Pass IndexThe State of AISign in

GLM-4.6

As the latest iteration in the GLM series, GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications.

text → text · made by Z.ai

$0.6$2.2per Mtok in / out
Z.ai · 16 sellers

Sold by 24 ways

SellerLaneRate
Z.ai apistandard$0.6per Mtok in$2.2per Mtok out$0.11per Mtok cacheddocs.z.ai · read 2026-08-24
IO.NET aggregatorstandard$0.4per Mtok in$1.75per Mtok out$0.2per Mtok cached$0.8per Mtok cache writemodels.dev · read 2026-09-16
Nous Research aggregatorstandard$0.43per Mtok in$1.75per Mtok out$0.08per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
OpenRouter 6 ways$0.43per Mtok in$1.75per Mtok out$0.08per Mtok cached
OpenRouter aggregatorstandard$0.43per Mtok in$1.75per Mtok out$0.08per Mtok cachedopenrouter.ai · read 2026-09-09
OpenRouter aggregatorvenice/fp4$0.43per Mtok in$1.75per Mtok out$0.08per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatordeepinfra/fp4$0.5per Mtok in$2per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatornovita/bf16$0.55per Mtok in$2.2per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatoratlas-cloud/fp8$0.6per Mtok in$2.2per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-26
OpenRouter aggregatorz-ai/fp4$0.6per Mtok in$2.2per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-25
Venice AI aggregatorstandard$0.43per Mtok in$1.75per Mtok out$0.08per Mtok cachedmodels.dev · read 2026-09-16
DeepInfra aggregatorstandard$0.5per Mtok in$2per Mtok outapi.deepinfra.com · read 2026-08-25
Hugging Face Inference Providers 3 ways$0.55per Mtok in$2.2per Mtok out
Hugging Face Inference Providers aggregatordeepinfra$0.5per Mtok in$2per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatorstandard$0.55per Mtok in$2.2per Mtok outmodels.dev · read 2026-09-16
Hugging Face Inference Providers aggregatornovita$0.55per Mtok in$2.2per Mtok outrouter.huggingface.co · read 2026-08-25
Fireworks AI aggregatorstandard$0.55per Mtok in$2.19per Mtok outraw.githubusercontent.com · read 2026-09-16
Novita AI aggregatorstandard$0.55per Mtok in$2.2per Mtok out$0.11per Mtok cachedapi.novita.ai · read 2026-08-25
Baseten aggregatorstandard$0.6per Mtok in$2.2per Mtok outraw.githubusercontent.com · read 2026-09-16
ElectronHub aggregatorstandard$0.6per Mtok in$2.2per Mtok outapi.electronhub.ai · read 2026-09-16
Requesty 2 ways$0.6per Mtok in$2.2per Mtok out$0.6per Mtok cached
Requesty aggregatornovita$0.6per Mtok in$2.2per Mtok out$0.6per Mtok cachedrouter.requesty.ai · read 2026-08-28
Requesty aggregatorzai$0.6per Mtok in$2.2per Mtok out$0.11per Mtok cachedrouter.requesty.ai · read 2026-08-28
Together AI aggregatorstandard$0.6per Mtok in$2.2per Mtok outraw.githubusercontent.com · read 2026-09-16
Vercel AI Gateway aggregatorstandard$0.6per Mtok in$2.2per Mtok out$0.11per Mtok cachedai-gateway.vercel.sh · read 2026-08-25
Cerebras aggregatorstandard$2.25per Mtok in$2.75per Mtok outraw.githubusercontent.com · read 2026-09-16
PPIO aggregatorstandard$4per Mtok in$16per Mtok outapi.ppinfra.com · read 2026-09-16

Measured 27 standings

PlaceBoardMetricScore
4thof 109Berkeley Function-Calling Leaderboard (BFCL) V4Overall Acc (fc thinking)72.38
15thof 61AIME 2025Accuracy (± 95% CI)91.67
19thof 42Design Arena · godotgamedev (agents)Elo1180
21stof 25SWE-Bench Pro (Public Dataset)Resolve Rate9.67
43rdof 55Design Arena · androidnative (agents)Elo1100
47thof 72Frontiermath tier 4 — Epoch AImean_score2.128
50thof 63Design Arena · mobileapps (agents)Elo1125
52ndof 105Vectara Hallucination LeaderboardHallucination Rate9.5
57thof 64Design Arena · fullstack (agents)Elo1038
61stof 65Apex agents — Epoch AIPass@1 score0.04
76thof 101FrontierMath (Tiers 1-3)mean_score3.819
77thof 109Design Arena · svg (models)Elo1134
86thof 147Design Arena · 3d (models)Elo1157
88thof 155Design Arena · gamedev (models)Elo1174
93rdof 156Design Arena · codecategories (models)Elo1181
94thof 152Design Arena · dataviz (models)Elo1177
94thof 150Design Arena · uicomponent (models)Elo1163
94thof 162Design Arena · website (models)Elo1187
97thof 121Webdev arena — Epoch AIArena Score1340.18
100thof 112Ale bench — Epoch AIPerformance340.82
100thof 184Artificial Analysis · Coding IndexIndex45.8
100thof 128LMArena · WebDevScore (Elo)1341
112thof 177Critpt — Epoch AIAccuracy1.143
112thof 402LMArena · TextScore (Elo)1425
127thof 168Scicode — Epoch AIScore38.426
158thof 202Terminalbench — Epoch AIAccuracy mean0.245
423rdof 656Epoch capabilities index — Epoch AIECI Score140.85

About

GLM-4.6 — a text model from Z.ai, sold by 16 companies from $0.4 in and $1.75 out per million tokens, placed 4th of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.

It takes text and returns text, with a context window of 200,000 tokens. It was published in September 2025, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Sixteen companies sell it. The cheapest is $0.4 in and $1.75 out per million tokens at IO.NET. Beside the standard rate there are separately routed and regional lanes. It has been measured on 27 boards, and stands best at 4th of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.

Every current figure

Maker
Z.ai
Register
model
Takes
text
Returns
text
Context
200,000 tokens
Published
September 2025
Knowledge to
April 2025
Parameters
357 billion
Licence
not read
Sellers
16
Price
$0.4 in and $1.75 out per million tokens — IO.NET
Boards
27
Best place
4th of 109 — Berkeley Function-Calling Leaderboard (BFCL) V4

Known as 6 names

GLM 4.6GLM-4.6 (FC thinking)zai-org/GLM-4.6z-ai/glm-4.6novita/zai-org/glm-4.6zai/GLM-4.6