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

GPT Oss 20b

gpt-oss-20bby OpenAI
Try in Chat

Context

131K

Max output

no data

Price per million tokens

$0.009in$0.004cached$0.045out

Released

-

Waterfall

  1. 1
    greenference via Experiential Cloud$0.009/$0.04599.9% up--

Quickstart

I want you to route my LLM calls for "gpt-oss-20b" 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 "gpt-oss-20b" 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? See error referenceAzure OpenAI docs

Benchmarks11
BenchmarkScoreSource
MMLUvendor reported · Aug 202685.3%vendor reported · Aug 2026
MMLU-Propaper · Aug 202665.6%paper · Aug 2026
GPQA Diamondvendor reported · Aug 202671.5%vendor reported · Aug 2026
SWE-bench Verifiedvendor reported · Aug 202660.7%vendor reported · Aug 2026
AIME 2025vendor reported · Aug 202691.7%vendor reported · Aug 2026
AIME 2026paper · Aug 202676.9%paper · Aug 2026
Humanity's Last Examvendor reported · Aug 202610.9%vendor reported · Aug 2026
MATH-500paper · Aug 202696.5%paper · Aug 2026
IFEvalpaper · Aug 202672.5%paper · Aug 2026
LMArena EloLMArena · Aug 20261288LMArena · Aug 2026
Terminal-Benchpublic leaderboard · Aug 20263.1public leaderboard · Aug 2026
Providers serving this model4
Status
greenference via Experiential Cloudexperientialno datano data99.9%#1 / 1131Kno data$0.009$0.045cache$0.004-no dataactiveestimated
Azure Foundrygpt-oss-20bno datano data99.9%-131Kno data$0.61≈$2.94≈no data≈-no dataactiveestimated
Azure FoundryFW-GPT-OSS-20Bno datano data99.9%-131Kno data$0.61≈$2.94≈no data≈-no dataactiveestimated
Fireworksno datano data99.9%-131Kno data$0.61≈$2.94≈no data≈-ZDRactiveestimated
Hugging Face