Models / OpenAI / GPT OSS 120B

OpenAI · gpt-oss

GPT OSS 120B

Open GPT reasoning model for self-hosted agents and controllable deployments

$0.15 in · $0.60 out

per 1M tokens · provider rate closest to the median. No first-party OpenAI price was listed. The reference price is ai&'s rate, the provider closest to the median.

Provider input prices run from $0.03 to $2.92 per 1M tokens. Output prices run from $0.15 to $4.88.

Context
131,072
Max output
32,768
Cache read
$0.08
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
No
Open weights
Yes
License
—
Released
Aug 5, 2025
Updated in source
Aug 5, 2025
Knowledge
—
Providers
44

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. Where a provider lists the model more than once, the row is the listing whose id is closest to the canonical model id.
ProviderInputOutputCache readCache writeStatus
CoreWeave$0.03$0.17$0.03——
Eden AI$0.03$0.17$0.005——
Kilo Gateway$0.03$0.15$0.03——
OrcaRouter$0.03$0.17———
OpenRouter$0.037$0.17———
Crusoe$0.05$0.20$0.05——
Merge Gateway$0.05$0.25———
Novita AI$0.05$0.25———
Venice AI$0.07$0.30———
Abacus$0.08$0.44———
Cortecs$0.089$0.45$0.01——
Vertex$0.09$0.36———
Vercel AI Gateway$0.10$0.50$0.10——
OpenReason$0.11$0.42———
ai&reference$0.15$0.60$0.08——
AKI.IO$0.15$0.55———
Amazon Bedrock$0.15$0.60———
Groq$0.15$0.60$0.075——
Impossibl$0.15$0.60$0.075——
LLM Gateway$0.15$0.75———
Neon$0.15$0.60———
OCI Generative AI$0.15$0.60———
Pioneer$0.15$0.60$0.015$0.15—
Tinfoil$0.15$0.60———
watsonx.ai$0.16$0.64———
LowRouter$0.17$0.68———
SCX.ai$0.17$0.55———
Charm Hyper$0.18$0.68$0.089——
SambaNova$0.22$0.59———
GreenPT$0.23$0.80———
Privatemode AI$0.23$0.75$0.046——
Hugging Face$0.25$0.69———
Cerebras$0.35$0.75———
Cloudflare Workers AI$0.35$0.75———
Prime Inference$0.35$0.75———
Tempr Gateway$0.35$0.75———
AI/ML API$0.48$1.31$0.48——
STACKIT$0.53$0.76———
Opper$1.16$4.88———
NanoGPT$2.00$2.00$2.00——
CloudFerro Sherlock$2.92$2.92———
Kenari$0$0———
Pendra$0$0———
QVAC$0$0———

Jobs this model qualifies for

Comparisons