GPT OSS 120B

openai/gpt-oss-120b

Maker: OpenAI, United States
Released: 2025-08-05
Knowledge cutoff: 2024-06
Family: gpt-oss
Weights: open (apache-2.0)
Tasks: text.chat, text.reasoning, code
Cheapest offering: DeepInfra, about $0.000088 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Amazon Bedrock	`openai.gpt-oss-120b`	ga	Input: $0.15 Output: $0.6 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Amazon Bedrock	`openai.gpt-oss-120b-1:0`	ga	Input: $0.15 Output: $0.6 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 128,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Amazon Bedrock	`us-gov.openai.gpt-oss-120b-1:0`	ga	Input: $0.18 Output: $0.72 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Cerebras	`gpt-oss-120b`	ga	Input: $0.35 Output: $0.75 Cache read: $0.35 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 40,960 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed
DeepInfra	`openai/gpt-oss-120b`	ga	Input: $0.037 Output: $0.17 Unverified: sources disagree by more than 5%Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 16,384 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Fireworks AI	`accounts/fireworks/models/gpt-oss-120b`	deprecateddeprecated 2026-11-07	Input: $0.15 Output: $0.6 Cache read: $0.015 Input, priority tier: $0.18 Output, priority tier: $0.72 Cache read, priority tier: $0.018 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 32,768 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed
Groq	`openai/gpt-oss-120b`	ga	Input: $0.15 Output: $0.6 Cache read: $0.075 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 65,536 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed `web_search` claimed
OpenRouter	`openai/gpt-oss-120b`	ga	Input: $0.15 Output: $0.6 Cache read: $0.075 Unverified: sources disagree by more than 5%Since 2026-11-04 · models.dev, MIT	none	Context: 131,072 tokens Max output: 65,536 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Together AI	`openai/gpt-oss-120b`	ga	Input: $0.15 Output: $0.6 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed
Google Vertex AI	`openai/gpt-oss-120b-maas`	ga	Input: $0.09 Output: $0.36 Since 2026-11-03 · models.dev, MIT	none	Context: 131,072 tokens Max output: 131,072 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed

Run it locally

Free on your own device. Memory is the weights, the KV cache at the context shown and about 10% overhead; a longer context needs more. GB are 10⁹ bytes. See local models.

Runtime	Model id in the runtime	Quantization	Needs	Context
llama.cpp	`lmstudio-community/gpt-oss-120b-GGUF:MXFP4`	MXFP4	Memory: 70.4 GB at 8,192 tokens GPU memory: 70.4 GB Disk: 63.39 GB Parameters: 116.8B License: apache-2.0	Context: 131,072 tokens
LM Studio	`lmstudio-community/gpt-oss-120b-GGUF/gpt-oss-120b-MXFP4-00001-of-00002.gguf`	MXFP4	Memory: 70.4 GB at 8,192 tokens GPU memory: 70.4 GB Disk: 63.39 GB Parameters: 116.8B License: apache-2.0	Context: 131,072 tokens
Ollama	`gpt-oss:120b`	MXFP4	Memory: 72.72 GB at 8,192 tokens GPU memory: 72.72 GB Disk: 65.5 GB Parameters: 116.8B License: apache-2.0	Context: 131,072 tokens

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.786	0.7576	2025-12-11	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`curated`	0.600 (estimated)	0.6000	2026-11-02	Curated tier (estimated), Nanner Tech
`epoch:aider_polyglot`	0.475	0.4180	2025-08-05	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:terminal_bench`	0.221	0.1870	2025-11-01	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

accounts/fireworks/models/gpt-oss-120b
gpt-oss-120b
openai.gpt-oss-120b
openai.gpt-oss-120b-1:0
openai/gpt-oss-120b-maas
us-gov.openai.gpt-oss-120b-1:0

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/openai/gpt-oss-120b' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=bedrock,cerebras,deepinfra,fireworks,groq,openrouter,together,vertex' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).