All models
GLM 5.2
z-ai/glm-5.2
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Modalities
Text
In / Out price
$0.669 / $2.103 per 1M
Context
1.05M · 131K out
Released
Jun 13, 2026
Providers
Live list prices and uptime across 33 providers serving this model.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output | Uptime 24h |
|---|---|---|---|---|---|---|
| StreamLakefp8 | $0.752 | $2.365 | $0.14 | 1.02M | 128K | 99.26% |
| Novitafp8 | $0.753 | $2.367 | $0.14 | 1.05M | 131K | 99.36% |
| CoreWeavefp4 | $0.76 | $2.42 | $0.14 | 262K | 262K | 98.25% |
| Baidufp8 | $0.77 | $2.42 | $0.143 | 1.05M | 131K | 99.69% |
| AkashMLfp8 | $0.77 | $2.42 | $0.143 | 97K | 97K | 96.88% |
| Alibaba | $0.826 | $2.596 | $0.165 | 1.05M | 131K | 99.45% |
| GMICloudfp8 | $0.924 | $2.904 | $0.172 | 1.05M | — | 96.17% |
| DeepInfrafp4 | $0.93 | $3.00 | $0.18 | 1.05M | 131K | 98.64% |
| Inceptronfp4 | $0.94 | $2.90 | $0.17 | 1.05M | 1.05M | 94.06% |
| DigitalOcean | $1.05 | $4.40 | $0.21 | 262K | — | 98.48% |
| Ambientfp8 | $1.05 | $4.40 | $0.20 | 101K | 101K | 69.29% |
| Morph | $1.10 | $4.10 | $0.22 | 1.05M | 1.05M | 98.12% |
| Sail Researchfp8 | $1.12 | $3.52 | $0.208 | 1.05M | 131K | 97.81% |
| Decartfp8 | $1.20 | $2.50 | $0.20 | 1.05M | 1.05M | 95.32% |
| Chutesfp4 | $1.25 | $3.95 | $0.625 | 1.05M | 66K | 94.41% |
| Waferfp4 | $1.26 | $3.96 | $0.234 | 1.05M | 131K | 99.71% |
| AtlasCloudfp8 | $1.26 | $3.96 | $0.234 | 1.05M | 131K | 99.23% |
| SiliconFlowfp8 | $1.302 | $4.092 | $0.26 | 1.05M | 262K | 99.34% |
| Z.AIfp8 | $1.40 | $4.40 | $0.26 | 1.05M | 131K | 99.60% |
| Fireworks | $1.40 | $4.40 | $0.14 | 1.05M | — | 98.92% |
| Cloudflare | $1.40 | $4.40 | $0.26 | 262K | 262K | 100.00% |
| Friendli | $1.40 | $4.40 | $0.26 | 1.05M | 1.05M | 98.93% |
| Parasailfp4 | $1.40 | $4.40 | $0.26 | 262K | 262K | 90.43% |
| Venicefp8 | $1.40 | $4.40 | $0.26 | 1M | 131K | 97.85% |
| Together | $1.40 | $4.40 | $0.26 | 262K | — | 98.38% |
| Ionstreamfp4 | $1.40 | $4.40 | $0.26 | 1.05M | 131K | 78.09% |
| Phala | $1.40 | $4.40 | $0.70 | 1.05M | 131K | 99.16% |
| BaseTenfp8 | $1.40 | $4.40 | $0.14 | 524K | 524K | 99.88% |
| Waferfp4 | $2.10 | $6.60 | $0.21 | 1.05M | 131K | 99.70% |
| Fireworks | $2.10 | $6.60 | $0.21 | 1.05M | — | 96.39% |
| BaseTenfp8 | $2.10 | $6.60 | $0.21 | 524K | 524K | 99.93% |
| Alibaba | $2.31 | $7.26 | $0.462 | 1.05M | 131K | 99.88% |
| Io Netfp8 | $2.75 | $6.016 | $1.375 | 262K | 66K | 99.54% |
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
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
top_k
top_logprobs
top_p
Pricing detail
- Input
- $0.669
- Output
- $2.103
- Cache read
- $0.124
- Cache write
- —
USD per 1M tokens.