Mistral Medium 3 API pricing
Updated
The cheapest standard price for Mistral Medium 3 is Google Vertex AI at USD 0.40 per 1M input tokens and USD 2 per 1M output tokens. The median across 2 standard prices is USD 1.79 / USD 5.75. Every price is read from the provider's own pricing page, checked 2026-11-15.
Does Mistral AI sell Mistral Medium 3 directly?
Mistral AI publishes no price for Mistral Medium 3 on its own API that we could find, so this page compares hosts only.
Mistral Medium 3 price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 5.9× the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Google Vertex AI cheapestmistral-medium-3Notes and source quote“Mistral Medium 3 Input $0.40 … Output $2.00” | USD 0.40 | not published | USD 2 | USD 0.80 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | IBM watsonx.aimistral-medium-2505Notes and source quote“mistral-medium-2505 Mistral AI USD 3.18 per 1M tokens input USD 9.5per 1M tokens output” | USD 3.18 | not published | USD 9.50 | USD 4.76 | not stated | not stated | IBM watsonx.ai page checked 2026-11-15 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Mistral Medium 3 cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Google Vertex AI | USD 72.00 | USD 126.00 | USD 900.00 |
| IBM watsonx.ai | USD 457.20 | USD 905.70 | USD 6,579 |
For the support chatbot, the cheapest price (Google Vertex AI, USD 72.00 a month) saves USD 192.60 against the median (USD 264.60). For the coding agent the gap is USD 2,839 a month (76% lower).
Which Mistral Medium 3 provider is cheapest for your traffic?
Google Vertex AI has the lowest input price (USD 0.40) and the lowest output price (USD 2), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Google Vertex AI (no cache price) | USD 0.80 cheapest | USD 0.80 cheapest | USD 0.80 cheapest |
| IBM watsonx.ai (no cache price) | USD 4.76 | USD 4.76 | USD 4.76 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
None of the 2 providers publishes a cached-input discount for Mistral Medium 3, so cache hits do not change the ranking.
No provider states a context window for Mistral Medium 3 on its pricing page.
Estimate your own bill
- LLM API cost calculator with Mistral Medium 3 preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Mistral Medium 3 compare with other Mistral AI models?
The Mistral AI models whose cheapest standard price is closest to Mistral Medium 3's (USD 0.80 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Mistral Large 3 | USD 0.50 | USD 1.50 | — | 3 |
| Ministral 3 14B | USD 0.20 | USD 0.20 | 262,144 | 3 |
| Mistral Small 3.1 24B Instruct | USD 0.10 | USD 0.30 | 32,768 | 4 |
| Ministral 3 8B | USD 0.15 | USD 0.15 | 262,144 | 2 |
| Mistral Small 3.2 24B Instruct | USD 0.075 | USD 0.20 | 256,000 | 4 |
| Ministral 3 3B | USD 0.10 | USD 0.10 | 262,144 | 2 |
Priced closest from other makers: GLM 4.6 (Z.ai, USD 0.76) · Gemini 2.5 Flash (Google, USD 0.85) · Gemini 3.5 Flash-Lite (Google, USD 0.85).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Mistral Medium 3 API cost per token?
From USD 0.40 per 1M input tokens (USD 0.0000004 per token) and USD 2 per 1M output tokens (USD 0.000002 per token) at the cheapest standard price. The median of 2 standard prices is USD 1.79 input and USD 5.75 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Mistral Medium 3?
Google Vertex AI, ranked on a blend of 3 input tokens to 1 output token (USD 0.80 per 1M). It is also the cheapest on both input and output. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Mistral AI sell Mistral Medium 3 on its own API?
Mistral AI publishes no price for Mistral Medium 3 on its own API that we could find, so there is no maker price to compare. The cheapest host is Google Vertex AI at USD 0.40 / USD 2 per 1M tokens.
Does Mistral Medium 3 have cached input pricing?
None of the 2 standard prices includes a cached-input price, so budget repeated prompts at the full input price.
How much does a coding agent cost per month on Mistral Medium 3?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 900.00 a month at Google Vertex AI, USD 3,739 at the median price and USD 6,579 at IBM watsonx.ai. Try your own numbers.
Is Mistral Medium 3 free to use through an API?
No provider in our data lists a free price for Mistral Medium 3 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.