Last updated: Oct 14, 2026 59 sources 20 endpoints monitored

gpt-oss-120b

1352 Score third-party Elo · arena.ai / LMArena ?

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...

LLM & Generative AI 1 model 6 listings snapshot Oct 14, 2026, 12:54 AM

Platforms

click a card to open the detail table

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form
Model Provider Tags Input /1M Output /1M
openai/gpt-oss-120b OpenRouter 120b128k contextreasoning $0.150 $0.600
openai/gpt-oss-120b:batch :batch OpenRouter 120b128k contextreasoning $0.030 $0.136
openai/gpt-oss-120b DeepInfra 120b128k contextreasoning $0.037 $0.170
openai/gpt-oss-120b Together 120b128k context $0.150 $0.600
openai/gpt-oss-120b Groq 120b128k context $0.150 $0.600
openai/gpt-oss-120b Novita 120b $0.050 $0.250

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

  • gamedev 997 · 40.5% wr
  • dataviz 989 · 43.6% wr
  • website 970 · 32.5% wr
  • codecategories 966 · 33.4% wr
  • uicomponent 929 · 35.7% wr
  • 3d 902 · 29.4% wr

Input / Output modalities modality: text->text

  • text in+out

Platform details

per provider
provider model Input /1M Output /1M Latency ? Official $/1M Availability Data time
DeepInfra openai/gpt-oss-120b-Ultra $0.200 $0.950 — — — 2026-10-14 00:43:44
Groq openai/gpt-oss-120b $0.150 $0.600 — — — 2026-10-14 00:54:15
Novita openai/gpt-oss-120b $0.050 $0.250 — — — 2026-10-14 00:54:15
OpenRouter openai/gpt-oss-120b $0.150 $0.600 128.1 ms — 100% available 2026-10-14 00:43:21
Together openai/gpt-oss-120b $0.150 $0.600 — — — 2026-10-14 00:53:13

5 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json