GLM-5.1 is Z.AI's flagship reasoning and agentic-engineering model released April 7, 2026, a 754B-parameter hybrid MoE (GlmMoeDSA) combining linear and standard attention with sparse MoE feed-forward layers. It offers a 200K context window and up to 128K max output, and is designed for sustained multi-hour autonomous execution via iterative experiment-analyze-optimize loops. Reported benchmarks include 58.4% on SWE-Bench Pro and 95.3% on AIME 2026, with thinking mode, function calling, structured output and MCP support. Ideal for complex reasoning, tool use and long-running agentic coding tasks.
$1.813 in · $5.698 out / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $1.81 | per 1M tokens |
| Cached input (cache hit) | $0.34 | per 1M tokens |
| Output tokens | $5.7 | per 1M tokens |
TuneRouter live platform pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "glm-5.1", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: glm-5.1 · works with OpenAI SDKs — just point base_url at api.tunerouter.com