Baseten
GLM-5.2 Fast (Baseten) token cost
Faster GLM-5.2 variant on Baseten when latency matters more than token price.
Published list rates
Input
$2.10
per 1M tokens
Output
$6.60
per 1M tokens
Cached input
$0.21
per 1M tokens
Context window
200,000
tokens
Pricing source: Baseten Model APIs 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
Read down to see GLM-5.2 Fast (Baseten) get more expensive as tokens grow. The last column is a typical mix: 70% input, 30% output.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.000002 | $0.000007 | $0.000003 |
| 10 | $0.000021 | $0.000066 | $0.000035 |
| 100 | $0.00021 | $0.00066 | $0.000345 |
| 200 | $0.00042 | $0.00132 | $0.00069 |
| 300 | $0.00063 | $0.00198 | $0.001035 |
| 400 | $0.00084 | $0.00264 | $0.00138 |
| 500 | $0.00105 | $0.0033 | $0.001725 |
| 1,000 | $0.0021 | $0.0066 | $0.00345 |
| 2,000 | $0.0042 | $0.0132 | $0.0069 |
| 5,000 | $0.0105 | $0.033 | $0.01725 |
| 10,000 | $0.021 | $0.066 | $0.0345 |
| 25,000 | $0.0525 | $0.165 | $0.08625 |
| 50,000 | $0.105 | $0.33 | $0.1725 |
| 100,000 | $0.21 | $0.66 | $0.345 |
| 250,000 | $0.525 | $1.65 | $0.8625 |
| 500,000 | $1.05 | $3.30 | $1.725 |
| 1,000,000 | $2.10 | $6.60 | $3.45 |
| 5,000,000 | $10.50 | $33.00 | $17.25 |
| 10,000,000 | $21.00 | $66.00 | $34.50 |
| 50,000,000 | $105.00 | $330.00 | $172.50 |
| 100,000,000 | $210.00 | $660.00 | $345.00 |
| 500,000,000 | $1,050.00 | $3,300.00 | $1,725.00 |
| 1,000,000,000 | $2,100.00 | $6,600.00 | $3,450.00 |
| 10,000,000,000 | $21,000.00 | $66,000.00 | $34,500.00 |
| 100,000,000,000 | $210,000.00 | $660,000.00 | $345,000.00 |
Tokens for a fixed budget
If you cap spend, this is roughly how many GLM-5.2 Fast (Baseten) tokens that money buys.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 4,762 | 1,515 | 2,899 |
| $0.1 | 47,619 | 15,152 | 28,986 |
| $0.5 | 238,095 | 75,758 | 144,928 |
| $1.00 | 476,190 | 151,515 | 289,855 |
| $5.00 | 2.38M | 757,576 | 1.45M |
| $10.00 | 4.76M | 1.52M | 2.9M |
| $20.00 | 9.52M | 3.03M | 5.8M |
| $25.00 | 11.9M | 3.79M | 7.25M |
| $30.00 | 14.3M | 4.55M | 8.7M |
| $50.00 | 23.8M | 7.58M | 14.5M |
| $100.00 | 47.6M | 15.2M | 29M |
| $250.00 | 119M | 37.9M | 72.5M |
| $500.00 | 238.1M | 75.8M | 144.9M |
| $1,000.00 | 476.2M | 151.5M | 289.9M |
| $5,000.00 | 2.38B | 757.6M | 1.45B |
| $10,000.00 | 4.76B | 1.52B | 2.9B |
At these rates
- A workload with 70% input and 30% output costs $3.45 per 1 million total tokens and $345.00 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 $0.42, before any output.
- Cached input is $0.21 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.