Mistral
Mistral Medium 3.5 token cost
Mistral Medium 3.5 for long-horizon tools, agentic coding, and multimodal work at $1.50/$7.50.
Published list rates
Input
$1.50
per 1M tokens
Output
$7.50
per 1M tokens
Cached input
$0.15
per 1M tokens
Context window
128,000
tokens
Pricing source: Mistral API pricing
Estimate cost
Estimate from text
Calculate from a token total
Project monthly volume
Daily requests × tokens per request × 30 days.
Estimated cost
- Estimated tokens
- —
- Characters
- —
- Words
- —
- Input tokens
- —
- Output tokens
- —
- Input cost
- —
- Output cost
- —
- Total cost
- —
- Combined price per 1M tokens
- —
- Estimated monthly cost
- —
- Estimated daily cost
- —
Cost as volume grows
What Mistral Medium 3.5 costs if you only send tokens, only get a reply, or do both (70% in / 30% out). Rows start small and go up to huge traffic.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000002 | $0.000007 | $0.000003 |
| 10 | $0.000015 | $0.000075 | $0.000033 |
| 100 | $0.00015 | $0.00075 | $0.00033 |
| 200 | $0.0003 | $0.0015 | $0.00066 |
| 300 | $0.00045 | $0.00225 | $0.00099 |
| 400 | $0.0006 | $0.003 | $0.00132 |
| 500 | $0.00075 | $0.00375 | $0.00165 |
| 1,000 | $0.0015 | $0.0075 | $0.0033 |
| 2,000 | $0.003 | $0.015 | $0.0066 |
| 5,000 | $0.0075 | $0.0375 | $0.0165 |
| 10,000 | $0.015 | $0.075 | $0.033 |
| 25,000 | $0.0375 | $0.1875 | $0.0825 |
| 50,000 | $0.075 | $0.375 | $0.165 |
| 100,000 | $0.15 | $0.75 | $0.33 |
| 250,000 | $0.375 | $1.875 | $0.825 |
| 500,000 | $0.75 | $3.75 | $1.65 |
| 1,000,000 | $1.50 | $7.50 | $3.30 |
| 5,000,000 | $7.50 | $37.50 | $16.50 |
| 10,000,000 | $15.00 | $75.00 | $33.00 |
| 50,000,000 | $75.00 | $375.00 | $165.00 |
| 100,000,000 | $150.00 | $750.00 | $330.00 |
| 500,000,000 | $750.00 | $3,750.00 | $1,650.00 |
| 1,000,000,000 | $1,500.00 | $7,500.00 | $3,300.00 |
| 10,000,000,000 | $15,000.00 | $75,000.00 | $33,000.00 |
| 100,000,000,000 | $150,000.00 | $750,000.00 | $330,000.00 |
Tokens for a fixed budget
Tokens Mistral Medium 3.5 can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 6,667 | 1,333 | 3,030 |
| $0.1 | 66,667 | 13,333 | 30,303 |
| $0.5 | 333,333 | 66,667 | 151,515 |
| $1.00 | 666,667 | 133,333 | 303,030 |
| $5.00 | 3.33M | 666,667 | 1.52M |
| $10.00 | 6.67M | 1.33M | 3.03M |
| $20.00 | 13.3M | 2.67M | 6.06M |
| $25.00 | 16.7M | 3.33M | 7.58M |
| $30.00 | 20M | 4M | 9.09M |
| $50.00 | 33.3M | 6.67M | 15.2M |
| $100.00 | 66.7M | 13.3M | 30.3M |
| $250.00 | 166.7M | 33.3M | 75.8M |
| $500.00 | 333.3M | 66.7M | 151.5M |
| $1,000.00 | 666.7M | 133.3M | 303M |
| $5,000.00 | 3.33B | 666.7M | 1.52B |
| $10,000.00 | 6.67B | 1.33B | 3.03B |
At these rates
- A workload with 70% input and 30% output costs $3.30 per 1 million total tokens and $330.00 per 100 million.
- At the same token count, output costs 5 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 128,000-token context window with input alone would cost about $0.192, before any output.
- Cached input is $0.15 per million, 90% below standard input when the workload meets the provider’s cache rules.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.