GLM-4.6

GLM-4.6 is Z.AI's flagship coding model in the GLM-4 line, built for programming tasks and complex agent work.

start building →
compare models

input · usd / 1m tok

$0.60

output · usd / 1m tok

$2.20

context window

200ktokens

modalities · in → out

takes text in, gives text out

pricing

base api ratesusd per 1m tokens

input
$0.60
output
$2.20
cache read
$0.11

providers

Z.AI hosts GLM-4.6. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

  • Z.AI

specifications

takes text in, gives text outzai/glm-4.6

  • creatorZ.AI
  • model typeText generation
  • context window200,000 tokens
  • maximum outputnot published
  • input

    takes text in, gives text out

  • outputtext
  • tool callingnot verified
  • releasedsep 30, 2025
  • endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="zai/glm-4.6",
    input="",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

14.9#69 of 90 models on the gateway

  1. omniscience-31.7#70 of 86
  2. gpqa63.2%#81 of 88
  3. humanity’s last exam5.5%#77 of 89
  1. Tau276.9%
  2. GPQA63.2%
  3. LiveCodeBench56.1%
  4. AIME 202544.3%
  5. IFBench36.7%
  6. Terminal-Bench Hard28.8%
  7. AA-LCR26.3%
  8. Humanity’s Last Exam5.5%
  9. CritPt0.0%
  • Intelligence Index14.93
  • Omniscience Index-31.68
  • intelligence index (API)14.9

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-09-11.

compare GLM-4.6 with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

impossibl models --all →

frequently asked questions

What is GLM-4.6?

GLM-4.6 is Z.AI's flagship coding model in the GLM-4 line, built for programming tasks and complex agent work. Over GLM-4.5 it expands the context window, sharpens coding performance, and improves reasoning and tool use inside agent frameworks.

How much does GLM-4.6 cost?

GLM-4.6 costs $0.60 per million input tokens and $2.20 per million output tokens through the Impossibl API. Cache reads cost $0.11 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of GLM-4.6?

GLM-4.6 has a 200,000-token context window through the Impossibl API.

What inputs and outputs does GLM-4.6 support?

GLM-4.6 accepts text as input. GLM-4.6 returns text.

How do I use GLM-4.6 through an API?

GLM-4.6 is available through the Impossibl API. Use zai/glm-4.6 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was GLM-4.6 released?

Z.AI released GLM-4.6 on September 30, 2025.

this page describes GLM-4.6 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →