $0.40 per 1M input tokens and $2.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).

Prices

Devstral Medium prices, USD per 1M tokens
PriceUSD per 1M tokens
Input$0.40
Output$2.00
Cache readNot published
Cache writeNot published

Mistral's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation

Estimated monthly cost

$420.00

per month

per day
$14.00
per request
$0.0014

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.

Compare this workload across models

Monthly cost by workload

WorkloadPer month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day$420.00/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day$630.00/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input$720.00/mo

Context and capabilities

Context
128,000 tokens
Max output
128,000 tokens
Input
text
Output
text
Knowledge cutoff
May 2025
Open weights
Yes
Tool calling
Yes
Reasoning
No
Structured outputs
No

Capabilities and limits as listed by models.dev.

Similarly priced models

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does Devstral Medium cost per month?
For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Devstral Medium costs about $420.00 per month at Mistral's list prices ($0.40 per 1M input tokens, $2.00 per 1M output tokens).
Does Devstral Medium support prompt caching?
No cache read price is published for Devstral Medium.
How long is Devstral Medium's context window?
Devstral Medium accepts up to 128,000 tokens (128K) of context and returns up to 128,000 tokens per response.