DeepInfra
Qwen3 32B (DeepInfra) token cost
Qwen3 32B on DeepInfra for multilingual chat and coding at low unit cost.
Published list rates
Input
$0.08
per 1M tokens
Output
$0.28
per 1M tokens
Context window
40,000
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
- 100,000
- Characters
- 400,000
- Words
- 75,000
- Input tokens
- 70,000
- Output tokens
- 30,000
- Input cost
- $0.0056
- Output cost
- $0.0084
- Total cost
- $0.014
- Combined price per 1M tokens
- $0.14
- Estimated monthly cost
- $8.40
- Estimated daily cost
- $0.28
Cost as volume grows
Three views of Qwen3 32B (DeepInfra): sending only, receiving only, and a 70/30 mix. Same list rates, bigger rows.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000008 | $0.00000028 | $0.00000014 |
| 10 | $0.0000008 | $0.000003 | $0.000001 |
| 100 | $0.000008 | $0.000028 | $0.000014 |
| 200 | $0.000016 | $0.000056 | $0.000028 |
| 300 | $0.000024 | $0.000084 | $0.000042 |
| 400 | $0.000032 | $0.000112 | $0.000056 |
| 500 | $0.00004 | $0.00014 | $0.00007 |
| 1,000 | $0.00008 | $0.00028 | $0.00014 |
| 2,000 | $0.00016 | $0.00056 | $0.00028 |
| 5,000 | $0.0004 | $0.0014 | $0.0007 |
| 10,000 | $0.0008 | $0.0028 | $0.0014 |
| 25,000 | $0.002 | $0.007 | $0.0035 |
| 50,000 | $0.004 | $0.014 | $0.007 |
| 100,000 | $0.008 | $0.028 | $0.014 |
| 250,000 | $0.02 | $0.07 | $0.035 |
| 500,000 | $0.04 | $0.14 | $0.07 |
| 1,000,000 | $0.08 | $0.28 | $0.14 |
| 5,000,000 | $0.4 | $1.40 | $0.7 |
| 10,000,000 | $0.8 | $2.80 | $1.40 |
| 50,000,000 | $4.00 | $14.00 | $7.00 |
| 100,000,000 | $8.00 | $28.00 | $14.00 |
| 500,000,000 | $40.00 | $140.00 | $70.00 |
| 1,000,000,000 | $80.00 | $280.00 | $140.00 |
| 10,000,000,000 | $800.00 | $2,800.00 | $1,400.00 |
| 100,000,000,000 | $8,000.00 | $28,000.00 | $14,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on Qwen3 32B (DeepInfra) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 125,000 | 35,714 | 71,429 |
| $0.1 | 1.25M | 357,143 | 714,286 |
| $0.5 | 6.25M | 1.79M | 3.57M |
| $1.00 | 12.5M | 3.57M | 7.14M |
| $5.00 | 62.5M | 17.9M | 35.7M |
| $10.00 | 125M | 35.7M | 71.4M |
| $20.00 | 250M | 71.4M | 142.9M |
| $25.00 | 312.5M | 89.3M | 178.6M |
| $30.00 | 375M | 107.1M | 214.3M |
| $50.00 | 625M | 178.6M | 357.1M |
| $100.00 | 1.25B | 357.1M | 714.3M |
| $250.00 | 3.13B | 892.9M | 1.79B |
| $500.00 | 6.25B | 1.79B | 3.57B |
| $1,000.00 | 12.5B | 3.57B | 7.14B |
| $5,000.00 | 62.5B | 17.9B | 35.7B |
| $10,000.00 | 125B | 35.7B | 71.4B |
At these rates
- A workload with 70% input and 30% output costs $0.14 per 1 million total tokens and $14.00 per 100 million.
- At the same token count, output costs 3.5 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 40,000-token context window with input alone would cost about $0.0032, 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.