GLM Latest
GLM Latest is a large language model made by Z.ai, added to the catalog on 19 Aug 2026. It has a context window of 1,048,576 tokens and costs $0.0699 per 1M input tokens and $1.40 per 1M output tokens. It accepts text and produces text. Typical uses: analyzing long text documents, producing structured text responses and reasoning through text-based problems.
Price checked ยท source: OpenRouter
What GLM Latest is
Z.ai: GLM Latest is a text model identifier that redirects to the latest GLM model from Z.ai. It accepts text and produces text. Because the identifier points to the latest GLM model, the specific model it represents can change over time. The catalog lists a context length of 1,048,576 tokens and a maximum output of 943,718 tokens, allowing a request to include a substantial amount of text and return a lengthy response within those limits.
The model supports reasoning, tools, structured outputs, and response formats. These options make it suitable for text tasks that benefit from working through a problem, using supported tools, or returning information in a defined structure. The facts do not specify particular tools, response formats, languages, or domain expertise, so those details depend on the current GLM model and its configuration.
Its text input and output, together with its large listed context, can suit tasks involving long documents or extended text exchanges. Examples include analyzing material provided in a prompt, producing structured text, and drafting or revising written content. The large maximum output can accommodate long responses, while the context limit defines how much information can be included in a request. Since this model identifier tracks the latest GLM model rather than naming a fixed version, users should account for the possibility that the underlying model changes.
Key features
- Accepts text and produces text
- 1,048,576-token context length
- Maximum output of 943,718 tokens
- Supports reasoning and tools
- Supports structured outputs and response formats
Typical uses
- Analyzing long text documents
- Producing structured text responses
- Reasoning through text-based problems
- Drafting and revising written content
GLM Latest pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.0699 |
| Output, per 1M tokens | $1.40 |
| Cached input read, per 1M tokens | $0.0689 |
No price change since it was added on 19 Aug 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0029 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0049 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.013 |
GLM Latest specifications
| Model id | ~z-ai/glm-latest |
|---|---|
| Version | glm-latest |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 19 Aug 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| 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 Latest yet.
Compare GLM Latest
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.