GLM-5.2
glm-5.2
These are Mengbi Router customer prices in USD per 1M tokens. Provider: Z.AI; Context: 1M; Input price: $1.4; Output price: $4.4.
- Coding
- Agents & tools
- Cost effective
AI models and pricing
Model specs
- Provider
- Z.AI
- Context
- 1M
- Max output
- 96K
- Released
- Jun 2026
- Input modalities
- Text
- Output modalities
- Text
- Tool calling
- Supported
- Structured output
- Supported
- Currency
- USD
- Model ID
- glm-5.2
Model pricing and access details
USD / 1M tokens| Model | Official | Mengbi | Discount |
|---|---|---|---|
| Input price | $1.4 | $1.4 | |
| Output price | $4.4 | $4.4 | |
| Cache read price | $0.26 | $0.26 |
Estimated cost for common usage
Estimates based on current Mengbi Router prices, so you can plan real request costs.
| Token volume | Input | Output | Input + output total |
|---|---|---|---|
| 10K tokens | $0.014 | $0.044 | $0.058 |
| 100K tokens | $0.14 | $0.44 | $0.58 |
| 1M tokens | $1.4 | $4.4 | $5.8 |
| 10M tokens | $14 | $44 | $58 |
Estimates use the current prices above and exclude cache-hit discounts. Your invoice is metered by the actual token usage of each request.
Public benchmark scores
How GLM-5.2 scores on common public benchmarks, so you can compare capability at a glance.
| Benchmark | Score |
|---|---|
| GPQA Diamond | 81.2 |
| SWE-bench Verified | 63.1 |
| AIME 2026 | 80.4 |
Curated from vendor-published evaluations (snapshot 2026-09). For reference only; not independently tested by Mengbi.
API protocol compatibility
Keep your SDK. Change one line.
Use the protocol your stack already speaks.
const client = new OpenAI({
apiKey: process.env.MENGBI_ROUTER_KEY,
baseURL: process.env.MENGBI_ROUTER_BASE_URL,
})
const response = await client.chat.completions.create({
model: 'glm-5.2',
messages,
})Frequently asked questions
Common questions about the GLM-5.2 API: pricing, capabilities, and integration.
How much does the GLM-5.2 API cost?
Through Mengbi Router, GLM-5.2 costs $1.4 per 1M input tokens and $4.4 per 1M output tokens. Cached input is billed at $0.26 per 1M tokens.
What is the context window of GLM-5.2?
GLM-5.2 supports a 1M-token context window. A single request can generate up to about 96K output tokens.
Does GLM-5.2 support tool calling and structured output?
Yes. GLM-5.2 supports the tools parameter in chat.completions for function calling. It also supports response_format with a JSON Schema for structured output.
What input and output formats does GLM-5.2 support?
It accepts Text and returns Text.
How do I call GLM-5.2 with the OpenAI SDK?
Keep your OpenAI SDK, point the base URL at Mengbi Router, use your Mengbi API key, and set model to glm-5.2 in the request.
Which company provides GLM-5.2?
GLM-5.2 is provided by Z.AI and available through Mengbi Router with one API key and pay-as-you-go billing. The model was first released in Jun 2026.