GLM 5.3

reasoningmit

GLM 5.3 is an open-weight mixture-of-experts reasoning and coding model with a 1M context window, hosted by Reka. It is served as an OpenAI-compatible passthrough with native tool calling, structured outputs, logprobs, and streaming.

Context
1.0M
Max output
262K
Input price
$1.17/1M tokens
Output price
$3.96/1M tokens

Capabilities

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

Details

Model IDglm5.3
Provider Reka AI
Familyglm
Licensemit
Statusactive
Typereasoning
Input modalitiestext
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window1.0M tokens
Max input—
Max output262K tokens
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.reka.ai/v1/chat/completions

Pricing

Input
$1.17
Output
$3.96
Cache write
—
Cache read
$0.23
Batch in
—
Batch out
—

Family Comparison: glm

ModelContextMax outPricing
GLM 5.3 Flash1.0M1.0M$0.15$0.5
GLM 5.31.0M262K$1.17$3.96

API

GET/v1/models/reka/glm5.3