Together AI
GLM 5.2 (Together) token cost
GLM 5.2 hosted on Together with cached-input pricing for RAG and chat.
Published list rates
Input
$1.40
per 1M tokens
Output
$4.40
per 1M tokens
Cached input
$0.26
per 1M tokens
Context window
200,000
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
GLM 5.2 (Together) 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 | $0.000001 | $0.000004 | $0.000002 |
| 10 | $0.000014 | $0.000044 | $0.000023 |
| 100 | $0.00014 | $0.00044 | $0.00023 |
| 200 | $0.00028 | $0.00088 | $0.00046 |
| 300 | $0.00042 | $0.00132 | $0.00069 |
| 400 | $0.00056 | $0.00176 | $0.00092 |
| 500 | $0.0007 | $0.0022 | $0.00115 |
| 1,000 | $0.0014 | $0.0044 | $0.0023 |
| 2,000 | $0.0028 | $0.0088 | $0.0046 |
| 5,000 | $0.007 | $0.022 | $0.0115 |
| 10,000 | $0.014 | $0.044 | $0.023 |
| 25,000 | $0.035 | $0.11 | $0.0575 |
| 50,000 | $0.07 | $0.22 | $0.115 |
| 100,000 | $0.14 | $0.44 | $0.23 |
| 250,000 | $0.35 | $1.10 | $0.575 |
| 500,000 | $0.7 | $2.20 | $1.15 |
| 1,000,000 | $1.40 | $4.40 | $2.30 |
| 5,000,000 | $7.00 | $22.00 | $11.50 |
| 10,000,000 | $14.00 | $44.00 | $23.00 |
| 50,000,000 | $70.00 | $220.00 | $115.00 |
| 100,000,000 | $140.00 | $440.00 | $230.00 |
| 500,000,000 | $700.00 | $2,200.00 | $1,150.00 |
| 1,000,000,000 | $1,400.00 | $4,400.00 | $2,300.00 |
| 10,000,000,000 | $14,000.00 | $44,000.00 | $23,000.00 |
| 100,000,000,000 | $140,000.00 | $440,000.00 | $230,000.00 |
Tokens for a fixed budget
How far a fixed spend goes on GLM 5.2 (Together) at these list rates.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 7,143 | 2,273 | 4,348 |
| $0.1 | 71,429 | 22,727 | 43,478 |
| $0.5 | 357,143 | 113,636 | 217,391 |
| $1.00 | 714,286 | 227,273 | 434,783 |
| $5.00 | 3.57M | 1.14M | 2.17M |
| $10.00 | 7.14M | 2.27M | 4.35M |
| $20.00 | 14.3M | 4.55M | 8.7M |
| $25.00 | 17.9M | 5.68M | 10.9M |
| $30.00 | 21.4M | 6.82M | 13M |
| $50.00 | 35.7M | 11.4M | 21.7M |
| $100.00 | 71.4M | 22.7M | 43.5M |
| $250.00 | 178.6M | 56.8M | 108.7M |
| $500.00 | 357.1M | 113.6M | 217.4M |
| $1,000.00 | 714.3M | 227.3M | 434.8M |
| $5,000.00 | 3.57B | 1.14B | 2.17B |
| $10,000.00 | 7.14B | 2.27B | 4.35B |
At these rates
- A workload with 70% input and 30% output costs $2.30 per 1 million total tokens and $230.00 per 100 million.
- At the same token count, output costs 3.14 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 200,000-token context window with input alone would cost about $0.28, before any output.
- Cached input is $0.26 per million, 81% 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.