GLM-4.7 is a state-of-the-art, multilingual Mixture-of-Experts (MoE) language model designed for complex reasoning, agentic coding, and tool use. Building on its predecessor GLM-4.6, it delivers significant improvements across key benchmarks, including multilingual SWE-bench, Terminal Bench, and reasoning-heavy evaluations like HLE. The model features advanced "Interleaved Thinking" and new "Preserved Thinking" modes, allowing it to reason before actions and maintain consistency across long, ...
function_callinghttps://api.deepinfra.com/v1/openai/v1/chat/completions| Model | Context | Max out | Pricing |
|---|---|---|---|
| GLM-4.7-Flash | 203K | 128K | $0.06$0.4 |
| GLM-4.7 | 203K | 128K | $0.4$1.75 |
/v1/models/deepinfra/zai-org/GLM-4.7GLM-4.7 is a state-of-the-art, multilingual Mixture-of-Experts (MoE) language model designed for complex reasoning, agentic coding, and tool use. Building on its predecessor GLM-4.6, it delivers significant improvements across key benchmarks, including multilingual SWE-bench, Terminal Bench, and reasoning-heavy evaluations like HLE. The model features advanced "Interleaved Thinking" and new "Preserved Thinking" modes, allowing it to reason before actions and maintain consistency across long, ...