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...

toolsstructuredreasoning
Data source

OpenAI: gpt-oss-120b usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

OpenAI: gpt-oss-120b holds 0.55% today, down from 0.59% at the start of the visible window.

Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/openai-gpt-oss-120b

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/openai-gpt-oss-120b

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?

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/openai-gpt-oss-120b

Citable stat

As of 2026-09-01, OpenAI: gpt-oss-120b holds 0.6% of OpenRouter token share, down 0.41pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one OpenAI: gpt-oss-120b session, by coding agent and session length.

Tidelines — LLM usage and market share

Token rate sets the price; session length and reasoning set the bill.

Agent1 turn2–9 turns10–49 turns50+ turns
Hermes Agent$0.0006$0.0023$0.023$0.097
Claude Code$0.0021$0.020

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-08-30 · Source: tidelines.ai/models/openai-gpt-oss-120b

Where to run it

OpenAI: gpt-oss-120b pricing by provider

Tidelines — LLM usage and market share

Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.

OpenAI: gpt-oss-120b is served by 19 tracked endpoints on OpenRouter. The cheapest output price is $0.17 per million tokens from AkashML, and the most expensive is $0.95 from SambaNova. The largest context window offered is 131k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
AkashML$0.03$0.17131k96.73%
CoreWeave$0.03$0.17131k99.92%
DeepInfra · 131k$0.04$0.17131k99.98%
Novita$0.05$0.25131k100.00%
Google$0.09$0.36131k92.62%
DigitalOcean$0.06$0.39128k99.99%
SiliconFlow$0.05$0.45131k99.92%
Mancer 2$0.07$0.50131k100.00%
BaseTen$0.10$0.50128k100.00%
Amazon Bedrock$0.15$0.60131k
Nebius$0.15$0.60131k99.83%
DeepInfra · 131k$0.15$0.60131k100.00%
Phala$0.15$0.60131k100.00%
Together$0.15$0.60131k99.77%
Groq$0.15$0.60131k100.00%
Parasail$0.10$0.75131k100.00%
Mara$0.15$0.75131k95.74%
Cerebras$0.35$0.75131k99.98%
SambaNova$0.14$0.95131k99.30%