GLM 5.3
Inferenceapis textinferenceapis/zai-org/GLM-5.3
Input
$1.82
per 1M input tokens
Output
$5.72
per 1M output tokens
Cache read
$0.3400
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
1,048,575
Max output
1,048,575
Effective date
Oct 27, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Oct 27, 2026 | $1.82 | $5.72 | $2.80 |
| Oct 16, 2026 | $1.82 | $5.72 | $2.80 |
GLM 5.3 on other providers
Openrouter
· $0.0390 in / $3.39 out
Clf Ai Gateway
· $0.5600 in / $1.76 out
Gmi
· $0.7000 in / $2.20 out
Wandb
· $0.7500 in / $3.00 out
Sail
· $0.9800 in / $3.08 out
Scx-Ai
· $0.9800 in / $3.08 out
Aiand
· $1.00 in / $4.00 out
Coralbricks
· $1.12 in / $4.40 out
Aihubmix
· $1.13 in / $3.94 out
Bigmodel
· $1.14 in / $4.00 out
Kyma
· $1.18 in / $3.70 out
Friendliai
· $1.26 in / $3.96 out
Other Inferenceapis models
inferenceapis/gpt-oss-20b
· $0.1900/Mtok out
inferenceapis/openai/gpt-oss-20b
· $0.1900/Mtok out
inferenceapis/Qwen/Qwen3.8-Flash
· $0.5000/Mtok out
inferenceapis/qwen3.8-flash
· $0.5000/Mtok out
inferenceapis/deepseek-ai/DeepSeek-V3
· $0.3800/Mtok out
inferenceapis/deepseek-ai/DeepSeek-V4-Flash
· $0.3800/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.