GLM 4 32 B0414 128 K pricing
Source: litellm · updated 2026-10-27
Short answer: GLM 4 32 B0414 128 K costs $0.100 per million input tokens and $0.100 per million output tokens. That is a 3:1 blended rate of $0.100 per million tokens, ranking it #148 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.100 |
| Output, per 1M tokens | $0.100 |
| Output รท input multiple | 1.00× |
| 3:1 blended, per 1M tokens | $0.100 |
| Context window | 128,000 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.100 | $0.025 | $0.125 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $1.00 | $0.250 | $1.25 | ||||
| 100M in / 25M out | $10.00 | $2.50 | $12.50 |
Other zai models
| Model | Input | Output |
|---|---|---|
| GLM 4.5 Airx | $1.10 | $4.50 |
| GLM 5 Code | $1.20 | $5.00 |
| GLM 4.5 X | $2.20 | $8.90 |
Compare against
Cheaper alternatives
Next cheaper option: Dolphin 3.8 B at $0.080 per 1M input tokens. Next step up: Nemotron 3 Nano 30 B A3 B at $0.060 per 1M input tokens.