Together AI
Qwen3.5 9B (Together) token cost
Compact Qwen3.5 9B on Together for multilingual throughput at low unit cost.
Published list rates
Input
$0.17
per 1M tokens
Output
$0.25
per 1M tokens
Context window
128,000
tokens
Pricing source: Together AI 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 Qwen3.5 9B (Together) 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 | $0.00000017 | $0.00000025 | $0.000000194 |
| 10 | $0.000002 | $0.000003 | $0.000002 |
| 100 | $0.000017 | $0.000025 | $0.000019 |
| 200 | $0.000034 | $0.00005 | $0.000039 |
| 300 | $0.000051 | $0.000075 | $0.000058 |
| 400 | $0.000068 | $0.0001 | $0.000078 |
| 500 | $0.000085 | $0.000125 | $0.000097 |
| 1,000 | $0.00017 | $0.00025 | $0.000194 |
| 2,000 | $0.00034 | $0.0005 | $0.000388 |
| 5,000 | $0.00085 | $0.00125 | $0.00097 |
| 10,000 | $0.0017 | $0.0025 | $0.00194 |
| 25,000 | $0.00425 | $0.00625 | $0.00485 |
| 50,000 | $0.0085 | $0.0125 | $0.0097 |
| 100,000 | $0.017 | $0.025 | $0.0194 |
| 250,000 | $0.0425 | $0.0625 | $0.0485 |
| 500,000 | $0.085 | $0.125 | $0.097 |
| 1,000,000 | $0.17 | $0.25 | $0.194 |
| 5,000,000 | $0.85 | $1.25 | $0.97 |
| 10,000,000 | $1.70 | $2.50 | $1.94 |
| 50,000,000 | $8.50 | $12.50 | $9.70 |
| 100,000,000 | $17.00 | $25.00 | $19.40 |
| 500,000,000 | $85.00 | $125.00 | $97.00 |
| 1,000,000,000 | $170.00 | $250.00 | $194.00 |
| 10,000,000,000 | $1,700.00 | $2,500.00 | $1,940.00 |
| 100,000,000,000 | $17,000.00 | $25,000.00 | $19,400.00 |
Tokens for a fixed budget
Tokens Qwen3.5 9B (Together) 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 | 58,824 | 40,000 | 51,546 |
| $0.1 | 588,235 | 400,000 | 515,464 |
| $0.5 | 2.94M | 2M | 2.58M |
| $1.00 | 5.88M | 4M | 5.15M |
| $5.00 | 29.4M | 20M | 25.8M |
| $10.00 | 58.8M | 40M | 51.5M |
| $20.00 | 117.6M | 80M | 103.1M |
| $25.00 | 147.1M | 100M | 128.9M |
| $30.00 | 176.5M | 120M | 154.6M |
| $50.00 | 294.1M | 200M | 257.7M |
| $100.00 | 588.2M | 400M | 515.5M |
| $250.00 | 1.47B | 1B | 1.29B |
| $500.00 | 2.94B | 2B | 2.58B |
| $1,000.00 | 5.88B | 4B | 5.15B |
| $5,000.00 | 29.4B | 20B | 25.8B |
| $10,000.00 | 58.8B | 40B | 51.5B |
At these rates
- A workload with 70% input and 30% output costs $0.194 per 1 million total tokens and $19.40 per 100 million.
- At the same token count, output costs 1.47 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 $0.02176, 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.