LLM Reference

GLM-5.3-Flash

Released
2026-08-26
Last refreshed
2026-08-26
Status
Researched 1d ago
Open sourceCommercial use: permittedMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

GLM-5.3-Flash is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1m context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
GLM-5
Released
2026-08-26
Context
1m
Max output
131,072
Parameters
320B total, 18B active
Architecture
Mixture of Experts
Specialization
coding
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Created by

Chinese AI research lab developing GLM language models.

Beijing, China
Founded 2019
Website
Pricing
Output / 1M
$0.250
Input / 1M
$0.075

Cheapest of 1 route · Z.ai · cache read $0.015

About

GLM-5.3-Flash is Z.ai's first native multimodal model in the GLM-5 series. It is a 320B-total / 18B-active Mixture-of-Experts model with a 1M-token context window and 131,072 max output tokens, supporting image, video, and file input plus function calling, tool use, structured outputs, reasoning, and prompt caching. MIT open weights are ungated on Hugging Face at zai-org/GLM-5.3-Flash. Official API model ID: glm-5.3-flash. The same model was previously tested anonymously as ox-alpha; that name is not a separate catalog slug.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
Z.ai$0.075$0.250read $0.015
Serverless

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt Caching

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Terminal-Bench 2.184.3Terminal-Bench 2.1Observed 2026-08-26Source
DeepSWE 1.163.4DeepSWE v1.1Observed 2026-08-26Source
Toolathlon78.4Toolathlon VerifiedObserved 2026-08-26Source
Humanity's Last Exam55.3HLE with toolsObserved 2026-08-26Source
Agents' Last Exam26.3Agents' Last Exam (CLI)Observed 2026-08-26Source

Migration checks

No linked migration route is available for this model yet.

API versions

glm-5.3-flash