Log in
← All models

GLM 4.6

Balanced

The breakout open-weight coding model — exceptional value that won over the agent community.

Z.AI
Maker
80/100
Overall
69
Value score
$0.82
Blended /1M
203K
Context
Open
Weights
Pricing: $0.43 in · $1.74 out / 1M tokens · synced from OpenRouter · updated 2026-06-22

Scorecard

Output Quality7.8/10 · 71% community
Agentic Ability7.9/10 · 72% community
Speed8.0/10 · 73% community
Value for $8.8/10 · 76% community
Reliability8.4/10 · 74% community

GLM 4.6 is the model that made the GLM line a staple of open coding agents: very strong coding ability for the price, open weights, and a 202K context. Even after GLM 5's release it stays popular for its value.

Strengths
  • Outstanding coding value
  • Open weights
  • Proven in agent stacks
Trade-offs
  • Smaller context than the 5.x line
  • Below frontier on the hardest tasks

Agents that run GLM 4.6 well

The value pick for open-weight coding agents.

Best model for ClineBest model for AiderBest model for Kilo CodeBest model for OpenCodeBest model for OpenClawBest model for Continue

GLM 4.6 FAQ

Is GLM 4.6 good for AI agents?
The value pick for open-weight coding agents. On our editorial scoring it rates 7.9/10 for agentic ability and 7.8/10 for output quality. Outstanding coding value.
How much does GLM 4.6 cost?
Via OpenRouter, GLM 4.6 is priced at $0.43 in · $1.74 out / 1M tokens — a blended rate of about $0.82 per 1M tokens for typical input-heavy agent use.
What is GLM 4.6's context window?
GLM 4.6 has a 203K-token context window. Z.AI is the maker.
Is GLM 4.6 open source?
Yes — GLM 4.6 ships with open weights, so you can self-host it for privacy or run it through a hosted provider like OpenRouter. That openness is a big reason it's popular in open agent stacks.
What are the downsides of GLM 4.6?
The main trade-offs: smaller context than the 5.x line; below frontier on the hardest tasks. It's strongest for the value pick for open-weight coding agents.

GLM 4.6 compared

GLM 4.6 vs Sonnet 4.6GLM 4.6 vs GPT-5.4GLM 4.6 vs Gemini 3.5 FlashGLM 4.6 vs GPT-5.3-CodexGLM 4.6 vs Kimi K2.7 CodeGLM 4.6 vs MiniMax M3GLM 4.6 vs Qwen3.7 PlusGLM 4.6 vs Devstral 2

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.

Compare AI agents →