GLM-5.2
zai/glm-5-2By Z.AI / Zhipu · family: glm · released 2026-06-13
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding100
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)20/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output88
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume8/20
Cost efficiency48
- Headline price (log-scaled)43/95
- Has prompt-cache pricing5/5
Long context90
- Context window (100K → 2M)80/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $9.20 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $18.40 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $5.00 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $15.60 $0.02 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $19.44 $0.02 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from zai · glm-5.2
Cheapest provider: zhipuai-coding-plan · Unknown input + Unknown output
Available on 62 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| Z.AI zai | glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Zhipu AI zhipuai | glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Zhipu AI Coding Plan zhipuai-coding-plan | glm-5.2 | Unknown | Unknown | 1M | 2026-06-13 |
| Z.AI Coding Plan zai-coding-plan | glm-5.2 | Unknown | Unknown | 1M | 2026-06-13 |
| OpenRouter openrouter | z-ai/glm-5.2 | $0.738 | $2.32 | 1.05M | 2026-06-13 |
| Vercel AI Gateway vercel | zai/glm-5.2 | $1.40 | $4.40 | 1.04M | 2026-06-16 |
| Together AI togetherai | zai-org/GLM-5.2 | $1.40 | $4.40 | 262K | 2026-06-16 |
| Deep Infra deepinfra | zai-org/GLM-5.2 | $0.930 | $3.00 | 1.05M | 2026-06-13 |
| Hugging Face huggingface | zai-org/GLM-5.2 | $1.40 | $4.40 | 262K | 2026-06-13 |
| Weights & Biases wandb | zai-org/GLM-5.2 | $0.760 | $2.42 | 262K | 2026-06-16 |
| CrossModel crossmodel | z-ai/glm-5.2 | $1.20 | $4.40 | 1M | 2026-06-13 |
| OpenCode Go opencode-go | glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Baseten baseten | zai-org/GLM-5.2 | $1.40 | $4.40 | 524K | 2026-06-13 |
| Nvidia nvidia | z-ai/glm-5.2 | Unknown | Unknown | 1M | 2026-06-13 |
| Nebius Token Factory nebius | zai-org/GLM-5.2 | $1.40 | $4.40 | 432K | 2026-06-13 |
| Vivgrid vivgrid | glm-5.2 | $1.20 | $4.20 | 1M | 2026-06-13 |
| Lilac lilac | zai-org/glm-5.2 | $0.900 | $3.00 | 524K | 2026-06-13 |
| CrofAI crof | glm-5.2 | $0.500 | $2.20 | 1M | 2026-06-13 |
| LLM Gateway llmgateway | glm-5.2 | $0.800 | $2.55 | 1.05M | 2026-06-13 |
| Kenari kenari | glm-5-2 | Unknown | Unknown | 1M | 2026-06-13 |
| Friendli friendli | zai-org/GLM-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| OpenCode Zen opencode | glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Cloudflare Workers AI cloudflare-workers-ai | @cf/zai-org/glm-5.2 | $1.40 | $4.40 | 262K | 2026-06-13 |
| Ambient ambient | zai-org/GLM-5.2-FP8 | $1.20 | $4.20 | 203K | 2026-06-13 |
| Ambient ambient | z-ai/glm-5.2 | $1.05 | $4.40 | 101K | 2026-06-13 |
| DInference dinference | glm-5.2 | $1.25 | $3.89 | 1M | 2026-06-13 |
| UnoRouter unorouter | glm-5.2 | $1.60 | $5.03 | 1M | 2026-06-13 |
| ClinePass cline-pass | cline-pass/glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| ai& aiand | zai-org/glm-5.2 | $1.00 | $4.00 | 1.05M | 2026-06-13 |
| Pioneer pioneer | zai-org/GLM-5.2 | $1.40 | $4.40 | 1.05M | 2026-06-13 |
| SiliconFlow siliconflow | zai-org/GLM-5.2 | $1.40 | $4.40 | 1.05M | 2026-06-13 |
| ZenMux zenmux | z-ai/glm-5.2 | $1.40 | $4.50 | 1M | 2026-06-13 |
| evroc evroc | zai-org/GLM-5.2 | $1.44 | $5.75 | 1.05M | 2026-06-13 |
| Abacus abacus | zai-org/GLM-5.2 | $1.40 | $4.40 | 1.05M | 2026-06-13 |
| Inceptron inceptron | zai-org/GLM-5.2 | $1.20 | $4.20 | 1M | 2026-06-13 |
| EmpirioLabs AI empiriolabs | glm-5-2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Alibaba Token Plan alibaba-token-plan | glm-5.2 | Unknown | Unknown | 1M | 2026-06-13 |
| Wafer wafer.ai | GLM-5.2 | $1.20 | $4.10 | 1.05M | 2026-06-13 |
| Venice AI venice | zai-org-glm-5-2 | $1.40 | $4.40 | 1M | 2026-06-16 |
| Scaleway scaleway | glm-5.2 | $1.80 | $5.50 | 256K | 2026-06-13 |
| DigitalOcean digitalocean | glm-5.2 | $1.05 | $4.40 | 1M | 2026-06-13 |
| Model Oracle AI model-oracle-ai | glm-5.2 | Unknown | Unknown | 1M | 2026-06-13 |
| Berget.AI berget | zai-org/GLM-5.2 | $1.54 | $4.84 | 524K | 2026-06-13 |
| Vultr vultr | zai-org/GLM-5.2-FP8 | $0.850 | $3.10 | 393K | 2026-06-13 |
| Neuralwatt neuralwatt | glm-5.2 | $1.45 | $4.50 | 1.05M | 2026-06-17 |
| AIHubMix aihubmix | glm-5.2 | $1.13 | $3.94 | 1M | 2026-06-13 |
| Ofox ofox | z-ai/glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| routing.run routing-run | glm-5.2 | $0.800 | $2.40 | 200K | 2026-06-13 |
| Synthetic synthetic | hf:zai-org/GLM-5.2 | $1.40 | $4.40 | 524K | 2026-06-13 |
| GMI Cloud gmicloud | zai-org/GLM-5.2-FP8 | $0.979 | $3.08 | 1M | 2026-06-13 |
| Merge Gateway merge-gateway | zai/glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Subconscious subconscious | subconscious/glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-13 |
| Charm Hyper hyper | glm-5.2 | $1.40 | $4.40 | 1M | 2026-06-30 |
| Alibaba (China) alibaba-cn | glm-5.2 | $1.10 | $3.85 | 1M | 2026-06-13 |
| NovitaAI novita-ai | zai-org/glm-5.2 | $1.40 | $4.40 | 1.05M | 2026-06-13 |
| SiliconFlow (China) siliconflow-cn | zai-org/GLM-5.2 | $1.40 | $4.40 | 1.05M | 2026-06-13 |
| Tinfoil tinfoil | glm-5-2 | $1.50 | $5.25 | 384K | 2026-06-13 |
| Cloudflare AI Gateway cloudflare-ai-gateway | workers-ai/@cf/zai-org/glm-5.2 | $1.40 | $4.40 | 262K | 2026-06-13 |
| Alibaba Token Plan (China) alibaba-token-plan-cn | glm-5.2 | Unknown | Unknown | 1M | 2026-06-13 |
| Ollama Cloud ollama-cloud | glm-5.2 | Unknown | Unknown | 976K | 2026-06-13 |
| Cortecs cortecs | glm-5.2 | $1.44 | $4.53 | 1M | 2026-06-13 |
| HPC-AI hpc-ai | zai-org/glm-5.2 | $1.40 | $4.40 | 1.05M | 2026-06-13 |
Data inconsistencies across providers
- context_window varies: 1000000, 101376, 1040000, 1048560, 1048576, 1049000, 200000, 202752, 256000, 262144, 384000, 393216, 432000, 524288, 976000
- release_date varies (span 17d): 2026-06-13, 2026-06-16, 2026-06-17, 2026-06-30
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does GLM-5.2 cost?
GLM-5.2 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens, sourced from zai. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of GLM-5.2?
GLM-5.2 has a context window of 1M tokens, with a max output of 131K tokens per reply. This is the total combined size of prompt + completion.
Does GLM-5.2 support tool calling?
Yes. GLM-5.2 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does GLM-5.2 support structured output / JSON mode?
Yes. GLM-5.2 supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can GLM-5.2 accept image input?
No. GLM-5.2 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is GLM-5.2 open-weight?
Yes. GLM-5.2's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to GLM-5.2?
If GLM-5.2 doesn't fit, consider GLM-5.1, GLM-5, GLM-4.7. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Z.AI / Zhipu models
- GLM-5.1$1.40 in / $4.40 out
- GLM-5$1.00 in / $3.20 out
- GLM-4.7$0.60 in / $2.20 out
- GLM-4.6$0.60 in / $2.20 out
- GLM-4.7-Flash$0.04 in / $0.30 out
Capability lists this model is in
Last updated:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.