LLM Reference

GLM-5

Released
2026-02-11
Last refreshed
2026-06-30
Status
Researched 20d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use

GLM-5 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 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
GLM-5
Released
2026-02-11
Context
200k
Max output
128,000
Parameters
744B total, 40B active
Architecture
Mixture of Experts
Knowledge cutoff
2025-11
Specialization
general
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Training
Fine-tuned
Created by

Chinese AI research lab developing GLM language models.

Beijing, China
Founded 2019
Website
Pricing
Output / 1M
$2.08
Input / 1M
$0.600

Cheapest of 7 routes · OpenRouter

About

Flagship open-weight foundation model from Zhipu AI with 744B parameters (40B active per token) in Mixture of Experts architecture. Trained on 28.5T tokens using DeepSeek Sparse Attention on Huawei Ascend hardware. Achieves state-of-the-art performance on coding and agentic benchmarks (SWE-bench Verified: 77.8%). Supports autonomous planning, multi-step tool use, and self-correction.

GLM-5 is an open-source model. The structured metadata tracks a 200k-token context window, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through Fireworks AI, OpenRouter, Together AI, and 4 more, with the cheapest tracked route listed at $0.6 input and $2.08 output per 1M tokens. Headline tracked benchmarks include SWE-bench Pro 55.1, SWE-bench Verified 77.8, and τ-bench 82.1.

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

Coding

Q/$ C

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ C

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 7

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
OpenRouter$0.600$2.08
Serverless
Fireworks AI$1.00$3.20
Serverless
GCP Vertex AI$1.00$3.20
Serverless
Novita AI$1.00$3.20
Serverless

Available via routers & gateways(14)

Capabilities

ReasoningFunction CallingTool UseStructured OutputsPrompt Caching

Benchmark peer barsfor Coding

Benchmark scores(9)

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
SWE-bench Pro55.1Observed 2026-03-01Source
SWE-bench Verified77.8SWE-bench VerifiedObserved 2026-04-24Source
τ-bench82.1τ-benchObserved 2026-04-24Source
SWE-rebench62.8pass@1 (best of 5 runs)Observed 2026-05-28Source
AIME 202592.7AIME 2026 (accuracy)Observed 2026-06-07Source
Google-Proof Q&A86.0GPQA Diamond (accuracy)Observed 2026-06-07Source
Humanity's Last Exam30.5HLE text-only (accuracy)Observed 2026-06-07Source
LiveCodeBench81.9LiveCodeBench v6 (accuracy)Observed 2026-06-07Source
MMLU PRO86.0From model card / Apex Agents listing (accuracy)Observed 2026-06-07Source

Migration checks

No linked migration route is available for this model yet.

Compare GLM-5 with other models

Show all 44 popular comparisonssorted by 7-day search impressions

Frequently asked questions

What is the context window of GLM-5?

GLM-5 has a context window of 200k tokens.

What is the max output of GLM-5?

GLM-5 can generate up to 128,000 output tokens.

How much does GLM-5 cost?

GLM-5 pricing ranges from $0.6/1M to $1/1M input tokens depending on the provider.

When was GLM-5 released?

GLM-5 was released on 2026-02-11.

Which providers offer GLM-5?

GLM-5 is available from 7 providers: Fireworks AI, OpenRouter, Together AI, GCP Vertex AI, NVIDIA NIM, Vercel AI Gateway, Novita AI.

What benchmarks has GLM-5 been tested on?

GLM-5 has been evaluated on 9 benchmarks, including SWE-bench Pro, SWE-bench Verified, τ-bench, SWE-rebench, AIME 2025.