OpenAI
OpenAI: gpt-oss-120b
openai/gpt-oss-120bHugging Face ↗
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
OpenAI: gpt-oss-120b usage over time
OpenRouter share of tokens, by day.
OpenAI: gpt-oss-120b holds 0.88% today, down from 0.91% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
OpenAI: gpt-oss-120b's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-07-14, OpenAI: gpt-oss-120b holds 0.9% of OpenRouter token share, down 0.15pp over 30 days. Source: Tidelines (OpenRouter).
Where to run it
Providers & pricing
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| WandB | $0.04 | $0.14 | 131k | 81.59% |
| OpenInference | $0.03 | $0.15 | 131k | 99.70% |
| DeepInfra · 131k | $0.04 | $0.17 | 131k | 76.78% |
| DekaLLM | $0.03 | $0.18 | 131k | 90.05% |
| Novita | $0.05 | $0.25 | 131k | 98.92% |
| $0.09 | $0.36 | 131k | 99.55% | |
| Mancer 2 | $0.04 | $0.38 | 131k | 97.19% |
| SiliconFlow | $0.05 | $0.45 | 131k | 98.60% |
| DigitalOcean | $0.07 | $0.49 | 128k | 98.93% |
| BaseTen | $0.10 | $0.50 | 128k | 99.80% |
| Amazon Bedrock | $0.15 | $0.60 | 131k | 99.97% |
| DeepInfra · 131k | $0.15 | $0.60 | 131k | 99.90% |
| Together | $0.15 | $0.60 | 131k | 99.18% |
| Nebius | $0.15 | $0.60 | 131k | 88.22% |
| Phala | $0.15 | $0.60 | 131k | 99.81% |
| Groq | $0.15 | $0.60 | 131k | 100.00% |
| Parasail | $0.10 | $0.75 | 131k | 75.91% |
| Mara | $0.15 | $0.75 | 131k | — |
| Cerebras | $0.35 | $0.75 | 131k | 82.83% |
| SambaNova | $0.14 | $0.95 | 131k | 94.87% |