Skip to content
Sovyron

GPT OSS 120B

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

As of Nov 22, 2026, the cheapest GPT OSS 120B API price is $0.0291 per 1M input tokens (DevPass (LLM Gateway)) and $0.1 per 1M output tokens (Synthetic). GPT OSS 120B is offered by 74 providers in the gpt-oss family, open weights, reasoning enabled. One provider lists it as a free-tier offer.

Cheapest input
$0.0291
Cheapest output
$0.1
Official
—
output per 1M tokens
Providers
74
offering this model
Spread
48.8×
max / min output
Free offers
1
free-tier offer

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

GPT OSS 120B API prices by provider in USD per 1M tokens, updated Nov 22, 2026
DevPass (LLM Gateway)opengpt-oss-120bCheapest$0.0291$0.1455$0.0044—131k4d agoout −38.7%
Kilo Gatewayopenopenai/gpt-oss-120b$0.03$0.15$0.015—131k13d agoout +89.9%
NanoGPTopenopenai/gpt-oss-120b$0.03$0.15$0.03—128k34d ago
CoreWeaveopenopenai/gpt-oss-120b$0.03$0.17$0.03—131k—
Heliconeopengpt-oss-120b$0.04$0.16——131k—
Abacusopenopenai/gpt-oss-120b$0.037$0.17——128k31d ago
Deep Infraopenopenai/gpt-oss-120b$0.037$0.17$0.0185—131k—
Eden AIopendeepinfra/openai/gpt-oss-120b$0.037$0.17$0.0185—131k—
Phase Routeropengpt-oss-120b$0.0385$0.1768——131k—
Runcrateopenopenai/gpt-oss-120b$0.0389$0.1785$0.0058—131k—
Kenariopengpt-oss-120b$0.036$0.2$0.0036—131k31d ago
Crusoeopenopenai/gpt-oss-120b$0.05$0.25$0.05—131k31d ago
Merge Gatewayopenopenai/gpt-oss-120b$0.05$0.25——128k50d ago
Novita AIopenopenai/gpt-oss-120b$0.05$0.25——131k—
Syntheticopenhf:openai/gpt-oss-120b$0.1Cheapest$0.1$0.02—131k—
DInferenceopengpt-oss-120b$0.0675$0.27——131k—
Moneoopengpt-oss-120b$0.07$0.28——128k—
Venice AIopenopenai-gpt-oss-120b$0.07$0.3——128k—
AI Power Gridopengpt-oss-120b$0.075$0.3——40k—
SiliconFlowopenopenai/gpt-oss-120b$0.05$0.45——131k—
FastRouteropenopenai/gpt-oss-120b$0.09$0.36——131k31d ago
Vertexopenopenai/gpt-oss-120b-maas$0.09$0.36——131k—
OpenRouteropenopenai/gpt-oss-120b$0.09$0.36——131k2d agoout −40%
Powerspringopengpt-oss-120b$0.0884$0.4421——131k—
Cortecsopengpt-oss-120b$0.089$0.446$0.01—131k—
OpenReasonopenopenai/gpt-oss-120b$0.1055$0.422——131k—
Eden AIopenovhcloud/gpt-oss-120b$0.09$0.47——131k—
OVHcloud AI Endpointsopengpt-oss-120b$0.09$0.47——131k—
SOKKAN Routeropenopenai/gpt-oss-120b$0.1$0.5$0.1—131k—
submodelopenopenai/gpt-oss-120b$0.1$0.5——131k—
Vercel AI Gatewayopenopenai/gpt-oss-120b$0.1$0.5$0.1—131k—
DigitalOceanopenopenai-gpt-oss-120b$0.1$0.7$0.02—128k61d ago
ai&openopenai/gpt-oss-120b$0.15$0.6$0.08—131k—
Amazon Bedrockopenopenai.gpt-oss-120b$0.15$0.6——131k—
Amazon Bedrockopenopenai.gpt-oss-120b-1:0$0.15$0.6——131k—
Databricksopendatabricks-gpt-oss-120b$0.15$0.6——131k31d ago
Eden AIopendatabricks/databricks-gpt-oss-120b$0.15$0.6$0.015$0.15131k8d agoout +0%
Eden AIopenfireworks_ai/accounts/fireworks/models/gpt-oss-120b$0.15$0.6$0.015—131k—
Eden AIopenfireworks_ai/gpt-oss-120b$0.15$0.6$0.014—131k—
Eden AIopengroq/openai/gpt-oss-120b$0.15$0.6$0.075—131k—
Eden AIopennebius/openai/gpt-oss-120b$0.15$0.6$0.15—131k—
Eden AIopentogether_ai/openai/gpt-oss-120b$0.15$0.6——131k—
FrogBotopengpt-oss-120b$0.15$0.6——131k—
GraphNopengpt-oss-120b$0.15$0.6——131k—
Groqopenopenai/gpt-oss-120b$0.15$0.6$0.075—131k—
Inference Cooperativeopentinfoil/gpt-oss-120b$0.15$0.6——131k—
Kelnopenopenai/gpt-oss-120b$0.15$0.6$0.1—131k—
LLM Gatewayopenazure/gpt-oss-120b$0.15$0.6——131k—
LLM Gatewayopentogether-ai/gpt-oss-120b$0.15$0.6——131k—
Nebius Token Factoryopenopenai/gpt-oss-120b$0.15$0.6$0.1—131k—
Neonopengpt-oss-120b$0.15$0.6——131k—
OCI Generative AIopenopenai.gpt-oss-120b$0.15$0.6——128k—
Ollama Cloudopengpt-oss:120b$0.15$0.6$0.014—131k—
Phalaopenopenai/gpt-oss-120b$0.15$0.6——131k—
Tinfoilopengpt-oss-120b$0.15$0.6——131k—
Together AIopenopenai/gpt-oss-120b$0.15$0.6——131k—
ZeroGPUopengpt-oss-120b$0.15$0.6——131k—
SCX.aiopengpt-oss-120b$0.17$0.55——131k—
Klavo AIopenopenai/gpt-oss-120b$0.1575$0.6057$0.0485—131k—
watsonx.aiopenopenai/gpt-oss-120b$0.159$0.636——131k—
AKI.IOopengpt-oss-120b$0.1682$0.6168——128k31d ago
Eden AIopenscaleway/gpt-oss-120b$0.1648$0.6594——128kyesterdayout +0.2%
Scalewayopengpt-oss-120b$0.1682$0.6729——128k31d ago
LowRouteropenauto/openai/gpt-oss-120b$0.1695$0.6779——131k—
LLM Gatewayopengroq/gpt-oss-120b$0.15$0.75——131k—
Charm Hyperopengpt-oss-120b$0.178$0.68$0.089—131k68d ago
SambaNovaopengpt-oss-120b$0.22$0.59——131k—
IO.NETopenopenai/gpt-oss-120b$0.188$0.7$0.094—131k31d ago
Inference APIsopenopenai/gpt-oss-120b$0.2$0.8——131k—
Eden AIopengreenpt/gpt-oss-120b$0.2198$0.7693——128kyesterdayout +0.2%
Hugging Faceopenopenai/gpt-oss-120b$0.25$0.69——131k—
Privatemode AIopengpt-oss-120b$0.2311$0.7511$0.0462—128k50d ago
GreenPTopengpt-oss-120b$0.228$0.798——131k—
evrocopenopenai/gpt-oss-120b$0.23$0.92——66k—
Cerebrasopengpt-oss-120b$0.35$0.75$0.35—131k—
Cloudflare Workers AIopen@cf/openai/gpt-oss-120b$0.35$0.75——128k—
Eden AIopencerebras/gpt-oss-120b$0.35$0.75$0.35—131k—
Eden AIopencloudflare/@cf/openai/gpt-oss-120b$0.35$0.75——128k—
LLM Gatewayopencerebras/gpt-oss-120b$0.35$0.75——131k—
Prime Inferenceopenopenai/gpt-oss-120b$0.35$0.75——131k—
Thinking Machinesopenopenai/gpt-oss-120b$0.33$0.84$0.066—33k—
Thinking Machinesopenopenai/gpt-oss-120b:peft:131072$0.33$0.84$0.066—131k—
AI/ML APIopenopenai/gpt-oss-120b$0.3703$1.0051$0.3703—131k30d agoout −23.1%
STACKITopenopenai/gpt-oss-120b$0.53$0.76——131k—
stepping stone AGopenopenai/gpt-oss-120b$0.476$1.904$0.0714—131k—
Regolo AIopengpt-oss-120b$1.1215$4.7103——128k31d ago
Opperopengpt-oss-120b$1.1622$4.8812——128k—
CloudFerro Sherlockopenopenai/gpt-oss-120b$2.92$2.92——131k—
Pendrafreegpt-oss:120bfreefree——131k—

GPT OSS 120B price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 21 providers whose rate moved. Each step is a recorded change. All recent price changes.

GPT OSS 120B output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$0.25$0.5$0.75$1Sep 10, 2026Oct 17, 2026Nov 22, 2026
DevPass (LLM Gateway)$0.1455Kilo Gateway$0.15NanoGPT$0.15Abacus$0.17Kenari$0.2Crusoe$0.25
GPT OSS 120B price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Eden AI$0.1645 → $0.1648$0.6581 → $0.6594+0.2%
Eden AI$0.2194 → $0.2198$0.7678 → $0.7693+0.2%
OpenRouter$0.15 → $0.09$0.6 → $0.36−40%
Eden AI$0.1648 → $0.1645$0.6593 → $0.6581−0.2%
Eden AI$0.2198 → $0.2194$0.7692 → $0.7678−0.2%
Eden AI$0.2203 → $0.2198$0.771 → $0.7692−0.2%
Eden AI$0.1652 → $0.1648$0.6608 → $0.6593−0.2%
DevPass (LLM Gateway)$0.0475 → $0.0291$0.2375 → $0.1455−38.7%
Eden AI$0.1658 → $0.1652$0.6631 → $0.6608−0.3%
Eden AI$0.221 → $0.2203$0.7736 → $0.771−0.3%
DevPass (LLM Gateway)$0.05 → $0.0475$0.25 → $0.2375−5%
Eden AI$0.2216 → $0.221$0.7757 → $0.7736−0.3%
Eden AI$0.1662 → $0.1658$0.6649 → $0.6631−0.3%
Eden AI$0.2225 → $0.2216$0.7789 → $0.7757−0.4%
Eden AI$0.1669 → $0.1662$0.6676 → $0.6649−0.4%
Eden AI$0.15 → $0.15$0.6 → $0.6+0%
Eden AI$0.2243 → $0.2225$0.785 → $0.7789−0.8%
Eden AI$0.1682 → $0.1669$0.6728 → $0.6676−0.8%
Eden AI$0.1679 → $0.1682$0.6716 → $0.6728+0.2%
Eden AI$0.2239 → $0.2243$0.7835 → $0.785+0.2%

GPT OSS 120B pricing FAQ

What is the cheapest GPT OSS 120B API?

As of Nov 22, 2026, Synthetic has the lowest GPT OSS 120B output price at $0.1 per 1M tokens, and DevPass (LLM Gateway) has the lowest input price at $0.0291 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?

74 providers list GPT OSS 120B on Sovyron; 88 of them sell it at a metered per-token price.

Is GPT OSS 120B free?

One provider lists a free-tier offer: Pendra. 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. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—