Context
1M
Max output
1M
Serving providers
10
Cheapest input
$0.61 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize, Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
70 t/s
tokens / second
Time to first token
1.56s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-Briefcase | 38% | — | — | |||||||||||||
| APEX Agents | 34% | default | — | |||||||||||||
| ARC-AGI-2 | 23% | default | $0.250 | |||||||||||||
| Automation Bench | 0.3 | default | — | |||||||||||||
| CritPt | 21% | default | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 3533.8 | default | — | |||||||||||||
| ||||||||||||||||
| GDPval | 1505.2 | default | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 89% | default | — | |||||||||||||
| ||||||||||||||||
| Harvey Lab | 0.9 | default | — | |||||||||||||
| Humanity's Last Exam | 41% | default | — | |||||||||||||
| ||||||||||||||||
| IFBench | 73% | default | — | |||||||||||||
| IT-Bench SRE | 43% | default | — | |||||||||||||
| Long-Context Reasoning | 77% | default | — | |||||||||||||
| ||||||||||||||||
| Mlcr Overall | 0.1 | default | — | |||||||||||||
| Omniscience | 4.4 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||
| ||||||||||||||||
| Omniscience Non Hallucination | 0.7 | default | — | |||||||||||||
| ||||||||||||||||
| SciCode | 50% | default | — | |||||||||||||
| ||||||||||||||||
| SWE-bench Pro | 62% | default | — | |||||||||||||
| TerminalBench Hard | 51% | default | — | |||||||||||||
| TerminalBench v2.1 | 78% | default | — | |||||||||||||
| ||||||||||||||||
| τ-bench Banking | 35% | default | — | |||||||||||||
| ||||||||||||||||
| τ²-bench | 99% | default | — | |||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.61 to $1.40 per 1M tokens across 10 providers, so the dearest route costs 130% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Scx AICheapest | $0.61 | $1.98 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| DeepInfra | $0.75 | $2.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Wandb | $0.76 | $2.42 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| OpenRouter | $1.19 | $3.74 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Databricks | $1.40 | $4.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Cloudflare | $1.40 | $4.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Dashscope | $1.40 | $4.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Mistral | $1.40 | $4.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Databricks is dearest at $1.40 / $4.40 | ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 56% since first tracked
Cost calculator
estimate your monthly spend on this model$280
estimated / month
Model IDs
copy the exact identifier for your platformscx-ai/GLM-5.2deepinfra/zai-org/GLM-5.2wandb/zai-org/GLM-5.2z-ai/glm-5.2databricks/databricks-glm-5-2cloudflare/@cf/zai-org/glm-5.2dashscope/glm-5.2mistral/glm-5-2together_ai/zai-org/GLM-5.2novita/zai-org/glm-5.2
Frequently asked questions
GLM 5.2 pricing, context and availabilityHow much does GLM 5.2 cost?
GLM 5.2 costs $0.61 per 1M input tokens and $1.98 per 1M output tokens at its cheapest provider via Scx AI. Across 10 serving providers, input prices range from $0.61 to $1.40 per 1M tokens.
What is the context window of GLM 5.2?
GLM 5.2 accepts up to 1M tokens of context and can return up to 1M output tokens.
Which providers serve GLM 5.2?
GLM 5.2 is available from 10 serving providers, each with its own pricing and model ID. Scx AI is currently the cheapest.
What can GLM 5.2 do?
GLM 5.2 supports tool use, reasoning, prompt caching and structured output.
Other Zhipu models
compare pricing across the Zhipu lineupPopular comparisons
head-to-head pages featuring GLM 5.2
GLM 5.2 vs Claude Fable 5side-by-side pricing & benchmarks GLM 5.2 vs Claude Opus 4.8side-by-side pricing & benchmarks GLM 5.2 vs Claude Sonnet 5side-by-side pricing & benchmarks
GLM 5.2 vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
GLM 5.2 vs Gemini 3.1 Pro Previewside-by-side pricing & benchmarks Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI