List price
Input / 1M$0.15Output / 1M$0.60Cache read / 1M$0.075Blended$0.488Value index—Last move-18.8% from 2025-08-11
models.dev · MIT · retrieved Oct 23, 2026
Groq
GPT OSS 120B
GPT OSS 120B is listed by Groq at $0.15 input and $0.6 output per million tokens. The recorded context window is 131,072 tokens. Release date on file: 2025-08-05. LMArena's text board published 2026-10-20 gives it an overall rating of 1365.6 (rank 193, 30,213 votes). Price source: models.dev (MIT).
- Context12
- Inverse price100
- Arena59
- GPQA—
- Tools100
- Modalities33
Price history
Input and output list price. A missing day stays a gap in the line. The series is not a quality history.
Benchmarks
LMArena is CC-BY-4.0. Epoch scores, including LiveBench where Epoch publishes it, are CC-BY-4.0. A blank cell means this snapshot has no match. Nothing here is estimated.
| Benchmark | Score | Detail | Source |
|---|---|---|---|
| LMArena overall | 1365.6 | rank 193 · 30,213 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| LMArena coding | 1379.3 | rank 193 · 6,410 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| LMArena math | 1388.7 | rank 179 · 1,781 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| GPQA Diamond | — | — | — |
| LiveBench | — | — | — |
| SWE-bench Verified | — | — | — |
| Epoch Capability Index | 139.79 | 135.57–142.12 | Epoch AI Capabilities & benchmarking · CC-BY-4.0 |
Provider prices
The list row is the price used for the value index. Other rows are the same model id on models.dev, plus the LiteLLM catalog price when we have one. A split quote is kept beside the list price.
| Quote | Provider | Input / 1M | Output / 1M | Blended | Source |
|---|---|---|---|---|---|
| List | Groq | $0.15 | $0.60 | $0.487 | models.dev · MIT |
| Also listed | Regolo AI | $1.12 | $4.71 | $3.813 | models.dev · MIT |
| Also listed | Thinking Machines | $0.33 | $0.84 | $0.713 | models.dev · MIT |
| Also listed | Thinking Machines | $0.33 | $0.84 | $0.713 | models.dev · MIT |
| LiteLLM | groq | $0.15 | $0.60 | $0.487 | LiteLLM model_prices_and_context_window.json · MIT |
Spec
Context131,072Max output65,536InputtextOutputtextReleased2025-08-05Open weightsYes
Spec fields are from the models.dev row for Groq.