GLM-5.1

mit

GLM-5.1 is Z-AI's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).

Context
203K
Max output
128K
Input price
$1.05/1M tokens
Output price
$3.5/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Prompt Caching
Fine-tuning

Details

Model IDzai-org/GLM-5.1
Provider DeepInfra
Creator Z.AI (Zhipu)
FamilyGLM-5.1
Licensemit
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window203K tokens
Max input—
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$1.05
Output
$3.5
Cache write
—
Cache read
$0.21
Batch in
—
Batch out
—

API

GET/v1/models/deepinfra/zai-org/GLM-5.1