Z.ai: GLM 5.2
z-ai/glm-5.2
Model weightsGLM 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, and complex multi-step automation.
Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is particularly strong at coding and tool use across long-running tasks, able to maintain engineering context and follow standards consistently through a full development workflow, from requirements to multi-platform deployment, in a single task.
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
| $0.6200 | $2.4200 | $0.1400 | 0.55s | 137 tok/s | ||
| $0.0070 | $6.8000 | $0.0060 | 0.44s | 124 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.37s | 160 tok/s | ||
| $0.1900 | $8.0000 | $0.1800 | 0.46s | 127 tok/s | ||
| $0.0066 | $7.9833 | $0.0066 | 0.96s | 80 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.39s | 94 tok/s | ||
| $0.6430 | $1.9780 | $0.2170 | 0.59s | 80 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 0.43s | 129 tok/s | ||
| $0.1900 | $8.0000 | $0.1900 | 1.32s | 89 tok/s | ||
50% off | $1.302$0.6510 | $4.092$2.0460 | $0.26$0.1300 | 1.21s | 69 tok/s | |
| $2.1000 | $6.6000 | $0.2100 | 0.44s | 198 tok/s | ||
| $0.9660 | $3.0360 | $0.1932 | 1.16s | 72 tok/s | ||
| $0.7000 | $2.2000 | $0.1050 | 0.63s | 89 tok/s | ||
| $1.5400 | $4.8400 | $0.1540 | 0.86s | 126 tok/s | ||
Fast | $2.1000 | $6.6000 | $0.2100 | 0.37s | 114 tok/s | |
33% off | $1.40$0.9380 | $4.40$2.9480 | $0.26$0.1742 | 1.29s | 45 tok/s | |
| $1.4000 | $4.4000 | $0.1400 | 1.17s | 75 tok/s | ||
56% off | $1.40$0.6131 | $4.40$1.9270 | $0.26$0.1139 | 1.84s | 38 tok/s | |
| $0.75$0.5625 | $2.40$1.8000 | $0.14$0.1050 | 2.16s | 42 tok/s | ||
54% off | $1.40$0.6496 | $4.40$2.0420 | $0.26$0.1206 | 2.38s | 42 tok/s | |
| $1.4000 | $4.4000 | $0.2600 | 0.66s | 129 tok/s | ||
| $1.4000 | $4.4000 | $0.1400 | 0.65s | 89 tok/s | ||
| $0.6000 | $2.0000 | $0.1500 | 1.08s | 65 tok/s | ||
| $1.4000 | $4.4000 | $0.1400 | 3.02s | 59 tok/s | ||
| $1.4000 | $4.4000 | $0.1400 | 3.27s | 52 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 2.30s | 55 tok/s | ||
| $1.125$0.8438 | $3.60$2.7000 | $0.21$0.1575 | 1.88s | 44 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 2.38s | 60 tok/s | ||
| $1.4000 | $4.4000 | $0.2600 | 1.41s | 36 tok/s | ||
| $1.1200 | $3.5200 | $0.2240 | 2.40s | 53 tok/s | ||
Fast | $2.2500 | $7.8800 | $0.5600 | 1.13s | 65 tok/s | |
Fast | $2.3100 | $7.2600 | $0.4620 | 0.85s | 112 tok/s | |
| $1.4000 | $4.4000 | $0.2600 | -- | -- | ||
Not used in Standard routing:Why these endpoints are not used | ||||||
| $0.60$0.4500 | $1.92$1.4400 | $0.112$0.0840 | 2.80s | 45 tok/s | ||
- Input $0.62 / Output $2.42137 tok/s96.99% uptime
- Input $0.007 / Output $6.80124 tok/s100.00% uptime
- Input $1.40 / Output $4.40160 tok/s100.00% uptime
- Input $0.19 / Output $8.00127 tok/s100.00% uptime
- Input $0.0066 / Output $7.983380 tok/s99.86% uptime
- Input $1.40 / Output $4.4094 tok/s99.88% uptime
- Input $0.643 / Output $1.97880 tok/s100.00% uptime
- Input $1.40 / Output $4.40129 tok/s99.94% uptime
- Input $0.19 / Output $8.0089 tok/s100.00% uptime
- Input $0.651 / Output $2.04650% off69 tok/s100.00% uptime
- Input $2.10 / Output $6.60198 tok/s100.00% uptimeFast
- Input $0.966 / Output $3.03672 tok/s98.09% uptime
- Input $0.70 / Output $2.2089 tok/s99.77% uptime
Input $1.54 / Output $4.84126 tok/s99.94% uptime- Input $2.10 / Output $6.60114 tok/s100.00% uptimeFast
- Input $0.938 / Output $2.94833% off45 tok/s100.00% uptime
Input $1.40 / Output $4.4075 tok/s100.00% uptime- Input $0.6131 / Output $1.92756% off38 tok/s100.00% uptime
Input $0.5625 / Output $1.8025% off42 tok/s99.35% uptime- Input $0.6496 / Output $2.04254% off42 tok/s100.00% uptime
- Input $1.40 / Output $4.40129 tok/s98.82% uptime
- Input $1.40 / Output $4.4089 tok/s99.62% uptime
- Input $0.60 / Output $2.0065 tok/s69.52% uptime
- Input $1.40 / Output $4.4059 tok/s100.00% uptime
- Input $1.40 / Output $4.4052 tok/s100.00% uptime
- Input $1.40 / Output $4.4055 tok/s99.91% uptime
Input $0.8438 / Output $2.7044 tok/s98.83% uptimePriority+11 more label- Input $1.40 / Output $4.4060 tok/s100.00% uptime
- Input $1.40 / Output $4.4036 tok/s100.00% uptime
- Input $1.12 / Output $3.5253 tok/s100.00% uptime
- Input $2.25 / Output $7.8865 tok/s100.00% uptimeFast
- Input $2.31 / Output $7.26112 tok/s97.50% uptimeFast
- Input $1.40 / Output $4.40-- tok/s99.96% uptime
- Not used in Standard routing:Why these endpoints are not used
Input $0.45 / Output $1.4445 tok/s100.00% uptimeFlex+11 more label
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
GLM 5.2 — Price history
| $0.00611 | $6.80 | 88.5% | 32.5% | ||
| $0.00659 | $7.98 | 84.2% | 3.1% | ||
| $0.18095 | $8.00 | 90.5% | 7.4% | ||
| $0.18998 | $8.00 | 66.4% | 0.4% | ||
| $0.20395 | $1.65 | 75.3% | 13.6% | ||
| $0.23229 | $1.80 | 72.3% | 3.5% | ||
| $0.24506 | $2.05 | 78.0% | 1.6% | ||
| $0.26256 | $3.04 | 91.0% | 0.5% | ||
| $0.26745 | $2.42 | 73.4% | 16.8% | ||
| $0.27279 | $4.40 | 89.5% | 1.8% | ||
| $0.28013 | $4.40 | 88.9% | 0.4% | ||
| $0.29606 | $2.05 | 67.1% | 0.7% | ||
| $0.30297 | $2.20 | 66.7% | 0.2% | ||
| $0.33466 | $2.00 | 59.0% | 0.1% | ||
| $0.34800 | $1.98 | 69.2% | 0.8% | ||
| $0.40035 | $4.40 | 87.7% | 1.6% | ||
| $0.40928 | $4.40 | 86.9% | 1.1% | ||
| $0.42099 | $4.84 | 80.7% | 0.9% | ||
| $0.45170 | $4.40 | 83.2% | 6.3% | ||
| $0.49906 | $2.70 | 50.2% | 0.3% | ||
| $0.52481 | $3.52 | 66.4% | 0.1% | ||
| $0.54107 | $4.40 | 75.3% | 0.0% | ||
| $0.57816 | $2.95 | 47.1% | 0.0% | ||
| $0.58488 | $4.40 | 71.5% | 0.4% | ||
Fast | $0.64261 | $7.26 | 90.2% | 0.6% | |
| $0.71806 | $4.40 | 59.8% | 0.2% | ||
| $0.73415 | $6.60 | 72.3% | 0.5% | ||
Fast | $0.76844 | $6.60 | 70.5% | 0.7% | |
| $0.78350 | $4.40 | 48.9% | 1.8% | ||
| $0.80495 | $4.40 | 47.2% | 0.4% | ||
| $0.80858 | $4.40 | 51.9% | 1.0% | ||
Fast | $1.10952 | $7.88 | 67.5% | 0.2% | |
| — | — | — | — | ||
Not used in Standard routing:Why these endpoints are not used | |||||
| $0.19873 | $1.44 | 68.6% | 0.4% | ||
- Effective in $0.00611 / Effective out $6.80Token share32.5%
- Effective in $0.00659 / Effective out $7.98Token share3.1%
- Effective in $0.18095 / Effective out $8.00Token share7.4%
- Effective in $0.18998 / Effective out $8.00Token share0.4%
- Effective in $0.20395 / Effective out $1.65Token share13.6%
- Effective in $0.23229 / Effective out $1.80Token share3.5%
- Effective in $0.24506 / Effective out $2.05Token share1.6%
- Effective in $0.26256 / Effective out $3.04Token share0.5%
- Effective in $0.26745 / Effective out $2.42Token share16.8%
- Effective in $0.27279 / Effective out $4.40Token share1.8%
- Effective in $0.28013 / Effective out $4.40Token share0.4%
- Effective in $0.29606 / Effective out $2.05Token share0.7%
- Effective in $0.30297 / Effective out $2.20Token share0.2%
- Effective in $0.33466 / Effective out $2.00Token share0.1%
- Effective in $0.34800 / Effective out $1.98Token share0.8%
- Effective in $0.40035 / Effective out $4.40Token share1.6%
- Effective in $0.40928 / Effective out $4.40Token share1.1%
- Effective in $0.42099 / Effective out $4.84Token share0.9%
- Effective in $0.45170 / Effective out $4.40Token share6.3%
- Effective in $0.49906 / Effective out $2.70PriorityToken share0.3%
- Effective in $0.52481 / Effective out $3.52Token share0.1%
- Effective in $0.54107 / Effective out $4.40Token share0.0%
- Effective in $0.57816 / Effective out $2.95Token share0.0%
- Effective in $0.58488 / Effective out $4.40Token share0.4%
- Effective in $0.64261 / Effective out $7.26FastToken share0.6%
- Effective in $0.71806 / Effective out $4.40Token share0.2%
- Effective in $0.73415 / Effective out $6.60FastToken share0.5%
- Effective in $0.76844 / Effective out $6.60FastToken share0.7%
- Effective in $0.78350 / Effective out $4.40Token share1.8%
- Effective in $0.80495 / Effective out $4.40Token share0.4%
- Effective in $0.80858 / Effective out $4.40Token share1.0%
- Effective in $1.10952 / Effective out $7.88FastToken share0.2%
- Effective in — / Effective out —Token share —
- Not used in Standard routing:Why these endpoints are not used
- Effective in $0.19873 / Effective out $1.44FlexToken share0.4%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
P50, best across providers
P50, best provider
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Availability over the last 3 days
Last 72 hoursAvailability over the last 24 hours
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | GLM-5.2 (Max) Coding Index | 68.8 |
| Artificial Analysis | GLM-5.2 (Max) Agentic Index | 38.4 |
| Artificial Analysis | GLM-5.2 (Max) GPQA Diamond | 89.5% |
| Artificial Analysis | GLM-5.2 (Max) HLE | 41.1% |
| Artificial Analysis | GLM-5.2 (Max) IFBench | 73.3% |
| Artificial Analysis | GLM-5.2 (Max) τ²-Bench Telecom | 99.1% |
| Artificial Analysis | GLM-5.2 (Max) AA-LCR | 78.3% |
| Artificial Analysis | GLM-5.2 (Max) τ-Bench Banking | 34.6% |
| Artificial Analysis | GLM-5.2 (Max) GDPval-AA | 44.0% |
| Artificial Analysis | GLM-5.2 (Max) CritPt | 20.9% |
| Artificial Analysis | GLM-5.2 (Max) SciCode | 51.2% |
| Artificial Analysis | GLM-5.2 (Max) Terminal-Bench Hard | 50.8% |
| Artificial Analysis | GLM-5.2 (Max) Terminal-Bench 4.0 | 1.0% |
| Artificial Analysis | GLM-5.2 (Max) Terminal-Bench 2.1 | 77.9% |
| Artificial Analysis | GLM-5.2 (Max) AA-Omniscience Accuracy | 21.1% |
| Artificial Analysis | GLM-5.2 (Max) AA-Omniscience Non-Hallucination Rate | 74.1% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) Coding Index | 46.5 |
| Artificial Analysis | GLM-5.2 (Non-reasoning) GPQA Diamond | 68.6% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) HLE | 9.8% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) AA-LCR | 42.3% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) τ-Bench Banking | 16.7% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) GDPval-AA | 37.6% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) CritPt | 3.1% |
| Artificial Analysis | GLM-5.2 (Non-reasoning) Terminal-Bench 2.1 | 51.7% |
| Design Arena | GLM 5.2 Agents Arena Agenticgamedev Elo | 1153 |
| Design Arena | GLM 5.2 Agents Arena Androidnative Elo | 1170 |
| Design Arena | GLM 5.2 Agents Arena Blender3d Elo | 983 |
| Design Arena | GLM 5.2 Agents Arena Full Stack Elo | 1215 |
| Design Arena | GLM 5.2 Agents Arena Godotgamedev Elo | 1142 |
| Design Arena | GLM 5.2 Agents Arena Htmlslides Elo | 1072 |
| Design Arena | GLM 5.2 Agents Arena Mobile Apps Elo | 1154 |
| Design Arena | GLM 5.2 Agents Arena Pdf Elo | 1240 |
| Design Arena | GLM 5.2 Agents Arena Python-Pptxslides Elo | 1160 |
| Design Arena | GLM 5.2 Agents Arena Spreadsheet Elo | 1023 |
| Design Arena | GLM 5.2 Agents Arena Webapps Elo | 1201 |
| Design Arena | GLM 5.2 Models Arena 3D Elo | 1266 |
| Design Arena | GLM 5.2 Models Arena Asciiart Elo | 1173 |
| Design Arena | GLM 5.2 Models Arena Code Categories Elo | 1276 |
| Design Arena | GLM 5.2 Models Arena Data Visualization Elo | 1281 |
| Design Arena | GLM 5.2 Models Arena Game Development Elo | 1256 |
| Design Arena | GLM 5.2 Models Arena SVG Elo | 1194 |
| Design Arena | GLM 5.2 Models Arena UI Component Elo | 1284 |
| Design Arena | GLM 5.2 Models Arena Website Elo | 1277 |
| Vals AI | GLM 5.2 Code Migration | 37.9% |
| Vals AI | GLM 5.2 CorpFin v2 | 66.1% |
| Vals AI | GLM 5.2 EMB | 61.5% |
| Vals AI | GLM 5.2 Finance Agent (v2) | 49.7% |
| Vals AI | GLM 5.2 GPQA Diamond | 85.6% |
| Vals AI | GLM 5.2 Harvey's Legal Agent Benchmark v1 | 7.1% |
| Vals AI | GLM 5.2 LiveCodeBench | 69.5% |
| Vals AI | GLM 5.2 LegalBench | 84.1% |
| Vals AI | GLM 5.2 Legal Research Bench | 31.3% |
| Vals AI | GLM 5.2 MedCode | 40.8% |
| Vals AI | GLM 5.2 MedScribe | 83.5% |
| Vals AI | GLM 5.2 MMLU Pro | 86.7% |
| Vals AI | GLM 5.2 ProgramBench | 0.5% |
| Vals AI | GLM 5.2 ProofBench v1 | 35.0% |
| Vals AI | GLM 5.2 SkillsBench | 45.1% |
| Vals AI | GLM 5.2 SRE Bench | 0.0% |
| Vals AI | GLM 5.2 SWE-bench | 82.8% |
| Vals AI | GLM 5.2 TaxEval v2 | 73.3% |
| Vals AI | GLM 5.2 Terminal-Bench 2.1 | 67.8% |
| Vals AI | GLM 5.2 Vals Index | 53.1% |
| Vals AI | GLM 5.2 Vibe Code Bench v1.1 | 64.0% |
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Available through EU in-region routing
Z.ai: GLM 5.2 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).
- Providers in Europe
- Inceptron, Mistral
- Prices in Europe
- Inceptron: $1.40/M tokens input, $4.40/M tokens output
- Mistral: $1.54/M tokens input, $4.84/M tokens output
- Base URL
https://eu.openrouter.ai/api/v1- Plan
- Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing
Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs
Frequently asked questions
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, and complex multi-step automation. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning.
GLM 5.2 costs $0.0066/M input tokens and $7.983/M output tokens, with separate rates for Cache Read at $0.0066/M tokens.
GLM 5.2 has a 1,048,576 token context window. It supports up to 131,072 completion tokens.
Yes. GLM 5.2 accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.
GLM 5.2 is served by 24 providers on OpenRouter: Relace, Wafer, Cloudflare, DeepInfra, Ambient, StreamLake, CoreWeave, Morph and 16 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
GLM 5.2 was released on June 16, 2026.