GPT OSS 120B

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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

openai/gpt-oss-120b

Organization: OpenAI
Family: gpt-oss
Providers: 67
Context: 131,072
Output limit: 32,768
Knowledge: 2024-06
Release: 2025-08-05
Updated: —
Weights: Open
Input: text
Output: text
Capabilities: —

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

119 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Abacus	openai/gpt-oss-120b	128,000	16,384	— / —	—	—	—	View
ai&	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
AI/ML API	openai/gpt-oss-120b	131,000	117,964	— / —	—	—	—	View
AKI.IO	gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
Amazon Bedrock	us-gov.openai.gpt-oss-120b-1:0	128,000	16,384	— / —	—	—	—	View
Amazon Bedrock	openai.gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Amazon Bedrock	openai.gpt-oss-120b-1:0	131,072	128,000	— / —	—	—	—	View
Baseten	openai/gpt-oss-120b	128,072	128,072	— / —	—	—	—	View
Cerebras	gpt-oss-120b	131,072	40,960	— / —	—	—	—	View
Charm Hyper	gpt-oss-120b	131,072	13,107	— / —	—	—	—	View
Clarifai	openai/chat-completion/models/gpt-oss-120b-high-throughput	131,072	16,384	— / —	—	—	—	View
CloudFerro Sherlock	openai/gpt-oss-120b	131,000	131,000	— / —	—	—	—	View
Cloudflare Workers AI	@cf/openai/gpt-oss-120b	128,000	16,384	— / —	—	—	—	View
CoreWeave	openai/gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Cortecs	gpt-oss-120b	131,000	131,000	— / —	—	—	—	View
Crusoe	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Databricks	databricks-gpt-oss-120b	131,072	25,000	— / —	—	—	—	View
Deep Infra	openai/gpt-oss-120b	131,072	16,384	— / —	—	—	—	View
DevPass (LLM Gateway)	gpt-oss-120b	131,072	32,766	— / —	—	—	—	View
DigitalOcean	openai-gpt-oss-120b	128,000	4,096	— / —	—	—	—	View
DInference	gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	together_ai/openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	nebius/openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	cerebras/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	ionos/openai/gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
Eden AI	arkanecloud/openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	flexai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	ovhcloud/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	cloudflare/@cf/openai/gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
Eden AI	deepinfra/openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	fireworks_ai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	greenpt/gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
Eden AI	databricks/databricks-gpt-oss-120b@eu	131,072	32,768	— / —	—	—	—	View
Eden AI	scaleway/gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
Eden AI	groq/openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	fireworks_ai/accounts/fireworks/models/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Eden AI	databricks/databricks-gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
evroc	openai/gpt-oss-120b	65,536	65,536	— / —	—	—	—	View
FastRouter	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Fireworks AI	accounts/fireworks/models/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
FrogBot	gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
GreenPT	gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
GreenPT	green-r-raw	131,072	32,768	— / —	—	—	—	View
GreenPT	green-r	131,072	32,768	— / —	—	—	—	View
Groq	openai/gpt-oss-120b	131,072	65,536	— / —	—	—	—	View
Helicone	gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Hugging Face	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Impossibl	cerebras/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Impossibl	fireworks/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Impossibl	groq/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
IO.NET	openai/gpt-oss-120b	131,072	4,096	— / —	—	—	—	View
Kenari	gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Kilo Gateway	openai/gpt-oss-120b	131,072	65,536	— / —	—	—	—	View
LLM Gateway	scx-ai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
LLM Gateway	bytedance/gpt-oss-120b	128,000	32,000	— / —	—	—	—	View
LLM Gateway	groq/gpt-oss-120b	131,072	32,766	— / —	—	—	—	View
LLM Gateway	runware/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
LLM Gateway	cerebras/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
LLM Gateway	azure/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
LLM Gateway	together-ai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
LowRouter	auto/openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Merge Gateway	openai/gpt-oss-120b	128,000	32,000	— / —	—	—	—	View
NanoGPT	openai/gpt-oss-120b	128,000	16,384	— / —	—	—	—	View
NanoGPT	TEE/gpt-oss-120b	131,072	16,384	— / —	—	—	—	View
Nebius Token Factory	openai/gpt-oss-120b	131,072	8,192	— / —	—	—	—	View
Neon	gpt-oss-120b	131,072	25,000	— / —	—	—	—	View
Novita AI	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
OCI Generative AI	openai.gpt-oss-120b	128,000	16,384	— / —	—	—	—	View
Ollama Cloud	gpt-oss:120b	131,072	32,768	— / —	—	—	—	View
OpenReason	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
AkashMLvia OpenRouter	openai/gpt-oss-120b bf16	131,072	117,964	$0.03 / $0.187	Yes	Yes	Yes	View
Amazon Bedrockvia OpenRouter	openai/gpt-oss-120b unknown	131,072	117,964	$0.15 / $0.60	Yes	No	No	View
Amazon Bedrockvia OpenRouter	openai/gpt-oss-120b unknown	131,072	117,964	$0.15 / $0.60	Yes	No	No	View
BaseTenvia OpenRouter	openai/gpt-oss-120b fp4	128,072	115,264	$0.10 / $0.50	Yes	Yes	Yes	View
Cerebrasvia OpenRouter	openai/gpt-oss-120b fp16	131,072	40,960	$0.35 / $0.75	Yes	Yes	Yes	View
CoreWeavevia OpenRouter	openai/gpt-oss-120b fp4	131,072	117,964	$0.03 / $0.17	Yes	Yes	Yes	View
Crusoevia OpenRouter	openai/gpt-oss-120b bf16	131,072	117,964	$0.05 / $0.25	Yes	Yes	Yes	View
DeepInfravia OpenRouter	openai/gpt-oss-120b bf16	131,072	16,384	$0.15 / $0.60	Yes	Yes	Yes	View
DeepInfravia OpenRouter	openai/gpt-oss-120b bf16	131,072	117,964	$0.037 / $0.17	Yes	Yes	Yes	View
DekaLLMvia OpenRouter	openai/gpt-oss-120b bf16	131,072	117,964	$0.03 / $0.18	Yes	Yes	Yes	View
DigitalOceanvia OpenRouter	openai/gpt-oss-120b unknown	128,000	4,096	$0.06 / $0.42	Yes	No	No	View
Googlevia OpenRouter	openai/gpt-oss-120b unknown	131,072	117,964	$0.09 / $0.36	Yes	No	Yes	View
Groqvia OpenRouter	openai/gpt-oss-120b unknown	131,072	65,536	$0.15 / $0.60	Yes	Yes	Yes	View
Mancer 2via OpenRouter	openai/gpt-oss-120b fp8	131,072	117,964	$0.05 / $0.25	Yes	Yes	Yes	View
Maravia OpenRouter	openai/gpt-oss-120b unknown	131,072	117,964	$0.15 / $0.75	Yes	Yes	Yes	View
Nebiusvia OpenRouter	openai/gpt-oss-120b fp4	131,072	117,964	$0.15 / $0.60	Yes	Yes	Yes	View
Novitavia OpenRouter	openai/gpt-oss-120b fp4	131,072	32,768	$0.05 / $0.25	Yes	Yes	No	View
Parasailvia OpenRouter	openai/gpt-oss-120b fp4	131,072	117,964	$0.10 / $0.75	Yes	Yes	Yes	View
Phalavia OpenRouter	openai/gpt-oss-120b unknown	131,072	32,768	$0.15 / $0.60	Yes	Yes	Yes	View
SambaNovavia OpenRouter	openai/gpt-oss-120b unknown	131,072	117,964	$0.14 / $0.95	Yes	Yes	No	View
SiliconFlowvia OpenRouter	openai/gpt-oss-120b fp8	131,072	8,192	$0.15 / $0.60	Yes	No	Yes	View
Togethervia OpenRouter	openai/gpt-oss-120b unknown	131,072	117,964	$0.15 / $0.60	Yes	Yes	Yes	View
Venicevia OpenRouter	openai/gpt-oss-120b int4	128,000	32,768	$0.03 / $0.15	Yes	Yes	No	View
Opper	gpt-oss-120b	128,000	8,192	— / —	—	—	—	View
OrcaRouter	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
OVHcloud AI Endpoints	gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Pendra	gpt-oss:120b	131,072	32,768	— / —	—	—	—	View
Poe	cerebras/gpt-oss-120b-cs	128,000	0	— / —	—	—	—	View
Prime Inference	openai/gpt-oss-120b	131,072	65,536	— / —	—	—	—	View
Privatemode AI	gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
QVAC	gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Regolo AI	gpt-oss-120b	128,000	16,384	— / —	—	—	—	View
SambaNova	gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Scaleway	gpt-oss-120b	128,000	32,768	— / —	—	—	—	View
SCX.ai	gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
SiliconFlow	openai/gpt-oss-120b	131,000	8,000	— / —	—	—	—	View
STACKIT	openai/gpt-oss-120b	131,000	8,192	— / —	—	—	—	View
submodel	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Synthetic	hf:openai/gpt-oss-120b	131,072	65,536	— / —	—	—	—	View
Tempr Gateway	cerebras/gpt-oss-120b	131,072	40,960	— / —	—	—	—	View
Tempr Gateway	groq/openai/gpt-oss-120b	131,072	65,536	— / —	—	—	—	View
Thinking Machines	openai/gpt-oss-120b:peft:131072	131,072	131,072	— / —	—	—	—	View
Thinking Machines	openai/gpt-oss-120b	32,768	32,768	— / —	—	—	—	View
Tinfoil	gpt-oss-120b	131,072	32,768	— / —	—	—	—	View
Together AI	openai/gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Venice AI	openai-gpt-oss-120b	128,000	16,384	— / —	—	—	—	View
Vercel AI Gateway	openai/gpt-oss-120b	131,072	131,072	— / —	—	—	—	View
Vertex	openai/gpt-oss-120b-maas	131,072	131,072	— / —	—	—	—	View
watsonx.ai	openai/gpt-oss-120b	131,072	32,768	— / —	—	—	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.03Per 1M input tokens

Output from$0.15Per 1M output tokens

Available offers119Across 67 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 10 lowest-priced configurations

InputOutput

AkashMLakashml/bf16

$0.03$0.187

CoreWeavecoreweave/fp4

$0.03$0.17

DekaLLMdekallm/bf16

$0.03$0.18

Venicevenice/int4

$0.03$0.15

DeepInfradeepinfra/bf16

$0.037$0.17

Crusoecrusoe/bf16

$0.05$0.25

Mancer 2mancer/fp8

$0.05$0.25

Novitanovita/fp4

$0.05$0.25

DigitalOceandigitalocean

$0.06$0.42

Googlegoogle-vertex/global

$0.09$0.36

openai/gpt-oss-120bObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.037
Output: $0.17

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
AkashMLakashml/bf16	$0.03	$0.187	$0.03	—
Amazon Bedrockamazon-bedrock	$0.15	$0.60	—	—
Amazon Bedrockamazon-bedrock/eu-west-1	$0.15	$0.60	—	—
BaseTenbaseten/fp4	$0.10	$0.50	$0.10	—
Cerebrascerebras/fp16	$0.35	$0.75	$0.35	—
CoreWeavecoreweave/fp4	$0.03	$0.17	$0.03	—
Crusoecrusoe/bf16	$0.05	$0.25	$0.05	—
DeepInfradeepinfra/turbo	$0.15	$0.60	—	—
DeepInfradeepinfra/bf16	$0.037	$0.17	—	—
DekaLLMdekallm/bf16	$0.03	$0.18	$0.03	—
DigitalOceandigitalocean	$0.06	$0.42	$0.012	—
Googlegoogle-vertex/global	$0.09	$0.36	—	—
Groqgroq	$0.15	$0.60	$0.075	—
Mancer 2mancer/fp8	$0.05	$0.25	—	—
Maramara	$0.15	$0.75	—	—
Nebiusnebius/fp4	$0.15	$0.60	—	—
Novitanovita/fp4	$0.05	$0.25	—	—
Parasailparasail/fp4	$0.10	$0.75	$0.055	—
Phalaphala	$0.15	$0.60	—	—
SambaNovasambanova	$0.14	$0.95	—	—
SiliconFlowsiliconflow/fp8	$0.15	$0.60	$0.075	—
Togethertogether	$0.15	$0.60	—	—
Venicevenice/int4	$0.03	$0.15	$0.03	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

AkashMLakashml/bf16

2,802–11,821.45 ms

Amazon Bedrockamazon-bedrock

555–5,826.52 ms

Amazon Bedrockamazon-bedrock/eu-west-1

414–11,089.88 ms

Cerebrascerebras/fp16

718.5–5,009.54 ms

CoreWeavecoreweave/fp4

361–9,992.36 ms

Crusoecrusoe/bf16

275–1,356.14 ms

All latency percentiles 22 endpoints

Endpoint	P50	P75	P90	P99
AkashMLakashml/bf16	2,802 ms	5,589 ms	7,798.7 ms	11,821.45 ms
Amazon Bedrockamazon-bedrock	555 ms	670 ms	989.2 ms	5,826.52 ms
Amazon Bedrockamazon-bedrock/eu-west-1	414 ms	622 ms	1,141 ms	11,089.88 ms
Cerebrascerebras/fp16	718.5 ms	1,424 ms	2,380.8 ms	5,009.54 ms
CoreWeavecoreweave/fp4	361 ms	466 ms	1,081.7 ms	9,992.36 ms
Crusoecrusoe/bf16	275 ms	406 ms	647.2 ms	1,356.14 ms
DeepInfradeepinfra/turbo	382 ms	489 ms	664 ms	1,577.12 ms
DeepInfradeepinfra/bf16	296 ms	397 ms	776.9 ms	3,829.81 ms
DekaLLMdekallm/bf16	620 ms	1,081 ms	2,063 ms	6,543.66 ms
DigitalOceandigitalocean	512 ms	836.25 ms	1,467.5 ms	3,255.7 ms
Googlegoogle-vertex/global	265 ms	435 ms	927 ms	7,442.49 ms
Groqgroq	195 ms	312 ms	562 ms	1,984.27 ms
Mancer 2mancer/fp8	679.5 ms	975.75 ms	1,706.5 ms	5,172.24 ms
Maramara	1,013 ms	1,157 ms	1,555.2 ms	6,399.6 ms
Nebiusnebius/fp4	282 ms	390.5 ms	597 ms	1,331.9 ms
Novitanovita/fp4	775 ms	1,072.25 ms	1,642.7 ms	5,643.86 ms
Parasailparasail/fp4	508 ms	604 ms	766 ms	1,064.99 ms
Phalaphala	983.5 ms	1,324.25 ms	1,851 ms	5,106.95 ms
SambaNovasambanova	949 ms	1,654.5 ms	3,913.6 ms	9,719.16 ms
SiliconFlowsiliconflow/fp8	1,356.5 ms	1,489.5 ms	1,973.5 ms	3,046.75 ms
Togethertogether	292 ms	551 ms	806.6 ms	1,703.76 ms
Venicevenice/int4	2,029 ms	2,850 ms	4,383.8 ms	13,886.82 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

AkashMLakashml/bf16

109–206 t/s

Amazon Bedrockamazon-bedrock

226–504.28 t/s

Amazon Bedrockamazon-bedrock/eu-west-1

150–309.71 t/s

Cerebrascerebras/fp16

367–1,700.36 t/s

CoreWeavecoreweave/fp4

40–86 t/s

Crusoecrusoe/bf16

227–284.86 t/s

All throughput percentiles 22 endpoints

Endpoint	P50	P75	P90	P99
AkashMLakashml/bf16	109 t/s	141 t/s	164 t/s	206 t/s
Amazon Bedrockamazon-bedrock	226 t/s	368 t/s	423.8 t/s	504.28 t/s
Amazon Bedrockamazon-bedrock/eu-west-1	150 t/s	185.25 t/s	234.4 t/s	309.71 t/s
Cerebrascerebras/fp16	367 t/s	712.25 t/s	1,065.9 t/s	1,700.36 t/s
CoreWeavecoreweave/fp4	40 t/s	50 t/s	61 t/s	86 t/s
Crusoecrusoe/bf16	227 t/s	249 t/s	264 t/s	284.86 t/s
DeepInfradeepinfra/turbo	121 t/s	158 t/s	281 t/s	517.05 t/s
DeepInfradeepinfra/bf16	81 t/s	91 t/s	104 t/s	141 t/s
DekaLLMdekallm/bf16	52 t/s	67 t/s	85 t/s	130.09 t/s
DigitalOceandigitalocean	64 t/s	72 t/s	76 t/s	80 t/s
Googlegoogle-vertex/global	180 t/s	207 t/s	240 t/s	378 t/s
Groqgroq	321 t/s	385 t/s	427 t/s	505 t/s
Mancer 2mancer/fp8	54 t/s	77 t/s	99 t/s	161.46 t/s
Maramara	194 t/s	258 t/s	376.2 t/s	573.7 t/s
Nebiusnebius/fp4	298 t/s	364 t/s	410 t/s	493.3 t/s
Novitanovita/fp4	167 t/s	205 t/s	230.4 t/s	251.44 t/s
Parasailparasail/fp4	109 t/s	143 t/s	183 t/s	275.19 t/s
Phalaphala	150 t/s	182 t/s	211 t/s	243.72 t/s
SambaNovasambanova	352 t/s	460 t/s	527 t/s	638.34 t/s
SiliconFlowsiliconflow/fp8	55.5 t/s	82.5 t/s	109.5 t/s	118.95 t/s
Togethertogether	124 t/s	160.25 t/s	206 t/s	259.02 t/s
Venicevenice/int4	13 t/s	16 t/s	18 t/s	20 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 23 endpoints

Endpoint5 minutes30 minutes24 hours

AkashMLakashml/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

Amazon Bedrockamazon-bedrockObserved Oct 10, 2026, 11:31 AM UTC

100%

Amazon Bedrockamazon-bedrock/eu-west-1Observed Oct 10, 2026, 11:31 AM UTC

100%

BaseTenbaseten/fp4Observed Oct 10, 2026, 11:31 AM UTC

—

Cerebrascerebras/fp16Observed Oct 10, 2026, 11:31 AM UTC

100%

CoreWeavecoreweave/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

99.65%

Crusoecrusoe/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

DeepInfradeepinfra/turboObserved Oct 10, 2026, 11:31 AM UTC

—

100%

DeepInfradeepinfra/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

99.86%

DekaLLMdekallm/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

DigitalOceandigitaloceanObserved Oct 10, 2026, 11:31 AM UTC

100%

Googlegoogle-vertex/globalObserved Oct 10, 2026, 11:31 AM UTC

60%

20.43%

GroqgroqObserved Oct 10, 2026, 11:31 AM UTC

100%

Mancer 2mancer/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

99.79%

MaramaraObserved Oct 10, 2026, 11:31 AM UTC

—

100%

99.3%

Nebiusnebius/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

99.93%

Novitanovita/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

99.93%

Parasailparasail/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

PhalaphalaObserved Oct 10, 2026, 11:31 AM UTC

—

100%

99.71%

SambaNovasambanovaObserved Oct 10, 2026, 11:31 AM UTC

100%

99.86%

SiliconFlowsiliconflow/fp8Observed Oct 10, 2026, 11:31 AM UTC

—

67.98%

TogethertogetherObserved Oct 10, 2026, 11:31 AM UTC

100%

85.68%

Venicevenice/int4Observed Oct 10, 2026, 11:31 AM UTC

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

openai/gpt-oss-120bObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 40

Coding

30.4

Agentic

3.7

Intelligence

11.6

Design Arena	Category	Elo	Win rate	Rank
models	3d	906	29.4%	113
models	codecategories	967	33.4%	122
models	dataviz	990	43.6%	112
models	gamedev	999	40.5%	113
models	uicomponent	930	35.7%	117
models	website	972	32.5%	125

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondOpenAI: gpt-oss-120b

72.306%

tau bench verified airlineOpenAI: gpt-oss-120b

64.952%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	OpenAI: gpt-oss-120bopenai/gpt-oss-120b	OpenRouter	72.306%	Details
Composite indices	gpt-oss-120b (High)openai/gpt-oss-120b	Artificial Analysis	Intelligence 11.6 · Coding 30.4 · Agentic 3.7	Details
models · 3d	GPT OSS 120Bopenai/gpt-oss-120b	Design Arena	901 Elo	Details
models · gamedev	GPT OSS 120Bopenai/gpt-oss-120b	Design Arena	992 Elo	Details
tau bench verified airline	OpenAI: gpt-oss-120bopenai/gpt-oss-120b	OpenRouter	64.952%	Details
models · codecategories	GPT OSS 120Bopenai/gpt-oss-120b	Design Arena	963 Elo	Details
models · dataviz	GPT OSS 120Bopenai/gpt-oss-120b	Design Arena	987 Elo	Details
models · website	GPT OSS 120Bopenai/gpt-oss-120b	Design Arena	968 Elo	Details
models · uicomponent	GPT OSS 120Bopenai/gpt-oss-120b	Design Arena	924 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Oct 18, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	openai/gpt-oss-120b	10–49 turns	$0.018641	Details
Hermes Agent	openai/gpt-oss-120b	1 turn	$0.000429	Details
Claude Code	openai/gpt-oss-120b	2–9 turns	$0.002365	Details
Hermes Agent	openai/gpt-oss-120b	2–9 turns	$0.001423	Details

Source: OpenRouter, as of Oct 20, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage6,574,206,465,620 reported tokens · 88 days with observations

151B0

2026-07-27
73,626,212,291 tokens

2026-07-28
86,942,273,073 tokens

2026-07-29
76,430,452,610 tokens

2026-07-30
80,598,169,897 tokens

2026-07-31
78,186,210,271 tokens

2026-08-01
76,986,037,986 tokens

2026-08-02
69,855,250,039 tokens

2026-08-03
65,741,515,179 tokens

2026-08-04
80,968,943,499 tokens

2026-08-05
59,116,643,962 tokens

2026-08-06
52,987,465,264 tokens

2026-08-07
52,892,303,388 tokens

2026-08-08
48,857,258,224 tokens

2026-08-09
57,717,627,882 tokens

2026-08-10
61,296,259,330 tokens

2026-08-11
76,683,977,369 tokens

2026-08-12
71,511,635,484 tokens

2026-08-13
67,713,330,455 tokens

2026-08-14
65,009,932,721 tokens

2026-08-15
50,508,503,542 tokens

2026-08-16
50,293,655,388 tokens

2026-08-17
76,270,529,222 tokens

2026-08-18
89,378,420,996 tokens

2026-08-19
69,087,964,402 tokens

2026-08-20
85,473,416,059 tokens

2026-08-21
69,689,203,493 tokens

2026-08-22
72,004,265,270 tokens

2026-08-23
54,396,515,959 tokens

2026-08-24
57,694,468,906 tokens

2026-08-25
65,330,217,924 tokens

2026-08-26
116,194,111,088 tokens

2026-08-27
82,893,119,880 tokens

2026-08-28
76,449,207,255 tokens

2026-08-29
35,615,007,120 tokens

2026-08-30
37,999,951,626 tokens

2026-08-31
64,869,533,374 tokens

2026-09-01
89,596,375,044 tokens

2026-09-02
81,970,720,121 tokens

2026-09-03
63,106,485,880 tokens

2026-09-04
63,984,868,933 tokens

2026-09-05
47,150,586,413 tokens

2026-09-06
51,293,909,895 tokens

2026-09-07
57,891,749,113 tokens

2026-09-08
74,491,045,998 tokens

2026-09-09
83,465,059,108 tokens

2026-09-10
92,430,113,866 tokens

2026-09-11
112,468,461,172 tokens

2026-09-12
72,299,306,963 tokens

2026-09-13
56,186,586,858 tokens

2026-09-14
83,933,730,337 tokens

2026-09-15
127,780,122,097 tokens

2026-09-16
150,784,489,658 tokens

2026-09-17
81,542,601,933 tokens

2026-09-18
67,376,759,806 tokens

2026-09-19
53,710,725,511 tokens

2026-09-20
58,608,187,032 tokens

2026-09-21
85,947,899,818 tokens

2026-09-22
104,632,368,805 tokens

2026-09-23
99,911,502,704 tokens

2026-09-24
112,082,050,529 tokens

2026-09-25
100,226,860,656 tokens

2026-09-26
73,412,190,031 tokens

2026-09-27
55,279,280,028 tokens

2026-09-28
79,581,300,028 tokens

2026-09-29
108,027,521,512 tokens

2026-09-30
104,414,061,130 tokens

2026-10-01
72,030,012,340 tokens

2026-10-02
76,460,953,490 tokens

2026-10-03
56,082,356,483 tokens

2026-10-04
56,269,115,058 tokens

2026-10-05
72,262,437,891 tokens

2026-10-06
78,494,168,660 tokens

2026-10-07
84,148,615,616 tokens

2026-10-08
69,993,070,550 tokens

2026-10-09
66,535,300,712 tokens

2026-10-10
48,397,930,514 tokens

2026-10-12
71,224,176,242 tokens

2026-10-13
99,160,916,459 tokens

2026-10-14
96,081,555,917 tokens

2026-10-15
96,809,756,695 tokens

2026-10-16
86,234,339,891 tokens

2026-10-17
66,910,481,225 tokens

2026-10-18
45,550,794,423 tokens

2026-10-19
72,834,882,317 tokens

2026-10-20
79,563,510,536 tokens

2026-10-21
66,449,754,384 tokens

2026-10-22
89,358,139,263 tokens

2026-10-23
72,497,685,547 tokens

Jul 26, 2026Oct 23, 2026

Daily observations · 88 days

Date (UTC)	Reported tokens	Reported routes
Oct 23, 2026	72,497,685,547	1
Oct 22, 2026	89,358,139,263	1
Oct 21, 2026	66,449,754,384	1
Oct 20, 2026	79,563,510,536	1
Oct 19, 2026	72,834,882,317	1
Oct 18, 2026	45,550,794,423	1
Oct 17, 2026	66,910,481,225	1
Oct 16, 2026	86,234,339,891	1
Oct 15, 2026	96,809,756,695	1
Oct 14, 2026	96,081,555,917	1
Oct 13, 2026	99,160,916,459	1
Oct 12, 2026	71,224,176,242	1
Oct 10, 2026	48,397,930,514	1
Oct 9, 2026	66,535,300,712	1
Oct 8, 2026	69,993,070,550	1
Oct 7, 2026	84,148,615,616	1
Oct 6, 2026	78,494,168,660	1
Oct 5, 2026	72,262,437,891	1
Oct 4, 2026	56,269,115,058	1
Oct 3, 2026	56,082,356,483	1
Oct 2, 2026	76,460,953,490	1
Oct 1, 2026	72,030,012,340	1
Sep 30, 2026	104,414,061,130	1
Sep 29, 2026	108,027,521,512	1
Sep 28, 2026	79,581,300,028	1
Sep 27, 2026	55,279,280,028	1
Sep 26, 2026	73,412,190,031	1
Sep 25, 2026	100,226,860,656	1
Sep 24, 2026	112,082,050,529	1
Sep 23, 2026	99,911,502,704	1
Sep 22, 2026	104,632,368,805	1
Sep 21, 2026	85,947,899,818	1
Sep 20, 2026	58,608,187,032	1
Sep 19, 2026	53,710,725,511	1
Sep 18, 2026	67,376,759,806	1
Sep 17, 2026	81,542,601,933	1
Sep 16, 2026	150,784,489,658	1
Sep 15, 2026	127,780,122,097	1
Sep 14, 2026	83,933,730,337	1
Sep 13, 2026	56,186,586,858	1
Sep 12, 2026	72,299,306,963	1
Sep 11, 2026	112,468,461,172	1
Sep 10, 2026	92,430,113,866	1
Sep 9, 2026	83,465,059,108	1
Sep 8, 2026	74,491,045,998	1
Sep 7, 2026	57,891,749,113	1
Sep 6, 2026	51,293,909,895	1
Sep 5, 2026	47,150,586,413	1
Sep 4, 2026	63,984,868,933	1
Sep 3, 2026	63,106,485,880	1
Sep 2, 2026	81,970,720,121	1
Sep 1, 2026	89,596,375,044	1
Aug 31, 2026	64,869,533,374	1
Aug 30, 2026	37,999,951,626	1
Aug 29, 2026	35,615,007,120	1
Aug 28, 2026	76,449,207,255	1
Aug 27, 2026	82,893,119,880	1
Aug 26, 2026	116,194,111,088	1
Aug 25, 2026	65,330,217,924	1
Aug 24, 2026	57,694,468,906	1
Aug 23, 2026	54,396,515,959	1
Aug 22, 2026	72,004,265,270	1
Aug 21, 2026	69,689,203,493	1
Aug 20, 2026	85,473,416,059	1
Aug 19, 2026	69,087,964,402	1
Aug 18, 2026	89,378,420,996	1
Aug 17, 2026	76,270,529,222	1
Aug 16, 2026	50,293,655,388	1
Aug 15, 2026	50,508,503,542	1
Aug 14, 2026	65,009,932,721	1
Aug 13, 2026	67,713,330,455	1
Aug 12, 2026	71,511,635,484	1
Aug 11, 2026	76,683,977,369	1
Aug 10, 2026	61,296,259,330	1
Aug 9, 2026	57,717,627,882	1
Aug 8, 2026	48,857,258,224	1
Aug 7, 2026	52,892,303,388	1
Aug 6, 2026	52,987,465,264	1
Aug 5, 2026	59,116,643,962	1
Aug 4, 2026	80,968,943,499	1
Aug 3, 2026	65,741,515,179	1
Aug 2, 2026	69,855,250,039	1
Aug 1, 2026	76,986,037,986	1
Jul 31, 2026	78,186,210,271	1
Jul 30, 2026	80,598,169,897	1
Jul 29, 2026	76,430,452,610	1
Jul 28, 2026	86,942,273,073	1
Jul 27, 2026	73,626,212,291	1

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

openai/gpt-oss-120bObserved Oct 10, 2026, 11:31 AM UTC

Context: 131,072
Maximum output: 117,964
Tokenizer: GPT
Input: text
Output: text
Moderation: No
Knowledge cutoff: 2024-06-30
Added to OpenRouter: 2025-08-05

Base URLhttps://openrouter.ai/api/v1

Model IDopenai/gpt-oss-120b

Version IDopenai/gpt-oss-120b

Weights IDopenai/gpt-oss-120b

Reasoning

Required: Yes
Enabled by default: Not reported
Default effort: medium
Supported efforts: high, medium, low

Supported parameters

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_a
top_k
top_logprobs
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does GPT OSS 120B cost?

Listed rates start at $0.03 per million input tokens and $0.15 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer GPT OSS 120B?

There are 119 cataloged offers across 67 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 131,072 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 4 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Oct 21, 2026 · aef714f4f0d0
Oct 20, 2026 · 2c655bf9a095
Sep 14, 2026 · 565ae3e125e5
Sep 12, 2026 · 80d28654c7e0