GLM 4.6
Z.ai · Open weights · Released Sep 30, 2025 · z-ai/glm-4.6
205K contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 Venice | $0.43 | $1.75 | $0.08 | 198K | fp4 | 1.2s | 12 tok/s | 3/5 | 99.9% |
 DeepInfra | $0.50 | $2.00 | $0.10 | 203K | fp4 | 0.67s | 78 tok/s | 3/5 | 99.9% |
 Novita | $0.55 | $2.20 | $0.11 | 205K | bf16 | 2.2s | 51 tok/s | 2/5 | 98.1% |
| ATAtlasCloud | $0.60 | $2.20 | $0.11 | 203K | fp8 | 2.2s | 41 tok/s | 4/5 | 79.3% |
 Z.AI1ST PARTY | $0.60 | $2.20 | $0.11 | 203K | fp4 | 0.7s | 62 tok/s | 2/5 | 97.5% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 43 hours ago
Pricing variants · USD / MTok in / out
STANDARD
$0.43 / $1.75
per MTok in / out
CACHE READ $0.08
About
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...
Specifications
Context window204,800
Max output131,072
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedSep 30, 2025
Knowledge cutoff2025-03-31
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/z-ai/glm-4.6)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks43 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.