Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocs
Sign in
Continue with GoogleContinue with GitHub
or
Models

GLM 5.2

glm-5.2by GLMZDR enforceable
Try in Chat

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Context

1.05M

Max output

131K

Price per million tokens

$1.40in$0.26cached$4.40out

Released

Jun 2026

Waterfall

  1. 1
    Qwen Cloud via Experiential Cloud$1.40/$4.4099.9% up--
  2. 2H
    Huawei Cloud via Experiential Cloud$1.40/$4.4099.9% up--
  3. 3
    Z.ai via Experiential Cloud$1.40/$4.4099.9% up--

Quickstart

I want you to route my LLM calls for "glm-5.2" through the Experiential gateway instead of calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL and key swap. Please:

1. Point the client at https://api.experientiallabs.jp/v1 as the base URL.
2. Securely ask me for my API key. Authenticate with my Experiential key from EXPLABS_API_KEY. I can create one under Settings -> API Keys.
3. Use the model id "glm-5.2" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key, leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my Experiential credits.

Tell me which files you changed.
CapabilitiesAccepts text

Sampling

Temperature0-2Top-p0-1Stop sequences*

Tools & structure

ToolsParallel tool calls*Structured output*

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

Sending an unsupported field? See error referenceAzure OpenAI docs

Benchmarks7
BenchmarkScoreSource
GPQA DiamondHugging Face · Aug 202691.2%Hugging Face · Aug 2026
SWE-bench Verifiedpublic leaderboard · Aug 202682.8%public leaderboard · Aug 2026
LiveBenchpublic leaderboard · Aug 202673.2%public leaderboard · Aug 2026
AIME 2026Hugging Face · Aug 202699.2%Hugging Face · Aug 2026
Humanity's Last ExamHugging Face · Aug 202640.5%Hugging Face · Aug 2026
LMArena EloLMArena · Aug 20261465LMArena · Aug 2026
Terminal-BenchHugging Face · Aug 202681.0Hugging Face · Aug 2026
Providers serving this model6
Status
HHuawei Cloud via Experiential Cloudexperientialno datano data99.9%#4 / 51.05M131K$1.40$4.40cache$0.26-no dataactive-
Qwen Cloud via Experiential Cloudexperientialno datano data99.9%#2 / 51.05M131K$1.40$4.40cache$0.26-no dataactive-
Vertex AI via Experiential Cloudexperientialno datano data99.9%#3 / 51.05M131K$1.40$4.40cache$0.14-no dataactive-
WWafer via Experiential Cloudexperientialno datano data99.9%#1 / 51.05M131K$1.26$3.96cache$0.23-no dataactive-
Z.ai via Experiential Cloudexperientialno datano data99.9%#5 / 51.05M131K$1.40$4.40cache$0.26Write 5m: $1.40-ZDRactive-
Azure Foundryno datano data99.9%-1.05M131K$1.54$4.84cache$0.15-no dataactiveestimated
Hugging Face