Mistral (Vertex) Pricing
Mistral (Vertex) charges from $0.150 per 1 million output tokens, depending on the model. Mistral Nemo Latest is the cheapest at $0.150/1M output and $0.150/1M input; its current flagship Mistral Large 2407 costs $6.00/1M output. The largest context window is 128K tokens (Codestral 2). Prices are USD, current as of August 11, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.150/1M
Mistral Nemo Latest
Cheapest output
$0.150/1M
Mistral Nemo Latest
Longest context
128K
Codestral 2
Models priced
19
Avg $2.45/1M output
Pricing by model
All prices in USD per 1 million tokens. All 19 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Mistral Nemo Latest | $0.150 | $0.150 | 128K |
| Codestral 2405 | $0.200 | $0.600 | 128K |
| Codestral 2501 | $0.200 | $0.600 | 128K |
| Codestral Latest | $0.200 | $0.600 | 128K |
| Codestral 2 | $0.300 | $0.900 | 128K |
| Codestral 2 001 | $0.300 | $0.900 | 128K |
| Mistralai Codestral 2 | $0.300 | $0.900 | 128K |
| Mistralai Codestral 2 001 | $0.300 | $0.900 | 128K |
| Mistral Medium 3 | $0.400 | $2.00 | 128K |
| Mistral Medium 3 001 | $0.400 | $2.00 | 128K |
| Mistralai Mistral Medium 3 | $0.400 | $2.00 | 128K |
| Mistralai Mistral Medium 3 001 | $0.400 | $2.00 | 128K |
| Mistral Nemo 2407 | $3.00 | $3.00 | 128K |
| Mistral Small 2503 | $1.00 | $3.00 | 128K |
| Mistral Small 2503 001 | $1.00 | $3.00 | 32K |
| Mistral Large 2407 | $2.00 | $6.00 | 128K |
| Mistral Large 2411 | $2.00 | $6.00 | 128K |
| Mistral Large 2411 001 | $2.00 | $6.00 | 128K |
| Mistral Large Latest | $2.00 | $6.00 | 128K |
Frequently asked questions
How much does Mistral (Vertex) cost per 1M tokens?
Mistral (Vertex) pricing starts at $0.150 per 1 million output tokens (Mistral Nemo Latest) across 19 models, with its current flagship Mistral Large 2407 at $6.00. Older premium models in the catalog list higher. Rates current as of August 11, 2026.
What is the cheapest Mistral (Vertex) model?
Mistral Nemo Latest is the cheapest Mistral (Vertex) model on both axes — $0.150 per 1M input tokens and $0.150 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.
What is the largest Mistral (Vertex) context window?
Codestral 2 has the largest context window in the Mistral (Vertex) catalog at 128K input tokens, with up to 128K output tokens per response.
How do I calculate my actual Mistral (Vertex) bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator