GLM-5.1 (Reasoning)
by Zhipu AI
GLM-5.1 (Reasoning) is a reasoning model from Zhipu AI, released on April 7, 2026. It has a 203K-token context window and can generate up to 203K output tokens. API pricing is $1.05 per 1M input tokens and $3.5 per 1M output tokens.
GLM-5.1 is Z.AI's next-generation flagship foundation model designed for long-horizon agentic engineering tasks. Built on a 754B MoE architecture (40B active parameters), it can work continuously and autonomously on a single task for up to 8 hours, completing the full loop from planning and execution to iterative optimization and delivery. GLM-5.1 achieves state-of-the-art on SWE-Bench Pro (58.4) and demonstrates strong performance across coding, reasoning, and agentic benchmarks. It supports 200K context length, 128K max output tokens, thinking mode, function calling, structured output, context caching, and MCP integration. Overall performance is aligned with Claude Opus 4.6 with particular strengths in sustained execution and complex engineering optimization.
Key specs
| Provider | Zhipu AI |
|---|---|
| Release date | 2026-04-07 |
| License | open source |
| Context window | 203K tokens |
| Max output | 203K tokens |
| Input price | $1.05 / 1M tokens |
| Output price | $3.5 / 1M tokens |
| Intelligence Score | 38.9 |
| Coding index | 29.4 |
Quick answers
What is the context window of GLM-5.1 (Reasoning)?
GLM-5.1 (Reasoning) has a context window of 203K tokens, with a maximum output of 203K tokens per response.
How much does GLM-5.1 (Reasoning) cost?
GLM-5.1 (Reasoning) costs $1.05 per 1M input tokens and $3.5 per 1M output tokens through the API.
Is GLM-5.1 (Reasoning) open source?
Yes. GLM-5.1 (Reasoning) is an open model released under the open source license.
When was GLM-5.1 (Reasoning) released?
Zhipu AI released GLM-5.1 (Reasoning) on April 7, 2026.
Compare on the AI leaderboard · All AI models
More models from Zhipu AI
- GLM-5.3 (Reasoning) — Zhipu AI
- GLM-5.3-Flash (Reasoning) — Zhipu AI