OpenAI: gpt oss 120b

openai/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.

Model specifications

Input
text
Output
text
Context
131,072 tokens
Max output
131,072 tokens
Input price
$0.09 / 1M tokens
Output price
$0.36 / 1M tokens
Released
2026-02-11

Capabilities

  • Streaming
  • Function calling
  • Vision
  • Playground

Provider pricing, discounts and data privacy

Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.

Standard service tier

11 available providers · tier input average $0.129727 / 1M tokens · tier output average $0.484545 / 1M tokens

DeepInfra

Tier: Standard · Region: US

Pricing
Input
$0.037 / 1M tokens
Output
$0.17 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
Yes
HIPAA compliant
No
SOC 2 certified
Yes
BYOK supported
Yes

Crusoe

Tier: Standard · Region: US

Pricing
Input
$0.05 / 1M tokens
Output
$0.25 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
No
Data retention
Unknown retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Google Vertex

Tier: Standard · Region: US

Pricing
Input
$0.09 / 1M tokens
Output
$0.36 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
Yes
HIPAA compliant
Yes
SOC 2 certified
Yes
BYOK supported
Yes

AtlasCloud

Tier: Standard · Region: US

Pricing
Input
$0.1 / 1M tokens
Output
$0.2 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
No
Data retention
7-day retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

BytePlus

Tier: Standard · Region: SG

Pricing
Input
$0.1 / 1M tokens
Output
$0.5 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
SG
Zero data retention
No
Data retention
Unknown retention
Used for training
Unknown
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

DigitalOcean

Tier: Standard

Pricing
Input
$0.1 / 1M tokens
Output
$0.7 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Azure

Tier: Standard · Region: US

Pricing
Input
$0.15 / 1M tokens
Output
$0.6 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
Yes
GDPR compliant
Yes
HIPAA compliant
Yes
SOC 2 certified
Yes
BYOK supported
No

Databricks

Tier: Standard

Pricing
Input
$0.15 / 1M tokens
Output
$0.6 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Zero data retention
No
Data retention
Unknown retention
Used for training
Unknown
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Groq

Tier: Standard · Region: US

Pricing
Input
$0.15 / 1M tokens
Output
$0.6 / 1M tokens
Cache read
$0.075 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
No
Data retention
30-day retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Nebius Token Factory

Tier: Standard · Region: NL · Quantization: fp4

Pricing
Input
$0.15 / 1M tokens
Output
$0.6 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
NL
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Cerebras

Tier: Standard · Region: US

Pricing
Input
$0.35 / 1M tokens
Output
$0.75 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
US
Zero data retention
Yes
Data retention
Zero retention
Used for training
No
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Frequently asked questions

What is OpenAI: 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.
How much does OpenAI: gpt oss 120b cost?
Input costs start at $0.09 / 1M tokens and output costs start at $0.36 / 1M tokens. Provider-level prices vary by service tier.
What is the context length of OpenAI: gpt oss 120b?
OpenAI: gpt oss 120b supports a 131,072 token context window and up to 131,072 output tokens.
What capabilities does OpenAI: gpt oss 120b support?
OpenAI: gpt oss 120b supports Streaming, Function calling, Vision, Playground.
Which providers offer OpenAI: gpt oss 120b?
OpenAI: gpt oss 120b is available from DeepInfra, Crusoe, Google Vertex, AtlasCloud, BytePlus, DigitalOcean, Azure, Databricks, Groq, Nebius Token Factory, Cerebras.
How do providers handle data privacy for OpenAI: gpt oss 120b?
11 of 11 providers report that customer data is not used for training, and 6 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.

Browse all AI models