GPT-OSS 120B

by openai · family gpt-oss

Facts

Release date	2025-08-05
Retired date	—
Knowledge cutoff	—
Context (max)	131,072
Max output	—
Modalities	text → text
Aliases	`gpt-oss-120b`
Open weights	yes (openai/gpt-oss-120b)
Description	117B-active MoE open-weight reasoning model; thinking cannot be disabled (low/medium/high only).

Unknown values are shown as —.

Intelligence Index v4.1.1: 24 · high effort · Source: Artificial Analysis (accessed 2026-08-20)

Offerings

Provider	Wire ID	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
Baseten	`openai/gpt-oss-120b`	chat-completions	openai-chat	ga	0.10 / 0.50	effort · default on · returns reasoning_content
Fireworks AI	`gpt-oss-120b`	inference-v1	openai-chat	ga	0.15 / 0.60	effort · default on · mandatory · returns reasoning_content
IO Intelligence (io.net)	`openai/gpt-oss-120b`	chat	openai-chat	ga	0.19 / 0.70	effort · default on · returns reasoning_content
NEAR AI Cloud	`openai/gpt-oss-120b`	chat	openai-chat	retired	0.15 / 0.55	effort · default on · mandatory · returns reasoning_content
NVIDIA NIM API	`openai/gpt-oss-120b`	v1-chat-completions	openai-chat	retired	—	toggle · default on · returns reasoning_content
Ollama Cloud	`gpt-oss:120b`	v1-chat-completions	openai-chat	ga	—	effort · default on · mandatory · returns hidden
OpenRouter	`openai/gpt-oss-120b`	chat-completions	openai-chat	ga	0.03 / 0.17	effort · default on · returns reasoning_content · round-trips reasoning_content
Synthetic	`hf:openai/gpt-oss-120b`	openai-chat	openai-chat	ga	—	adaptive · default on · returns hidden

Reasoning controls

Baseten· openai/gpt-oss-120b· chat-completions effort

reasoning_effort nonelowmedium●high

effort · default on · returns reasoning_content

Fireworks AI· gpt-oss-120b· inference-v1 effort

reasoning_effort lowmediumhigh● none is not offered on this surface.

effort · default on · mandatory · returns reasoning_content

IO Intelligence (io.net)· openai/gpt-oss-120b· chat effort

reasoning.effort nonelowmediumhigh● none suppresses reasoning output; the model still reasons internally.

effort · default on · returns reasoning_content

NEAR AI Cloud· openai/gpt-oss-120b· chat effort

reasoning_effort lowmedium●high

effort · default on · mandatory · returns reasoning_content

NVIDIA NIM API· openai/gpt-oss-120b· v1-chat-completions toggle

chat_template_kwargs.enable_thinking on true · off false

toggle · default on · returns reasoning_content

Ollama Cloud· gpt-oss:120b· v1-chat-completions effort

reasoning_effort lowmediumhigh● Default level not documented; verify.

effort · default on · mandatory · returns hidden

OpenRouter· openai/gpt-oss-120b· chat-completions effort

reasoning.effort nonelowmedium●highxhighmax

effort · default on · returns reasoning_content · round-trips reasoning_content

Synthetic· hf:openai/gpt-oss-120b· openai-chat adaptive

adaptive · default on · returns hidden

Example requests

Baseten · openai-chat · openai/gpt-oss-120b

curl 'https://inference.baseten.co/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://inference.baseten.co/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://inference.baseten.co/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())

Fireworks AI · openai-chat · gpt-oss-120b

curl 'https://api.fireworks.ai/inference/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.fireworks.ai/inference/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.fireworks.ai/inference/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

IO Intelligence (io.net) · openai-chat · openai/gpt-oss-120b

curl 'https://api.intelligence.io.solutions/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.intelligence.io.solutions/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.intelligence.io.solutions/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

NEAR AI Cloud · openai-chat · openai/gpt-oss-120b

curl 'https://cloud-api.near.ai/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "medium"
}'

Python (requests)

import requests

resp = requests.post(
    "https://cloud-api.near.ai/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "medium"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://cloud-api.near.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "medium"
  }),
})
console.log(await resp.json())

NVIDIA NIM API · openai-chat · openai/gpt-oss-120b

curl 'https://integrate.api.nvidia.com/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "chat_template_kwargs": {
    "enable_thinking": true
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://integrate.api.nvidia.com/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "chat_template_kwargs": {
        "enable_thinking": true
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://integrate.api.nvidia.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "chat_template_kwargs": {
      "enable_thinking": true
    }
  }),
})
console.log(await resp.json())

Ollama Cloud · openai-chat · gpt-oss:120b

curl 'https://ollama.com/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "gpt-oss:120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://ollama.com/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "gpt-oss:120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://ollama.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "gpt-oss:120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

OpenRouter · openai-chat · openai/gpt-oss-120b

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

Synthetic · openai-chat · hf:openai/gpt-oss-120b

curl 'https://api.synthetic.new/openai/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "hf:openai/gpt-oss-120b",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.synthetic.new/openai/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "hf:openai/gpt-oss-120b",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.synthetic.new/openai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "hf:openai/gpt-oss-120b",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())