# GLM-4.6

GLM-4.6 is a text generation model from Z.AI, available through the Impossibl API. Its published context window is 200,000 tokens. The advertised input rate is $0.60 per million input tokens. The advertised output rate is $2.20 per million output tokens.

- Model identifier: ` zai/glm-4.6 `
- Creator: Z.AI
- Model type: Text generation
- Canonical model page: [GLM-4.6](<https://impossibl.com/zai/glm-4.6>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2025-09-30

## Capabilities and limits

- Context window: 200,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text
- Outputs: text
- Tool calling: Not published

## API access

Use ` zai/glm-4.6 ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.60 | per million input tokens |
| Output | $2.20 | per million output tokens |
| Cache read | $0.11 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T11:52:20.926Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### GLM-4.6 (Non-reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/glm-4-6>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 14.93 |
| Omniscience Index | -31.68 |
| GPQA | 63.23% |
| Humanity’s Last Exam | 5.47% |
| CritPt | 0.00% |
| Terminal-Bench Hard | 28.79% |
| AA-LCR | 26.33% |
| IFBench | 36.73% |
| Tau2 | 76.90% |
| LiveCodeBench | 56.08% |
| AIME 2025 | 44.33% |
| intelligence index (API) | 14.9 |

### GLM-4.6 (Reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/glm-4-6-reasoning>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 18.53 |
| Omniscience Index | -41.88 |
| GPQA | 77.98% |
| Humanity’s Last Exam | 14.46% |
| CritPt | 1.14% |
| Terminal-Bench v2.1 | 49.44% |
| Terminal-Bench Hard | 25.00% |
| AA-LCR | 54.00% |
| GDPval Elo | 873.80 |
| IFBench | 43.40% |
| Tau2 | 70.47% |
| Tau Banking | 13.40% |
| LiveCodeBench | 69.52% |
| AIME 2025 | 86.00% |
| coding index (API) | 45.8 |
| intelligence index (API) | 18.5 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/zai/glm-4.6/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is GLM-4.6?

GLM-4.6 is a text-generation model from Z.AI, available through the Impossibl API.

### How much does GLM-4.6 cost?

GLM-4.6 costs $0.60 per million input tokens and $2.20 per million output tokens through the Impossibl API. Cache reads cost $0.11 per million tokens. All rates are in USD.

### What is the context length of GLM-4.6?

GLM-4.6 has a 200,000-token context window through the Impossibl API.

### What inputs and outputs does GLM-4.6 support?

GLM-4.6 accepts text as input. GLM-4.6 returns text.

### How do I use GLM-4.6 through an API?

GLM-4.6 is available through the Impossibl API. Use zai/glm-4.6 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was GLM-4.6 released?

Z.AI released GLM-4.6 on September 30, 2025.

Sources: [Creator release announcement](<https://docs.z.ai/release-notes/new-released>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [GLM-4.6: model details and pricing](<https://impossibl.com/zai/glm-4.6>)
- [Model directory](<https://impossibl.com/models>)