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

Qwen3 32b

qwen3-32bby Qwen
Try in Chat

Context

131K

Max output

131K

Price per million tokens

$0.095in$0.048cached$0.28out

Released

-

Waterfall

  1. 1
    greenference via Experiential Cloud$0.095/$0.2899.9% up--

Quickstart

I want you to route my LLM calls for "qwen3-32b" 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 "qwen3-32b" 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

Stop sequences*

Tools & structure

Parallel tool calls*

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

Sending an unsupported field?

Hugging Face
See error reference
Azure OpenAI docs
Benchmarks12
BenchmarkScoreSource
MMLUHugging Face · Aug 202681.0%Hugging Face · Aug 2026
MMLU-ProHugging Face · Aug 202679.1%Hugging Face · Aug 2026
GPQA Diamondpaper · Aug 202668.4%paper · Aug 2026
SWE-bench Verifiedpaper · Aug 202624.4%paper · Aug 2026
LiveBenchpaper · Aug 202674.9%paper · Aug 2026
AIME 2025paper · Aug 202672.9%paper · Aug 2026
AIME 2026paper · Aug 202675.8%paper · Aug 2026
Humanity's Last Exampaper · Aug 20269.3%paper · Aug 2026
MATH-500paper · Aug 202697.2%paper · Aug 2026
IFEvalpaper · Aug 202685.0%paper · Aug 2026
LMArena EloLMArena · Aug 20261340LMArena · Aug 2026
Terminal-Benchpaper · Aug 20263.4paper · Aug 2026
Providers serving this model4
Status
greenference via Experiential Cloudexperientialno datano data99.9%#1 / 1131K131K$0.095$0.28cache$0.048-no dataactiveestimated
Azure Foundryqwen3-32bno datano data99.9%-131K131K$0.61≈$2.94≈no data≈-no dataactiveestimated
Azure FoundryFW-Qwen3-32Bno datano data99.9%-131K131K$0.61≈$2.94≈no data≈-no dataactiveestimated
Fireworksno datano data99.9%-131K131K$0.61≈$2.94≈no data≈-ZDRactiveestimated