Open GPT reasoning model for self-hosted agents and controllable deployments
GPT OSS 20B by openai is offered by 48 providers on this page. Public prices are shown for 42 of them. Its reference price is $0.40 per 1M input tokens and $1.80 per 1M output tokens. The lowest paid channel is Kilo Gateway at $0.018 / $0.09 per 1M, about 22× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 5 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 10 on the Intelligence Index. Against its lowest blended price of $0.036 per 1M, that is roughly 278 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 263 tokens per second, with 0.95s to the first token.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 32,768 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-06.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | Cloud | Free | — | — | 131,072 ⚠ | 32,768 | ||
| LMStudio | Cloud | Free | — | — | 131,072 ⚠ | 32,768 | ||
| Kenari | Gateway | Free | — | — | 131,072 ⚠ | 32,768 | ||
| QVAC | Gateway | Free | — | — | 131,072 ⚠ | 32,768 | ||
| Eden AI | Gateway | Free | — | — | 32,768 ⚠ | 32,768 | ||
| Kilo Gateway | Gateway | $0.018 | $0.09 | $0.009 | — | 131,072 ⚠ | 32,768 | |
| OpenRouter | Gateway | $0.018 | $0.09 | $0.009 | — | 131,072 ⚠ | 32,768 | |
| Eden AI | Gateway | $0.02 | $0.10 | $0.003 | — | 131,072 ⚠ | 32,768 | |
| CoreWeave | Cloud | $0.03 | $0.13 | $0.03 | — | 131,072 ⚠ | 131,072 | |
| Deep Infra | Cloud | $0.03 | $0.14 | — | — | 131,072 ⚠ | 16,384 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 3 of 48 providers.
6 / 48 providers expose no reasoning control (reasoning_options: []).
5 more channels offer $0 (Nvidia, LMStudio, Kenari etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.