GLM 5.2 Fast pricing
Source: litellm · updated 2026-11-16
Short answer: GLM 5.2 Fast costs $2.10 per million input tokens and $6.60 per million output tokens. That is a 3:1 blended rate of $3.23 per million tokens, ranking it #697 of 822 tracked models by input price.
Input / 1M
$2.10
Output / 1M
$6.60
Output ÷ input
3.14×
Context window
1,048,576
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $2.10 |
| Output, per 1M tokens | $6.60 |
| Output ÷ input multiple | 3.14× |
| 3:1 blended, per 1M tokens | $3.23 |
| Context window | 1,048,576 tokens |
| Vendor | baseten |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $2.10 | $1.65 | $3.75 |
| 10M in / 2.5M out | $21.00 | $16.50 | $37.50 |
| 100M in / 25M out | $210 | $165 | $375 |
Other baseten models
| Model | Input | Output |
|---|---|---|
| Nvidia Nemotron 3.5 Super VL 120 B A12 B | $0.200 | $0.500 |
| Beam 1.0 | $0.400 | $1.20 |
| Nvidia Nemotron 3 Ultra 550 B A55 B | $0.600 | $2.40 |
| DeepSeek V4.1 Flash 1017 Fast | $0.600 | $2.40 |
Cheaper alternatives
Next cheaper option: Magnum V4 72 B at $2.50 per 1M input tokens. Next step up: Qwen 3.8 Max at $2.23 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.