Mistral API pricing
Mistral AI's API models, from Medium 3.5 ($1.50 / $7.50) down to the Ministral 3 family at $0.10 to $0.20 per 1M tokens. Batch requests cost 50% less.
Mistral Medium 3.5
What it costs in practice
Mistral Medium 3.5 at list prices, no batch discount.
| 1,000 chat replies1,500 tokens in and 300 out each | $4.50 |
|---|---|
| Summarising 100 long reports20,000 tokens in and 800 out each | $3.60 |
| A month of a coding agent400 tasks, 85% of input cached | $1,185 |
The coding-agent example assumes 85% of input is served from cache, typical for agents that resend the same context each step. Model your own workload
Details
mistral-medium-2604Checked 27 Sep 2026 against Mistral pricing and Mistral model card .
Other Mistral models
Mistral retired Nemo, Small 3.2, Devstral 2 and Magistral 1.2 on 31 July 2026.
| Model | Input / 1M | Output / 1M | Cached input | Context | Released |
|---|---|---|---|---|---|
| $0.50 | $1.50 | — | 256K | 2 Dec 2025 | |
| $0.30 | $0.90 | — | 256K | Aug 2025 | |
Open weights |
$0.15 | $0.60 | — | 256K | 16 Mar 2026 |
| $0.20 | $0.20 | — | — | 2 Dec 2025 | |
| $0.10 | $0.10 | — | — | 2 Dec 2025 | |
| $0.15 | $0.15 | — | — | 2 Dec 2025 |
Version details
Mistral Large 3
$0.50 / $1.50 per 1M tokensbatch 50% off · 256K context
Checked 27 Sep 2026 against Mistral pricing and Mistral model card .
Codestral 25.08
$0.30 / $0.90 per 1M tokensbatch 50% off · 256K context
- A code-specialised model; excluded from general comparisons and the index.
Checked 27 Sep 2026 against Mistral pricing .
Mistral Small 4
$0.15 / $0.60 per 1M tokensbatch 50% off · 256K context
Checked 27 Sep 2026 against Mistral pricing .
Ministral 3 14B
$0.20 / $0.20 per 1M tokensbatch 50% off
Checked 27 Sep 2026 against Mistral pricing .
Ministral 3 3B
$0.10 / $0.10 per 1M tokensbatch 50% off
Checked 27 Sep 2026 against Mistral pricing .
Ministral 3 8B
$0.15 / $0.15 per 1M tokensbatch 50% off
Checked 27 Sep 2026 against Mistral pricing .
Compare Mistral Medium 3.5
No ready-made comparisons for this family yet.
Price history
All changesMistral AI pricing rules
- Batch requests cost 50% less.
- Nemo, Small 3.2, Devstral 2 and Magistral 1.2 were retired on 31 July 2026.
Retired Mistral models
- Retired 31 Jul 2026Mistral Small 3.2. Use Mistral Small 4 instead.
- Retired 31 Jul 2026Mistral Nemo. Use Ministral 3 8B instead.
Questions
How much does Mistral Medium 3.5 cost?
As of 27 Sep 2026, Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens. Batch requests cost 50% less. Prices checked 27 Sep 2026.
What is the cheapest Mistral model?
Ministral 3 3B, at $0.10 / $0.10 per million input / output tokens.
What is Mistral Medium 3.5's context window?
256K tokens.