Patchwire

Z.ai · Released Sep 30, 2025

GLM 4.6

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...

ReasoningOpen weights
Compare in showdown → OpenRouter ↗ All Z.ai models
Released
Sep 30 2025
Context window
205K 131K out
Input / 1M tokens
$0.55 from $0.40
Output / 1M tokens
$2.20 from $1.60

Where to run it

4 providers compared

Cheapest: DeepInfra at $0.40 / $1.60 per 1M input / output tokens — 30% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
DeepInfraFP4 $0.40 $1.60 $0.08203K131K— Cheapest
VeniceFP4 $0.43 $1.75 $0.08198K16K96.6%24h +9%
DeepInfraFP4 $0.50 $2.00 $0.10203K131K99.7%24h +25%
NovitaBF16 $0.55 $2.20 $0.11205K131K100%24h +38%
Z.AIFP4 $0.60 $2.20 $0.11203K131K100%24h +43%

Value

Price vs. performance

12 models score higher for the same price or lesson Terminal-Bench, e.g. Gemini 3 Flash Preview.
3.4%30.5%57.6%84.7% $0.01$0.10$1.00$10.00$100.00 Qwen3.6 35B A3B (Qwen) — 24.6% · $0.10/1M in GPT-5.5 (OpenAI) — 84.7% · $5.00/1M in Claude Opus 4.7 (Anthropic) — 80.2% · $5.00/1M in Grok 4.20 (xAI) — 57.3% · $1.25/1M in MiniMax M2.7 (MiniMax) — 45.1% · $0.30/1M in Qwen3.5-9B (Qwen) — 9.2% · $0.10/1M in GPT-5.4 (OpenAI) — 81.8% · $2.50/1M in GPT-5.3-Codex (OpenAI) — 78.4% · $1.75/1M in Gemini 3.1 Pro Preview (Google) — 80.2% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 53.4% · $3.00/1M in MiniMax M2.5 (MiniMax) — 42.7% · $0.27/1M in Claude Opus 4.6 (Anthropic) — 79.8% · $5.00/1M in Kimi K2.5 (Moonshot AI) — 43.2% · $0.50/1M in GPT-5.2-Codex (OpenAI) — 66.5% · $1.75/1M in MiniMax M2.1 (MiniMax) — 36.6% · $0.30/1M in Gemini 3 Flash Preview (Google) — 64.3% · $0.50/1M in GPT-5.2 (OpenAI) — 64.9% · $1.75/1M in GPT-5.1-Codex-Max (OpenAI) — 60.5% · $1.25/1M in DeepSeek V3.2 (DeepSeek) — 39.6% · $0.28/1M in Claude Opus 4.5 (Anthropic) — 63.1% · $5.00/1M in GPT-5.1 (OpenAI) — 47.6% · $1.25/1M in GPT-5.1-Codex (OpenAI) — 57.8% · $1.25/1M in GPT-5.1-Codex-Mini (OpenAI) — 61.6% · $0.25/1M in Kimi K2 Thinking (Moonshot AI) — 35.7% · $0.60/1M in MiniMax M2 (MiniMax) — 30.0% · $0.26/1M in Claude Haiku 4.5 (Anthropic) — 35.5% · $1.00/1M in Claude Sonnet 4.5 (Anthropic) — 46.5% · $3.00/1M in DeepSeek V3.2 Exp (DeepSeek) — 39.6% · $0.27/1M in GPT-5 (OpenAI) — 49.6% · $1.25/1M in GPT-5 Mini (OpenAI) — 34.8% · $0.25/1M in GPT-5 Nano (OpenAI) — 21.8% · $0.05/1M in gpt-oss-120b (OpenAI) — 18.7% · $0.15/1M in gpt-oss-20b (OpenAI) — 3.4% · $0.018/1M in Claude Opus 4.1 (Anthropic) — 38.0% · $15.00/1M in Gemini 2.5 Flash (Google) — 17.1% · $0.30/1M in Gemini 2.5 Pro (Google) — 32.6% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 32.6% · $1.25/1M in GLM 5 (Z.ai) — 52.4% · $0.60/1M in GLM 4.7 (Z.ai) — 33.4% · $0.54/1M in GLM 4.6 (Z.ai) — 24.5% · $0.55/1M in GLM 4.6

GLM 4.6 Other Z.ai Other labs Value frontier · Terminal-Bench vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

4 benchmark scores

BenchmarkScoreRankLeader
Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) 24.5% #35of 40 GPT-5.584.7%
SciCodeSoftware engineering · Research-coding problems from the natural sciences 38.4% #80of 93 Claude Opus 5.566.9%
WebDev ArenaDesign & visual · People vote on which model builds the better website (Elo) 1341 #77of 88 Claude Opus 5.51820
CritPtReasoning & knowledge · Open-ended, research-level physics problems 1.1% #75of 96 GPT-5.6 Sol32.3%

Specs

Details

Model ID
z-ai/glm-4.6
Developer
Z.ai
Release date
Sep 30, 2025 ·
Context window
204,800 tokens
Max output
131,072 tokens
API price
$0.55 / $2.20 per 1M input / output tokens
Providers
4
Input types
text
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.