# GLM 5.1 vs GLM 5.2

As of November 12, 2026, GLM 5.1 and GLM 5.2 cost the same: $1.40 per 1M input tokens and $4.40 per 1M output tokens. GLM 5.2 has the larger context window: 1M tokens versus 200K.

- Page: https://models.litellm.ai/compare/glm-5.1-vs-glm-5.2
- GLM 5.1: https://models.litellm.ai/models/glm-5.1
- GLM 5.2: https://models.litellm.ai/models/glm-5.2

## Side by side

| | GLM 5.1 | GLM 5.2 |
|---|---|---|
| Input, per 1M tokens | $1.40 | $1.40 |
| Output, per 1M tokens | $4.40 | $4.40 |
| Cache read, per 1M tokens | $0.26 | $0.26 |
| Cache write, per 1M tokens | $0 | $0 |
| Context window | 200,000 tokens | 1,000,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | – | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 14 | 27 |
| Price shown is from | Z.ai | Z.ai |
| Added to LiteLLM | May 2026 | June 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- GLM 5.1: EmpirioLabs AI at $0.825 input per 1M tokens (`empiriolabs/glm-5-1`)
- GLM 5.2: CLF AI Gateway at $0.56 input per 1M tokens (`clf_ai_gateway/glm-5.2`)

## Benchmark scores

| Benchmark | GLM 5.1 | GLM 5.2 |
|---|---|---|
| APEX-Agents (Coding and agents) | 40.9% | 45.2% |
| GPQA Diamond (Reasoning and knowledge) | 89.9% | 91.9% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 34.0% | 34.2% (max) |
| FrontierMath (tiers 1-3) (Math) | 36.8% | 59.2% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 93.3% | 86.4% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of August 29, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- GLM 5.2: Larger context window: 1,000,000 vs 200,000 tokens.

## FAQ

### Which is cheaper, GLM 5.1 or GLM 5.2?

They cost the same: $1.40 per 1M input tokens and $4.40 per 1M output tokens, as of November 12, 2026.

### Which has the larger context window, GLM 5.1 or GLM 5.2?

GLM 5.2 has the larger context window: 1,000,000 tokens, versus 200,000 for GLM 5.1.

### Can I switch from GLM 5.1 to GLM 5.2 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "zai/glm-5.1" to "zai/glm-5.2", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.