Standard Compute
← All models

GLM 4.7

Balanced

The refinement of GLM 4.6 — slightly stronger coding at the same friendly price.

Z.AI
Maker
82/100
Overall
76
Value score
$0.81
Blended /1M
205K
Context
Open
Weights
Pricing: $0.40 in · $1.75 out / 1M tokens · synced from OpenRouter · updated 2026-08-02

Scorecard

Output Quality8.0/10 · 73% community
Agentic Ability8.2/10 · 73% community
Speed8.0/10 · 72% community
Value for $8.9/10 · 77% community
Reliability8.6/10 · 75% community

GLM 4.7 iterates on the wildly popular 4.6 with modest quality gains while keeping the price and 202K context. A safe upgrade path for setups already standardized on GLM for coding.

Strengths
  • Improved coding over 4.6
  • Open weights
  • Great value
Trade-offs
  • Incremental over 4.6
  • 202K context

Agents that run GLM 4.7 well

GLM users wanting a small step up from 4.6.

Best model for ClineBest model for AiderBest model for Kilo CodeBest model for OpenCodeBest model for OpenClaw

GLM 4.7 FAQ

Is GLM 4.7 good for AI agents?
GLM users wanting a small step up from 4.6. On our editorial scoring it rates 8.2/10 for agentic ability and 8.0/10 for output quality. Improved coding over 4.6.
How much does GLM 4.7 cost?
Via OpenRouter, GLM 4.7 is priced at $0.40 in · $1.75 out / 1M tokens — a blended rate of about $0.81 per 1M tokens for typical input-heavy agent use.
What is GLM 4.7's context window?
GLM 4.7 has a 205K-token context window. Z.AI is the maker.
Is GLM 4.7 open source?
Yes — GLM 4.7 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 4.7?
The main trade-offs: incremental over 4.6; 202k context. It's strongest for glm users wanting a small step up from 4.6.

GLM 4.7 compared

GLM 4.7 vs Sonnet 4.6GLM 4.7 vs TerraGLM 4.7 vs GPT-5.4GLM 4.7 vs Gemini 3.5 FlashGLM 4.7 vs GPT-5.3-CodexGLM 4.7 vs Kimi K2.7 CodeGLM 4.7 vs MiniMax M3GLM 4.7 vs Qwen3.7 Plus

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 →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Fable 5 · GPT-5.6 Sol

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. No usage limits. One flat bill.

Free trial · no card · plans from $39/mo

Free trial No credit card needed Billing by Stripe2,500+ agent users