Pass IndexThe State of AISign in

glm-5.2-fast

GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance performance on long-horizon tasks.

text → text · no single maker — the market carries it

$2.1$6.6per Mtok in / out
Baseten · 4 sellers

Sold by 4 ways

SellerLaneRate
Baseten aggregatorstandard$2.1per Mtok in$6.6per Mtok out$0.21per Mtok cachedmodels.dev · read 2026-09-16
Fireworks AI aggregatorstandard$2.1per Mtok in$6.6per Mtok out$0.21per Mtok cachedmodels.dev · read 2026-09-16
Requesty aggregatorfireworks$2.1per Mtok in$6.6per Mtok out$0.21per Mtok cachedrouter.requesty.ai · read 2026-08-28
Inference.net aggregatorstandard$2.6per Mtok in$8.8per Mtok out$0.4per Mtok cachedapi.inference.net · read 2026-09-16

About

glm-5.2-fast — a text model, sold by 4 companies from $2.1 in and $6.6 out per million tokens.

It takes text and returns text, with a context window of 1,000,000 tokens. It was published in June 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Four companies sell it. The cheapest is $2.1 in and $6.6 out per million tokens at Baseten. Beside the standard rate there is a separately routed lane.

Every current figure

Register
model
Takes
text
Returns
text
Context
1,000,000 tokens
Published
June 2026
Sellers
4
Price
$2.1 in and $6.6 out per million tokens — Baseten

Known as 1 name

fireworks/glm-5.2-fast