Context
131K
Max output
131K
Price per million tokens
$0.030in$0.030cached$0.14out
Released
Aug 2025
Waterfall
Quickstart
I want you to route my LLM calls for "gpt-oss-120b-batch" 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-120b-batch" 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.
Sampling
Tools & structure
Reasoning
Streaming
Limits
Sending an unsupported field? See error referenceOpenRouter docs
| Benchmark | Score | Source |
|---|---|---|
| MMLUvendor reported · Aug 2026 | 90.0% | vendor reported · Aug 2026 |
| MMLU-Propaper · Aug 2026 | 80.4% | paper · Aug 2026 |
| GPQA Diamondvendor reported · Aug 2026 | 80.1% | vendor reported · Aug 2026 |
| SWE-bench Verifiedvendor reported · Aug 2026 | 62.4% | vendor reported · Aug 2026 |
| LiveBenchpublic leaderboard · Aug 2026 | 46.1% | public leaderboard · Aug 2026 |
| AIME 2025vendor reported · Aug 2026 | 92.5% | vendor reported · Aug 2026 |
| AIME 2026paper · Aug 2026 | 93.2% | paper · Aug 2026 |
| Humanity's Last Examvendor reported · Aug 2026 | 14.9% | vendor reported · Aug 2026 |
| MATH-500paper · Aug 2026 | 96.0% | paper · Aug 2026 |
| IFEvalpublic leaderboard · Aug 2026 | 78.2% | public leaderboard · Aug 2026 |
| LMArena EloLMArena · Aug 2026 | 1366 | LMArena · Aug 2026 |
| Terminal-Benchpublic leaderboard · Aug 2026 | 18.7 | public leaderboard · Aug 2026 |