Open GPT reasoning model for self-hosted agents and controllable deployments
GPT OSS 120B by openai is offered by 84 providers on this page. Public prices are shown for 80 of them. Its reference price is $2.92 per 1M tokens. The lowest paid channel is DevPass (LLM Gateway) at $0.032 / $0.14 per 1M, about 97× 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 3 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 11.6 on the Intelligence Index, with 30.4 for coding and 3.7 for agentic tasks. Against its lowest blended price of $0.059 per 1M, that is roughly 197 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 196 tokens per second, with 0.83s to the first token. Running one task of the Artificial Analysis suite costs about $0.1074, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 131,000 tokens at the reference host, but hosts report different limits, from 65,536 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 |
|---|---|---|---|---|---|---|---|---|
| Pendra gpt-oss:120b | Gateway | Free | — | — | 131,072 ⚠ | 32,768 | ||
| Kenari | Gateway | Free | — | — | 131,072 ⚠ | 32,768 | ||
| QVAC | Gateway | Free | — | — | 131,072 ⚠ | 32,768 | ||
| DevPass (LLM Gateway) | Gateway | $0.032 | $0.14 | $0.032 | — | 131,072 ⚠ | 32,766 | |
| LLM Gateway | Gateway | $0.032 | $0.14 | $0.032 | — | 131,072 ⚠ | 32,768 | |
| CoreWeave | Cloud | $0.03 | $0.17 | $0.03 | — | 131,072 ⚠ | 131,072 | |
| Kilo Gateway | Gateway | $0.03 | $0.17 | $0.03 | — | 131,072 ⚠ | 117,964 | |
| OrcaRouter | Gateway | $0.03 | $0.17 | — | — | 131,072 ⚠ | 32,768 | |
| Eden AI | Gateway | $0.03 | $0.17 | $0.0045 | — | 131,072 ⚠ | 32,768 | |
| Helicone | Gateway | $0.04 | $0.16 | — | — | 131,072 ⚠ | 131,072 | |
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 10 of 84 providers.
7 / 84 providers expose no reasoning control (reasoning_options: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| priority | Fireworks AI | $0.18 | $0.72 | $0.018 | — |
3 more channels offer $0 (Pendra, Kenari, QVAC); 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.