OpenAI

gpt-oss-120b

Generally availableOpen weights131K contextReasoning

Summary

gpt-oss-120b is an open-weight language model from OpenAI, released on 5 Aug 2025. It accepts text and generates text, with a 131K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.04 per million input tokens and $0.17 per million output tokens (DeepInfra), across 15 providers we track.

Open GPT reasoning model for self-hosted agents and controllable deployments

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperOpenAI
Release date5 Aug 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters117B [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output131K tokens [models.dev]
Knowledge cutoffJun 2024 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Hugging Faceopenai/gpt-oss-120b [Hugging Face]

gpt-oss-120b API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
DeepInfra
openai/gpt-oss-120b
$0.04$0.17$0.02131Kmodels.dev, 18 Nov 2026
SiliconFlow
openai/gpt-oss-120b
$0.05$0.45–131Kmodels.dev, 18 Nov 2026
Novita AI
openai/gpt-oss-120b
$0.05$0.25–131Kmodels.dev, 18 Nov 2026
Google Vertex AI
openai/gpt-oss-120b-maas
$0.09$0.36–131Kmodels.dev, 18 Nov 2026
Baseten
openai/gpt-oss-120b
$0.10$0.50$0.10128Kmodels.dev, 18 Nov 2026
Vercel AI Gateway
openai/gpt-oss-120b
$0.10$0.50$0.10131Kmodels.dev, 18 Nov 2026
Databricks
databricks-gpt-oss-120b
$0.15$0.60–131Kmodels.dev, 18 Nov 2026
Amazon Bedrock
openai.gpt-oss-120b
$0.15$0.60–131Kmodels.dev, 18 Nov 2026
Amazon Bedrock
openai.gpt-oss-120b-1:0
$0.15$0.60–131Kmodels.dev, 18 Nov 2026
Together AI
openai/gpt-oss-120b
$0.15$0.60–131Kmodels.dev, 18 Nov 2026
Groq
openai/gpt-oss-120b
$0.15$0.60$0.07131Kmodels.dev, 18 Nov 2026
Nebius AI Studio
openai/gpt-oss-120b
$0.15$0.60$0.15131Kmodels.dev, 18 Nov 2026
OpenRouter
openai/gpt-oss-120b
$0.15$0.60$0.07131KOpenRouter, 18 Nov 2026
Amazon Bedrock
us-gov.openai.gpt-oss-120b-1:0
$0.18$0.72–128Kmodels.dev, 18 Nov 2026
Hugging Face Inference Providers
openai/gpt-oss-120b
$0.25$0.69–131Kmodels.dev, 18 Nov 2026
Cloudflare Workers AI
@cf/openai/gpt-oss-120b
$0.35$0.75–128Kmodels.dev, 18 Nov 2026
Cerebras
gpt-oss-120b
$0.35$0.75$0.35131Kmodels.dev, 18 Nov 2026

Running gpt-oss-120b locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)71 GB72 GB73 GB
Q8_0 (8-bit)124 GB125 GB126 GB
FP16 / BF16 (16-bit)234 GB235 GB236 GB

At 4-bit with an 8K conversation, gpt-oss-120b needs about 72 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of gpt-oss-120b?

gpt-oss-120b has a context window of 131,072 tokens (131K) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the gpt-oss-120b API cost?

gpt-oss-120b is listed from $0.04 per million input tokens and $0.17 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.

Is gpt-oss-120b open source?

gpt-oss-120b is an open-weight model: its weights are published on Hugging Face as openai/gpt-oss-120b under the apache-2.0 license. Check the license terms before commercial use.

When was gpt-oss-120b released?

OpenAI released gpt-oss-120b on 5 Aug 2025, according to models.dev.

Which providers offer gpt-oss-120b?

We track gpt-oss-120b on 15 providers: DeepInfra, SiliconFlow, Novita AI, Google Vertex AI, Baseten, Vercel AI Gateway, Databricks, Amazon Bedrock, Together AI, Groq, Nebius AI Studio, OpenRouter, Hugging Face Inference Providers, Cloudflare Workers AI, Cerebras.

How much VRAM does gpt-oss-120b need?

About 72 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 125 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Nvidia Nemotron Nano 9B V2NVIDIA18 Aug 2025131K$0.06$0.23Open
Baichuan M2 32BBaichuan13 Aug 2025131K$0.07$0.07Open
UI-TARS 7BBytedance22 Jul 2025128K$0.10$0.20Open
DeepSeek R1 0528 Qwen3 8BDeepSeek29 May 2025128K$0.06$0.09Open
Ministral 3 3BMistral AI2 Dec 2025131K$0.10$0.10Open
Granite 4.0 H MicroIBM2 Oct 2025131K$0.02$0.11Open

Change history

  • Name changed from GPT OSS 120B to gpt-oss-120b
  • Max output changed from 33K to 131K
  • DeepInfra price changed: input $0.04 → $0.04, output $0.17 → $0.17 per 1M tokens
  • Max output changed from 16K to 33K
  • Context window changed from 128K to 131K
  • Context window changed from 131K to 128K
  • Max output changed from 131K to 16K
  • Max output changed from 16K to 131K
  • Max output changed from 131K to 16K
  • Max output changed from 8K to 131K
  • Name changed from gpt-oss-120b to GPT OSS 120B
  • Name changed from GPT OSS 120B to gpt-oss-120b
  • Max output changed from 41K to 8K
  • OpenRouter price changed: input $0.03 → $0.15, output $0.09 → $0.60 per 1M tokens
  • Context window changed from 131K to 131K
  • Max output changed from 8K to 41K
  • Tool calling changed from no to yes
  • Name changed from openai/gpt-oss-120b to GPT OSS 120B
  • OpenRouter price changed: input $0.02 → $0.03, output $0.06 → $0.09 per 1M tokens
  • Max output changed from 66K to 8K
  • Tool calling changed from yes to no
  • Context window changed from 131K to 131K
  • Name changed from GPT OSS 120B to openai/gpt-oss-120b
  • OpenRouter price changed: input $0.03 → $0.02, output $0.10 → $0.06 per 1M tokens
  • Name changed from OpenAI GPT 120B to GPT OSS 120B

Sources