List price
Input / 1M$0.00Output / 1M$0.00Cache read / 1M—Blended$0.000Value index—Last move+0.5% from 2026-10-18
models.dev · MIT · retrieved Oct 24, 2026
Nvidia
GPT OSS 20B
GPT OSS 20B is listed by Nvidia at $0 input and $0 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 1287.6 (rank 261, 10,417 votes). Price source: models.dev (MIT).
- Context12
- Inverse price—
- Arena40
- GPQA38
- 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 | 1287.6 | rank 261 · 10,417 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| LMArena coding | 1306.5 | rank 255 · 2,112 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| LMArena math | 1316.9 | rank 227 · 678 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| GPQA Diamond | 46.0% | — | Epoch AI Capabilities & benchmarking · CC-BY-4.0 |
| LiveBench | — | — | — |
| SWE-bench Verified | — | — | — |
| Epoch Capability Index | 137.70 | 132.2–139.58 | 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 | Nvidia | $0.00 | $0.00 | $0.000 | models.dev · MIT |
| Also listed | Regolo AI | $0.11 | $0.47 | $0.381 | models.dev · MIT |
| Also listed | Thinking Machines | $0.18 | $0.45 | $0.383 | models.dev · MIT |
| Also listed | Merge Gateway | $0.040 | $0.15 | $0.122 | models.dev · MIT |
| LiteLLM | groq | $0.075 | $0.30 | $0.244 | LiteLLM model_prices_and_context_window.json · MIT |
Spec
Context131,072Max output32,768InputtextOutputtextReleased2025-08-05Open weightsYes
Spec fields are from the models.dev row for Nvidia.