Context
128K
Max output
8K
Serving providers
1
Cheapest input
$0.40 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
40 t/s
tokens / second
Time to first token
19.79s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 0% | default | — | |
| GPQA Diamond | 58% | default | — | |
| Humanity's Last Exam | 4% | default | — | |
| IFBench | 39% | default | — | |
| LiveCodeBench | 40% | default | — | |
| Long-Context Reasoning | 28% | default | — | |
| MMLU-Pro | 76% | default | — | |
| MMMU-Pro | 53% | default | — | |
| Omniscience | -31.5 | default | — | |
| SciCode | 33% | default | — | |
| TerminalBench Hard | 4% | default | — | |
| τ²-bench | 24% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Vertex AI Mistral ModelsCheapest | $0.40 | $2.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$240
estimated / month
Model IDs
copy the exact identifier for your platformvertex_ai/mistral-medium-3
Frequently asked questions
Mistral Medium 3 pricing, context and availabilityHow much does Mistral Medium 3 cost?
Mistral Medium 3 costs $0.40 per 1M input tokens and $2.00 per 1M output tokens at its cheapest provider via Vertex AI Mistral Models.
What is the context window of Mistral Medium 3?
Mistral Medium 3 accepts up to 128K tokens of context and can return up to 8K output tokens.
What can Mistral Medium 3 do?
Mistral Medium 3 supports tool use.
Other Mistral models
compare pricing across the Mistral lineupMixtral 8x7B Instruct V0 1$0.00/1M · 6 providersMistral Nemo Instruct 2407$0.02/1M · 5 providersMistral Large$2.00/1M · 5 providersCodestral 2405$0.00/1M · 4 providersMistral 7B Instruct$0.07/1M · 4 providersMixtral 8x7B Instruct$0.07/1M · 4 providersCodestral Latest$0.00/1M · 3 providersMistral 7B Instruct V0 1$0.00/1M · 3 providers
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI