Skip to content
Sovyron

GPT OSS 120B

gpt-oss131k context131k max outputreleased Aug 5, 2025Open weightsReasoningTool calling

As of Oct 4, 2026, the cheapest GPT OSS 120B API price is $0.03 per 1M input tokens (Kilo Gateway) and $0.1 per 1M output tokens (Synthetic). GPT OSS 120B is offered by 61 providers in the gpt-oss family, open weights, reasoning enabled. 3 providers list it as a free-tier offer.

Cheapest input
$0.03
Cheapest output
$0.1
Official
—
output per 1M tokens
Providers
61
offering this model
Spread
48.8×
max / min output
Free offers
3
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

GPT OSS 120B API prices by provider in USD per 1M tokens, updated Oct 4, 2026
DevPass (LLM Gateway)$0.032$0.14$0.032—131k—
Kilo GatewayopenCheapest$0.03$0.17$0.03—131k—
OrcaRouteropen$0.03$0.17——131k—
CoreWeaveopen$0.03$0.17$0.03—131k—
Helicone$0.04$0.16——131k—
Deep Infraopen$0.037$0.17——131k—
Eden AIopen$0.037$0.17——131k—
OpenRouteropen$0.037$0.17——131k4d agoout −71.7%
Crusoeopen$0.05$0.2$0.05—131k—
Merge Gatewayopen$0.05$0.25——128kyesterdayout −30.6%
NovitaAIopen$0.05$0.25——131k—
Syntheticopen$0.1Cheapest$0.1$0.1—131k—
DInferenceopen$0.0675$0.27——131k—
Databricksopen$0.072$0.28——131k—
Venice AIopen$0.07$0.3——128k—
IO.NETopen$0.04$0.4$0.02$0.08131k—
SiliconFlow$0.05$0.45——131k—
Vertexopen$0.09$0.36——131k—
Abacusopen$0.08$0.44——128k—
Cortecsopen$0.089$0.446$0.01—131k—
OpenReasonopen$0.1055$0.422——131k—
Eden AIopen$0.09$0.47——131k—
OVHcloud AI Endpointsopen$0.09$0.47——131k—
submodelopen$0.1$0.5——131k—
Vercel AI Gatewayopen$0.1$0.5$0.1—131k—
AKI.IOopen$0.15$0.55——128k—
DigitalOceanopen$0.1$0.7$0.02—128k12d agoout +81.8%
ai&open$0.15$0.6$0.08—131k—
Amazon Bedrockopen$0.15$0.6——131k—
Amazon Bedrockopen$0.15$0.6——131k—
Eden AIopen$0.15$0.6$0.015—131k—
Eden AIopen$0.15$0.6$0.014—131k—
Eden AIopen$0.15$0.6$0.075—131k—
Eden AIopen$0.15$0.6$0.15—131k—
Eden AIopen$0.15$0.6——131k—
FastRouteropen$0.15$0.6——131k—
Fireworks AIopen$0.15$0.6$0.015—131k—
FrogBotopen$0.15$0.6——131k—
Groqopen$0.15$0.6$0.075—131k—
Impossiblopen$0.15$0.6$0.015—131k—
Impossiblopen$0.15$0.6$0.075—131k—
LLM Gatewayopen$0.15$0.6——131k—
LLM Gatewayopen$0.15$0.6——131k—
Nebius Token Factoryopen$0.15$0.6$0.015$0.18131k—
Neonopen$0.15$0.6——131k—
OCI Generative AIopen$0.15$0.6——128k—
Ollama Cloudopen$0.15$0.6$0.014—131k—
Pioneeropen$0.15$0.6$0.015$0.15131k—
Scalewayopen$0.15$0.6——128k—
Tempr Gatewayopen$0.15$0.6$0.075—131k—
Tinfoilopen$0.15$0.6——131k—
Together AIopen$0.15$0.6——131k—
Eden AIopen$0.15$0.6$0.015$0.15131k—
SCX.aiopen$0.17$0.55——131k—
watsonx.aiopen$0.159$0.636——131k—
Eden AIopen$0.1684$0.6735——128kyesterdayout −0.6%
LLM Gatewayopen$0.15$0.75——131k—
Charm Hyperopen$0.178$0.68$0.089—131k19d agoout +3%
Hugging Faceopen$0.25$0.69——131k—
Privatemode AIopen$0.2311$0.7511$0.0462—128kyesterdayout −61.8%
GreenPTopen$0.228$0.798——131k—
evrocopen$0.23$0.92——66k—
Cerebrasopen$0.35$0.75——131k—
Cloudflare Workers AIopen$0.35$0.75——128k—
Eden AIopen$0.35$0.75$0.35—131k—
Eden AIopen$0.35$0.75——128k—
Impossiblopen$0.35$0.75——131k—
LLM Gatewayopen$0.35$0.75——131k—
NanoGPTopen$0.35$0.75——128k—
Tempr Gatewayopen$0.35$0.75——131k—
STACKITopen$0.53$0.76——131k—
Regolo AI$1$4.2——128k—
Opperopen$1.1622$4.8812——128k—
CloudFerro Sherlockopen$2.92$2.92——131k—
Kenarifreefreefree——131k—
Pendrafreefreefree——131k—
QVACfreefreefree——131k—

GPT OSS 120B pricing FAQ

What is the cheapest GPT OSS 120B API?

As of Oct 4, 2026, Synthetic has the lowest GPT OSS 120B output price at $0.1 per 1M tokens, and Kilo Gateway has the lowest input price at $0.03 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer GPT OSS 120B?

61 providers list GPT OSS 120B on Sovyron; 74 of them sell it at a metered per-token price.

Is GPT OSS 120B free?

3 provider(s) list a free-tier offer: Kenari, Pendra, QVAC. Free tiers usually have rate limits.

What is the context window of GPT OSS 120B?

GPT OSS 120B supports a 131k-token context window and up to 131k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.

Estimated

—