OpenAI: gpt-oss-120b

openai/gpt-oss-120b

gpt-oss-120b is a 120B open-weight model from OpenAI, ranking #127 of 235 on the TryAii Score. It's strongest on math (#16 on AIME-2025). API pricing starts at $0.037/$0.17 per million input/output tokens — about a quarter of what models at its level usually charge, with 24 independent hosts serving it. It's among the fastest models we track, at roughly 39-143 tokens/sec.

Prompt $/1M

$0.037

Completion $/1M

$0.170

Context

131,072 tok

Best provider

776 tok/s · Cerebras

Specs

Model id: openai/gpt-oss-120b
Display name: OpenAI: gpt-oss-120b
Modality: text->text
Tokenizer: GPT
Instruct type: —
Context length: 131,072
Max completion: 117,964
Prompt $/1M: $0.037
Completion $/1M: $0.170
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Cerebrasfastest	776	265 ms	347 ms
SambaNova	315	587 ms	744 ms
Groq	303	209 ms	272 ms
Amazon Bedrock	261	500 ms	549 ms
Nebius	234	208 ms	236 ms
Artificial Analysis	159	543 ms	—
BaseTen	157	301 ms	330 ms
Mara	138	2,364 ms	3,282 ms
Fireworks	126	346 ms	424 ms
AtlasCloud	112	595 ms	624 ms
DeepInfra	109	445 ms	502 ms
Parasail	103	419 ms	489 ms
Phala	72	801 ms	874 ms
Ambient	72	586 ms	741 ms
WandB	67	373 ms	411 ms
Novita	67	607 ms	746 ms
Google	55	1,186 ms	1,716 ms
Io Net	53	1,225 ms	1,726 ms
Together	41	356 ms	482 ms
Clarifai	40	1,363 ms	2,820 ms
Mancer 2	40	631 ms	843 ms
AkashML	37	1,393 ms	1,552 ms
OpenInference	36	471 ms	581 ms
CoreWeave	36	481 ms	546 ms
DigitalOcean	28	719 ms	867 ms
DekaLLM	23	1,360 ms	1,676 ms
SiliconFlow	11	2,072 ms	2,812 ms
Chutes	5	2,676 ms	2,782 ms
openaifastest	—	—	—