# GLM 5.2 API

Zhipu's GLM 5.2, through an OpenAI-compatible API. 3 providers quote it now, and each request goes to the offer with the lowest estimated charge that meets your rules.

- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send glm-5.2 as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

## Facts

- Model name: glm-5.2
- Maker: Zhipu
- Context window: 229.4K · 1M tokens
- Input price: $0.155 to $1.400 per million tokens
- Output price: $0.035 to $4.400 per million tokens
- Providers: 3 independent providers
- Regions: asia, global, us

## Providers

- [engy](https://liquidinference.ai/providers/dfb60c1c-bf13-4aed-aedf-d80cc249ba87.md): asia, $0.155 input and $0.035 output per million tokens, $0.100 cache read per million tokens, 229.4K tokens of context
- [EmpirioLabs AI](https://liquidinference.ai/providers/4f49f07c-0d26-44bd-88a8-34f3f5fbd3b7.md): global, $1.400 input and $4.400 output per million tokens, $1.400 cache read per million tokens, 1M tokens of context
- [Pera](https://liquidinference.ai/providers/f651491e-f85b-4f03-b80c-32876aeb80ce.md): us, $0.563 input and $1.800 output per million tokens, $0.563 cache read per million tokens, $0.02 fee for each request, 1M tokens of context

## Scores

- HLE: 41.1, #40 of 273
- GPQA: 89.5, #50 of 250
- AA-LCR: 78.3, #65 of 237
- SciCode: 51.2, #48 of 123
- Terminal-Bench Hard: 50.8, #11 of 166
- τ²-Bench: 99.1, #1 of 169
- IFBench: 73.3, #26 of 178
- SimpleQA Verified: 34.2, #62 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

## Request

```sh
curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2",
    "messages": [{"role":"user","content":"Say hello."}]
  }'
```

## Questions

### What is GLM 5.2?

Served by intent-router: each job goes to the cheapest healthy upstream for this model.

### How much does GLM 5.2 cost?

Offers now ask $0.155 to $1.400 per million input tokens and $0.035 to $4.400 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.

### What is the context length of GLM 5.2?

The largest offer takes 1,048,576 input tokens. One job can generate up to 131,072 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can GLM 5.2 do?

Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.

### What inputs and outputs does GLM 5.2 support?

Text → Text.

### Which providers serve GLM 5.2?

3 independent providers quote it now, with 3 offers. The table above ranks them by the cost of a typical job.

### How do I call GLM 5.2?

Send "glm-5.2" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was GLM 5.2 listed?

The exchange first listed it on 10/8/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/glm-5.2)
- [GLM 5.3](https://liquidinference.ai/models/glm-5.3.md)
- [GLM 5.3 Flash](https://liquidinference.ai/models/glm-5.3-flash.md)
- [Autoglm: Phone 9B Multilingual](https://liquidinference.ai/models/autoglm-phone-9b-multilingual.md)
- [GLM 5.3 Flash Uncensored](https://liquidinference.ai/models/glm-5.3-flash-uncensored.md)
- [GLM 4.7 Flash:thinking](https://liquidinference.ai/models/glm-4.7-flash%3Athinking.md)
- [GLM 4 6v Flashx](https://liquidinference.ai/models/glm-4-6v-flashx.md)
- [Set up a client](https://liquidinference.ai/connect/glm-5.2)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)