GLM 5.3
z-ai/glm-5.3
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
Modalities
Text
In / Out price
$1.40 / $4.40 per 1M
Context
1.31M · 944K out
Released
Aug 14, 2026
Providers
Live list prices and uptime across 34 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| Baidufp8 | $0.773 | $2.429 | $0.144 | 1.05M | 131K | 99.87% |
| Morph | $0.773 | $2.431 | $0.127 | 1.05M | 944K | 98.73% |
| Inceptronfp4 | $0.779 | $2.917 | $0.146 | 1.05M | 944K | 97.17% |
| Rekafp8 | $0.784 | $2.653 | $0.157 | 262K | 236K | 97.97% |
| Io Netfp8 | $0.806 | $2.728 | $0.161 | 262K | 33K | 98.99% |
| Novitafp8 | $0.867 | $2.724 | $0.161 | 1.05M | 131K | 90.21% |
| InferenceNetfp4 | $0.90 | $3.00 | $0.15 | 1M | 131K | 92.07% |
| DeepInfrafp4 | $0.90 | $3.00 | $0.15 | 1.05M | 131K | 95.53% |
| Phala | $0.91 | $2.86 | $0.169 | 1.05M | 131K | 99.64% |
| DigitalOcean | $0.91 | $2.86 | $0.169 | 1.05M | 128K | 77.74% |
| Sail Researchfp8 | $1.025 | $3.29 | $0.19 | 1.05M | 944K | 96.99% |
| GMICloudfp8 | $1.05 | $3.30 | $0.195 | 1.05M | 944K | 99.00% |
| Makorafp4 | $1.05 | $4.20 | $0.19 | 980K | 128K | 91.64% |
| SiliconFlowfp8 | $1.12 | $3.52 | $0.208 | 1.05M | 262K | 71.82% |
| Alibaba | $1.19 | $3.74 | $0.238 | 1M | 131K | 99.96% |
| Decartfp4 | $1.19 | $3.74 | $0.196 | 1.05M | 944K | 99.17% |
| Sail Researchfp8 | $1.207 | $3.871 | $0.225 | 1.05M | 944K | 97.48% |
| Friendli | $1.26 | $3.96 | $0.234 | 1.05M | 944K | 99.99% |
| AkashMLfp8 | $1.30 | $4.40 | $0.26 | 1.05M | 131K | 99.94% |
| BaseTenfp4 | $1.40 | $4.40 | $0.14 | 1.05M | 262K | 99.94% |
| Mistralnvfp4 | $1.40 | $4.40 | $0.14 | 1.05M | 131K | 99.91% |
| Crusoefp4 | $1.40 | $4.40 | $0.26 | 1.05M | 944K | 97.59% |
| Wafer | $1.40 | $4.40 | $0.26 | 1.05M | 944K | 97.44% |
| Venice | $1.40 | $4.40 | $0.26 | 1M | 131K | 59.29% |
| Together | $1.40 | $4.40 | $0.26 | 1.05M | 944K | 94.69% |
| Parasailfp8 | $1.40 | $4.40 | $0.26 | 1.05M | 944K | 99.48% |
| Modal | $1.40 | $4.40 | $0.26 | 1.05M | 944K | 98.89% |
| BaseTenfp4 | $1.40 | $4.40 | $0.14 | 1.05M | 262K | 99.87% |
| Fireworks | $1.40 | $4.40 | $0.26 | 1.05M | 944K | 99.34% |
| Cloudflare | $1.40 | $4.40 | $0.26 | 1.31M | 1.18M | 99.94% |
| AtlasCloudfp8 | $1.40 | $4.40 | $0.26 | 1.05M | 131K | 99.08% |
| Z.AIfp8 | $1.40 | $4.40 | $0.26 | 1.05M | 131K | 99.91% |
| BaseTenfp8 | $2.10 | $6.60 | $0.21 | 1.05M | 262K | 93.60% |
| BaseTenfp8 | $2.10 | $6.60 | $0.21 | 1.05M | 262K | 97.45% |
No implicit prompt caching; cache reads require explicit cache control.
Capabilities
Tool calling
Reasoning
Frequency penalty
Include reasoning
Logit bias
Logprobs
Max tokens
Min p
Parallel tool calls
Presence penalty
Reasoning effort
Repetition penalty
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top K
Top logprobs
Top P
Pricing detail
- Input
- $1.40
- Output
- $4.40
- Cache read
- $0.26
- Cache write
- —
USD per 1M tokens.