LLM Open Weight
GPT OSS 120B
by OpenAI
Prices last updated October 4, 2026
Open-weight 117B MoE model (5.1B active) achieving near o4-mini reasoning. Apache 2.0 licensed, runs on a single 80GB GPU.
Parameters
117B MoE (5.1B active)
Context
131k
Providers
13
Cheapest Input
$0.037
Function Calling JSON Mode Streaming Chat / InstructCode
Price Comparison
Compare pricing across 13 providers serving GPT OSS 120B
| Provider | Input $/1M | Output $/1M | Context | Speed | TTFT | Status |
|---|---|---|---|---|---|---|
| DE DeepInfra | $0.037 ● | $0.170 | 131k | — | — | Live |
| OP OpenRouter | $0.037 ● | $0.170 | 131k | — | — | Live |
| WA WaveSpeed AI | $0.037 ● | $0.170 | 131k | — | — | Live |
| NO Novita AI | $0.050 | $0.250 | 131k | — | — | Live |
| VE Venice AI | $0.070 | $0.300 | — | — | — | Live |
| PA Parasail | $0.100 | $0.750 | — | — | — | Live |
| FI Fireworks AI | $0.150 | $0.600 | — | — | — | Live |
| NE Nebius | $0.150 | $0.600 | — | — | — | Live |
| GR Groq | $0.150 | $0.600 | 131k | — | — | Live |
| TO Together AI | $0.150 | $0.600 | 131k | — | — | Live |
| SA Sambanova | $0.220 | $0.590 | — | — | — | Live |
| CE Cerebras | $0.350 | $0.750 | — | — | — | Live |
| CL Cloudflare Workers AI | $0.350 | $0.750 | — | — | — | Live |
● Cheapest ● Fastest Prices in USD per 1M tokens