OpenAI

OpenAI: gpt-oss-20b

openai/gpt-oss-20bHugging Face ↗

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

toolsstructuredreasoning
Data source

OpenAI: gpt-oss-20b usage over time

OpenRouter share of tokens, by day.

View
Tidelines — LLM usage and market share

OpenAI: gpt-oss-20b holds 0.43% today, up from 0.25% at the start of the visible window.

Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/openai-gpt-oss-20b

Rank history

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-01 · Source: tidelines.ai/models/openai-gpt-oss-20b

Adoption curve vs the pantheon

OpenAI: gpt-oss-20b'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-20b

Citable stat

As of 2026-09-01, OpenAI: gpt-oss-20b holds 0.4% of OpenRouter token share, up 0.07pp over 30 days. Source: Tidelines (OpenRouter).

Cost per session

Median dollars spent on one OpenAI: gpt-oss-20b 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 turns
Hermes Agent$0.0003$0.0014

Compare every model's session cost →

Data: OpenRouter session-cost dataset as of 2026-08-30 · Source: tidelines.ai/models/openai-gpt-oss-20b

Where to run it

OpenAI: gpt-oss-20b pricing by provider

Tidelines — LLM usage and market share

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

OpenAI: gpt-oss-20b is served by 13 tracked endpoints on OpenRouter. The cheapest output price is $0.10 per million tokens from Darkbloom, and the most expensive is $0.30 from Groq. The largest context window offered is 131k tokens. Prices are list rates and refresh daily.

ProviderInput $/MOutput $/MContextUptime
Darkbloom$0.02$0.10131k99.88%
AkashML$0.02$0.10131k99.25%
CoreWeave$0.03$0.13131k99.99%
DeepInfra$0.03$0.14131k100.00%
Parasail$0.03$0.15131k99.97%
Phala$0.04$0.15131k99.74%
Novita$0.04$0.15131k99.94%
Amazon Bedrock$0.07$0.15131k
SiliconFlow$0.04$0.18131k100.00%
Together$0.05$0.20131k
Google$0.07$0.25131k97.55%
Fireworks$0.07$0.30131k0.00%
Groq$0.07$0.30131k99.86%