Deprecated on Sep 25, 2026. 20 providers still list it at the prices below.
Context
1M
Max output
1M
Serving providers
20
Cheapest input
$0.05 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Benchmarks
independent evaluations · source: ARC Prize, Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
83 t/s
tokens / second
Time to first token
2.97s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AA-BriefcaseUndated | 38% | default | — | |||||||||||||||||||||||||||||
| APEX Agents | 34% | default | — | |||||||||||||||||||||||||||||
| ARC-AGI-2 | 23% | default | $0.25 | |||||||||||||||||||||||||||||
| Automation Bench | 0.3 | default | — | |||||||||||||||||||||||||||||
| CritPt | 21% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 3533.8 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 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 | 78% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||||||||||||||||||
| Omniscience | 4.4 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| Omniscience Non Hallucination | 0.7 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| SciCode | 51% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| SWE-bench Pro | 62% | default | — | |||||||||||||||||||||||||||||
| Terminal Bench40 | 0.0 | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| TerminalBench Hard | 51% | default | — | |||||||||||||||||||||||||||||
| TerminalBench v2.1 | 78% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| τ-bench Banking | 35% | default | — | |||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||
| τ²-bench | 99% | default | — | |||||||||||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
We cannot tell whether this benchmark is still being published. Treat these scores as undated.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.05 to $1.80 per 1M tokens across 20 providers, so the dearest route costs 3500% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouterRouted quote | $0.05 | $7.00 | 1 | |||||||||||||
Standardz-ai/glm-5.2
| ||||||||||||||||
| Scx AI | $0.61 | $1.98 | 1 | |||||||||||||
Standardscx-ai/GLM-5.2
| ||||||||||||||||
| DeepInfra | $0.75 | $2.40 | 1 | |||||||||||||
Standarddeepinfra/zai-org/GLM-5.2
| ||||||||||||||||
| Wandb | $0.76 | $2.42 | 1 | |||||||||||||
Standardwandb/zai-org/GLM-5.2
| ||||||||||||||||
| VercelVercel reseller quote | $0.80 | $2.55 | 1 | |||||||||||||
Standardzai/glm-5.2
| ||||||||||||||||
| Baseten | $1.40 | $4.40 | 1 | |||||||||||||
Standardbaseten/zai-org/GLM-5.2
| ||||||||||||||||
| Cloudflare | $1.40 | $4.40 | 1 | |||||||||||||
Standardcloudflare/@cf/zai-org/glm-5.2
| ||||||||||||||||
| Dashscope | $1.40 | $4.40 | 1 | |||||||||||||
Standarddashscope/glm-5.2
| ||||||||||||||||
| Vercel is dearest at $2.80 / $8.80 | ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 56% since first tracked
Cost calculator
estimate your monthly spend on this model$570
estimated / month
Model IDs
copy the exact identifier for your platformz-ai/glm-5.2:freez-ai/glm-5.2scx-ai/GLM-5.2z-ai/glm-5.2:batchdeepinfra/zai-org/GLM-5.2wandb/zai-org/GLM-5.2zai/glm-5.2tencent/glm-5.2cloudflare/@cf/zai-org/glm-5.2fireworks_ai/accounts/fireworks/models/glm-5p2dashscope/glm-5.2databricks/databricks-glm-5-2mistral/glm-5-2together_ai/zai-org/GLM-5.2novita/zai-org/glm-5.2qwencloud/glm-5.2qwen_ai_platform/glm-5.2zai/glm-5.2nebius/zai-org/GLM-5.2friendliai/zai-org/GLM-5.2baseten/zai-org/GLM-5.2scaleway/glm-5.2zai/glm-5.2-fast
Frequently asked questions
GLM 5.2 pricing, context and availabilityIs GLM 5.2 still available?
GLM 5.2 was deprecated on 2026-09-25, but 20 serving providers still list it.
How much does GLM 5.2 cost?
GLM 5.2 costs $0.05 per 1M input tokens as an OpenRouter routed quote, and $1.98 per 1M output tokens from Scx AI. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day. Across 20 serving providers, input prices range from $0.05 to $1.80 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 20 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest, as a routed quote.
What can GLM 5.2 do?
GLM 5.2 supports image input (vision), 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 Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI