GLM 4.7 Flash pricing
Source: openrouter · updated 2026-11-18
Short answer: GLM 4.7 Flash costs $0.060 per million input tokens and $0.400 per million output tokens. That is a 3:1 blended rate of $0.145 per million tokens, ranking it #106 of 833 tracked models by input price.
Input / 1M
$0.060
Output / 1M
$0.400
Output ÷ input
6.61×
Context window
200,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.060 |
| Output, per 1M tokens | $0.400 |
| Output ÷ input multiple | 6.61× |
| 3:1 blended, per 1M tokens | $0.145 |
| Context window | 200,000 tokens |
| Vendor | z-ai |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.060 | $0.100 | $0.161 |
| 10M in / 2.5M out | $0.605 | $1.00 | $1.60 |
| 100M in / 25M out | $6.05 | $10.00 | $16.05 |
Other z-ai models
| Model | Input | Output |
|---|---|---|
| GLM 5.2 | $0.0070 | $6.80 |
| GLM 5.3 Flash | $0.024 | $0.069 |
| GLM 5.3 | $0.070 | $1.40 |
| GLM 4.5 Air | $0.130 | $0.850 |
| GLM 4.6 V | $0.300 | $0.900 |
Compare against
Cheaper alternatives
Next cheaper option: GPT-5 Nano at $0.050 per 1M input tokens. Next step up: Qwen 3 14 B at $0.120 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.