GLM 4.6
GLM 4.6 is Z.AI's coding-focused model released September 30, 2025, with enhanced performance on both benchmarks and real-world programming tasks. It features an expanded context window of 204.8K tokens for handling large codebases and complex agent workflows.
import { streamText } from 'ai'
const result = streamText({ model: 'zai/glm-4.6', prompt: 'Why is the sky blue?'})Playground
Try out GLM 4.6 by Z.AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
GLM 4.6
GLM 4.6
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Z.AI
| Model |
|---|
| 1M | 1.2s | 209tps | $2.10/M | $6.60/M | Read:$0.21/M Write:— | — |   | 06/23/2026 | ||||
| 1M | 0.3s | 411tps | $1.40/M$0.90/M | $4.40/M$2.84/M | Read:$0.26/M$0.17/M Write:— | — |    +11 | 06/16/2026 | ||||
| 205K | 0.4s | 133tps | $1.30/M | $4.30/M | Read:$0.26/M Write:— | — |  +3 | 04/07/2026 | ||||
| 203K | 0.2s | 159tps | $0.80/M | $2.56/M | Read:$0.16/M Write:— | — |  +3 | 02/12/2026 | ||||
| 205K | 0.1s | 850tps | $2.25/M | $2.75/M | Read:$2.25/M Write:— | — |  +3 | 12/22/2025 | ||||
| 128K | 3.1s | 67tps | $0.20/M | $1.10/M | Read:$0.03/M Write:— | — | | 07/28/2025 |
About GLM 4.6
GLM 4.6 was released September 30, 2025 as Z.AI's dedicated coding model. It builds on the GLM-4.5 foundation with targeted improvements for software engineering workflows, benchmark performance, and real-world programming tasks.
The key architectural change is an expanded context window of 204.8K tokens. You can process entire codebases, long specification documents, and multi-file analysis in a single request. This benefits code generation tasks that require understanding cross-file relationships, and agentic coding workflows that maintain state across extended interactions.
GLM 4.6 shows enhanced performance on both public benchmarks and real-world programming tasks. Benchmark scores predict capability, but real-world coding involves ambiguous requirements, legacy code patterns, and iterative refinement. GLM 4.6 targets both dimensions.
What To Consider When Choosing a Provider
- Configuration: The context window of 204.8K tokens handles large codebases in a single pass. Structure your prompts to include relevant file context rather than relying on the model to infer missing dependencies.
- Configuration: GLM 4.6 is optimized for code generation and understanding. For general reasoning or conversational tasks, GLM-4.5 may provide a more balanced profile.
- Configuration: Coding tasks with large context inputs consume many tokens. Monitor usage through AI Gateway's built-in observability to track actual costs against estimates.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use GLM 4.6
Best for
- Software engineering workflows: Code generation, debugging, refactoring, and code review across large repositories
- Agentic coding tasks: Extended context and multi-step planning improve the quality of generated solutions
- Large codebase analysis: The context window of 204.8K tokens fits cross-file dependencies and architectural patterns
- Code migration and modernization: Understanding legacy patterns and generating updated code requires broad context
- Technical documentation generation: Codebases where the model must read and synthesize large amounts of source code
Consider alternatives when
- General-purpose workloads: GLM-4.5 provides broader capability without the coding specialization for reasoning or conversation
- Vision-enabled coding: GLM-4.6V combines vision input with coding capability for code-from-screenshot workflows
- Faster inference priority: GLM-4.6V-Flash offers vision and coding at reduced latency when speed matters more than depth
- Advanced coding improvements: GLM-4.7 includes further advancements in tool usage and multi-step reasoning for complex agentic tasks
Conclusion
GLM 4.6 targets the coding workload specifically, combining an expanded context window of 204.8K tokens with improvements in both benchmark and real-world programming performance. For teams building coding assistants, automated code review pipelines, or agentic development tools, it provides a focused alternative to general-purpose models.