GLM 5.1
GLM 5.1 is a large language model made by Z.ai, added to the catalog on 7 Apr 2026. It has a context window of 204,800 tokens and costs $1.40 per 1M input tokens and $4.40 per 1M output tokens. It accepts text and produces text. Typical uses: extended coding assignments, long-horizon coding tasks and text-based reasoning.
Price checked ยท source: OpenRouter
What GLM 5.1 is
Z.ai: GLM 5.1 is a text-in, text-out model described for coding, with particular emphasis on long-horizon tasks. The provider description characterizes it as able to work independently and continuously, though the supplied description does not identify the particular work covered by that statement. It accepts text and returns text. Its listed capabilities include reasoning, tool support, structured outputs, and response-format support. These details describe text-based interactions with support for tool use and constrained output structures.
The model has a context length of 204,800 tokens and a maximum output of 131,072 tokens. The context figure describes how much input context it can handle, while the output limit sets the stated maximum length of a generated response. These limits are relevant to requests involving substantial input material or an extended generated result. The catalog's coding and long-horizon-task description makes extended coding assignments a reasonable area to consider, while tool support and structured output may suit workflows that need those options. Reasoning is also listed among its supported capabilities, making text-based reasoning tasks another possible fit. The facts provided do not name programming languages, specific tools, or particular response schemas, so those details should not be assumed. No image or audio input or output is listed.
Key features
- Accepts text and produces text
- Has a context length of 204,800 tokens
- Supports reasoning and tools
- Supports structured outputs and response formats
- Maximum output length is 131,072 tokens
Typical uses
- Extended coding assignments
- Long-horizon coding tasks
- Text-based reasoning
- Generating structured text responses
GLM 5.1 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.40 |
| Output, per 1M tokens | $4.40 |
| Cached input read, per 1M tokens | $0.26 |
The price last changed on 22 Nov 2026. 7 price changes have been recorded since GLM 5.1 was added.
| Date | Input /1M | Output /1M | Change |
|---|---|---|---|
| $1.40 | $4.40 | Price raised | |
| $1.19 | $3.74 | Price lowered | |
| $1.40 | $4.40 | Price raised | |
| $1.19 | $3.74 | Price lowered | |
| $1.40 | $4.40 | Price raised | |
| $1.19 | $3.74 | Price lowered | |
| $1.40 | $4.40 | Price raised | |
| $1.19 | $3.74 | Added at this price |
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0020 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.039 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.051 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.217 |
GLM 5.1 specifications
| Model id | z-ai/glm-5.1 |
|---|---|
| Version | glm-5.1-20260406 |
| Context window | 204,800 tokensAbout 153,600 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 7 Apr 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for GLM 5.1 yet.
Compare GLM 5.1
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.