DeepInfra
Mistral Nemo (DeepInfra) token cost
Mistral Nemo Instruct on DeepInfra among the cheapest 12B-class open hosts.
Published list rates
Input
$0.019
per 1M tokens
Output
$0.03
per 1M tokens
Context window
128,000
tokens
Pricing source: DeepInfra 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
Mistral Nemo (DeepInfra) at rising volume: prompt-only, reply-only, and a mixed chat (70% in, 30% out).
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000000019 | $0.00000003 | $0.0000000223 |
| 10 | $0.00000019 | $0.0000003 | $0.000000223 |
| 100 | $0.000002 | $0.000003 | $0.000002 |
| 200 | $0.000004 | $0.000006 | $0.000004 |
| 300 | $0.000006 | $0.000009 | $0.000007 |
| 400 | $0.000008 | $0.000012 | $0.000009 |
| 500 | $0.00001 | $0.000015 | $0.000011 |
| 1,000 | $0.000019 | $0.00003 | $0.000022 |
| 2,000 | $0.000038 | $0.00006 | $0.000045 |
| 5,000 | $0.000095 | $0.00015 | $0.000112 |
| 10,000 | $0.00019 | $0.0003 | $0.000223 |
| 25,000 | $0.000475 | $0.00075 | $0.000558 |
| 50,000 | $0.00095 | $0.0015 | $0.001115 |
| 100,000 | $0.0019 | $0.003 | $0.00223 |
| 250,000 | $0.00475 | $0.0075 | $0.005575 |
| 500,000 | $0.0095 | $0.015 | $0.01115 |
| 1,000,000 | $0.019 | $0.03 | $0.0223 |
| 5,000,000 | $0.095 | $0.15 | $0.1115 |
| 10,000,000 | $0.19 | $0.3 | $0.223 |
| 50,000,000 | $0.95 | $1.50 | $1.115 |
| 100,000,000 | $1.90 | $3.00 | $2.23 |
| 500,000,000 | $9.50 | $15.00 | $11.15 |
| 1,000,000,000 | $19.00 | $30.00 | $22.30 |
| 10,000,000,000 | $190.00 | $300.00 | $223.00 |
| 100,000,000,000 | $1,900.00 | $3,000.00 | $2,230.00 |
Tokens for a fixed budget
How far a fixed spend goes on Mistral Nemo (DeepInfra) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 526,316 | 333,333 | 448,430 |
| $0.1 | 5.26M | 3.33M | 4.48M |
| $0.5 | 26.3M | 16.7M | 22.4M |
| $1.00 | 52.6M | 33.3M | 44.8M |
| $5.00 | 263.2M | 166.7M | 224.2M |
| $10.00 | 526.3M | 333.3M | 448.4M |
| $20.00 | 1.05B | 666.7M | 896.9M |
| $25.00 | 1.32B | 833.3M | 1.12B |
| $30.00 | 1.58B | 1B | 1.35B |
| $50.00 | 2.63B | 1.67B | 2.24B |
| $100.00 | 5.26B | 3.33B | 4.48B |
| $250.00 | 13.2B | 8.33B | 11.2B |
| $500.00 | 26.3B | 16.7B | 22.4B |
| $1,000.00 | 52.6B | 33.3B | 44.8B |
| $5,000.00 | 263.2B | 166.7B | 224.2B |
| $10,000.00 | 526.3B | 333.3B | 448.4B |
At these rates
- A workload with 70% input and 30% output costs $0.0223 per 1 million total tokens and $2.23 per 100 million.
- At the same token count, output costs 1.58 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 $0.002432, before any output.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.