Loading…
OpenAI
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...
OpenRouter share of tokens, by day.
OpenAI: gpt-oss-120b holds 0.36% today, down from 0.59% at the start of the visible window.
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 2026-10-14, OpenAI: gpt-oss-120b holds 0.4% of OpenRouter token share, down 0.10pp over 30 days. Source: OpenRouter (openrouter.ai/rankings), as of 2026-10-14. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
OpenAI: gpt-oss-120b is served by 22 tracked endpoints on OpenRouter. The cheapest output price is $0.15 per million tokens from Near AI, and the most expensive is $0.95 from SambaNova. The largest context window offered is 131k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Near AI | $0.030 | $0.15 | 131k | 100.00% |
| Venice | $0.030 | $0.15 | 128k | 100.00% |
| CoreWeave | $0.030 | $0.17 | 131k | 100.00% |
| DeepInfra | $0.037 | $0.17 | 131k | 100.00% |
| DekaLLM | $0.030 | $0.18 | 131k | 100.00% |
| AkashML | $0.030 | $0.19 | 131k | 100.00% |
| Crusoe | $0.050 | $0.25 | 131k | 100.00% |
| Mancer 2 | $0.050 | $0.25 | 131k | 100.00% |
| Novita | $0.050 | $0.25 | 131k | 100.00% |
| $0.090 | $0.36 | 131k | 0.00% | |
| DigitalOcean | $0.060 | $0.42 | 128k | 100.00% |
| BaseTen | $0.100 | $0.50 | 128k | 100.00% |
| Amazon Bedrock | $0.15 | $0.60 | 131k | 100.00% |
| Nebius | $0.15 | $0.60 | 131k | 100.00% |
| SiliconFlow | $0.15 | $0.60 | 131k | 63.64% |
| Phala | $0.15 | $0.60 | 131k | 100.00% |
| Together | $0.15 | $0.60 | 131k | 72.73% |
| Groq | $0.15 | $0.60 | 131k | 100.00% |
| Parasail | $0.100 | $0.75 | 131k | 100.00% |
| Mara | $0.15 | $0.75 | 131k | 100.00% |
| Cerebras | $0.35 | $0.75 | 131k | 100.00% |
| SambaNova | $0.14 | $0.95 | 131k | 100.00% |
Median dollars spent on one OpenAI: gpt-oss-120b session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns |
|---|---|---|---|
| Hermes Agent | $0.0004 | $0.0017 | $0.020 |
| Claude Code | — | $0.0022 | — |
