What does 'open-source' mean for GPT OSS 120B?

The model weights are publicly available. You can inspect and audit the model while using it through managed APIs.

How does GPT OSS 120B compare to GPT-5?

GPT-5 is OpenAI's closed-source general-purpose model with higher capability. GPT OSS 120B offers strong general-purpose performance with the advantage of open weights and model transparency.

What context window does GPT OSS 120B support?

131.1K tokens, providing substantial capacity for document processing and extended conversations.

How does AI Gateway handle authentication for GPT OSS 120B?

AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.

What are typical latency characteristics?

This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

OpenAI

GPT OSS 120B

GPT OSS 120B is OpenAI's open-source 120-billion parameter language model, offering strong general-purpose capability with the transparency and flexibility of open weights.

View API reference

Input and output price: Prices from: Input $0.10, Output $0.50, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'openai/gpt-oss-120b',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out GPT OSS 120B by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

GPT OSS 120B

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

Baseten

Legal:Terms•Privacy

131K

0.3 s

247 tps

$0.10/M

$0.50/M

—

08/05/2025

Bedrock

Legal:Terms•Privacy

128K

0.4 s

159 tps

$0.15/M

$0.60/M

—

08/05/2025

Fireworks

Legal:Terms•Privacy

128K

0.2 s

282 tps

$0.15/M

$0.60/M

Read$0.01/M

—

08/05/2025

Groq

Legal:Terms•Privacy

131K

33K

0.3 s

463 tps

$0.15/M

$0.60/M

Read$0.08/M

—

08/05/2025

Parasail

Legal:Terms•Privacy

131K

0.4 s

115 tps

$0.10/M

$0.75/M

—

08/05/2025

Nebius

Legal:Terms•Privacy

131K

0.5 s

289 tps

$0.15/M

$0.60/M

—

08/05/2025

Together AI

Legal:Terms•Privacy

128K

0.4 s

34 tps

$0.15/M

$0.60/M

—

08/05/2025

Cerebras

Legal:Terms•Privacy

131K

0.1 s

$0.35/M

$0.75/M

Read$0.25/M

—

08/05/2025

Getting started

Call GPT OSS 120B through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-oss-120b',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same GPT OSS 120B request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-oss-120b',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `openai/gpt-oss-120b`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. GPT OSS 120B supports up to `131,072` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 131K-token context window

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK openai provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-oss-120b',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['baseten', 'bedrock'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-oss-120b',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-oss-120b',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by OpenAI

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

openai/gpt-6-astra

1.1M

2.9 s

56 tps

$10/M+2 more

$50/M+2 more

Read$1/M

Write$12.50/M

$10/K

09/04/2026

openai/gpt-5.6-luna

1.1M

2.4 s

156 tps

$0.20/M+2 more

$1.20/M+2 more

Read$0.02/M

Write$0.25/M

$10/K

07/09/2026

openai/gpt-5.6-sol

1.1M

2.6 s

69 tps

$2/M+2 more

$10/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

openai/gpt-5.6-terra

1.1M

2.6 s

94 tps

$2/M+2 more

$12/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

openai/gpt-5.4

1.1M

3.5 s

88 tps

$2.50/M+2 more

$15/M+2 more

Read$0.25/M

$10/K

03/05/2026

openai/gpt-5-nano

400K

4.4 s

208 tps

$0.05/M

$0.40/M

Read$0.005/M

$14/K

08/07/2025

Copy link to headingAbout GPT OSS 120B

GPT OSS 120B became available on August 5, 2025 on AI Gateway as part of OpenAI's open-source model initiative. At 120 billion parameters, it is the larger of the two initial open-source releases, providing strong general-purpose language model capability with the transparency of open weights.

Open weights mean the model's parameters are publicly available, enabling inspection, auditing, and customization that closed-source models don't permit. For organizations with requirements around model transparency or regulatory compliance, this is significant.

Through AI Gateway, teams can use GPT OSS 120B as a managed API without handling the infrastructure required to serve a 120B parameter model.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: GPT OSS 120B ships with open weights, so you can inspect the model, understand its behavior, and deploy it in environments where model transparency is required.
Configuration: At 120B parameters, this is a substantial model. Through AI Gateway you access it as a managed API without handling infrastructure.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use GPT OSS 120B

Best for

Transparency-required deployments: Applications where model weights must be inspectable or auditable
Research and experimentation: Teams studying large language model behavior with full access to architecture
Open-source strategy: Organizations committed to open-source AI infrastructure
General-purpose tasks: Chat, content generation, analysis, and coding at a capable model scale

Consider alternatives when

Maximum proprietary capability: GPT-5 or GPT-5.2 for higher closed-source capability
Smaller open-source: Gpt-oss-20b for lighter-weight open-source deployments
Cost optimization: Smaller models for tasks that don't require 120B parameter scale
Specialized tasks: Codex models for coding, o-series for reasoning

Copy link to headingConclusion

GPT OSS 120B combines substantial language model capability with the openness of public weights. Available through AI Gateway as a managed API, it serves teams that need both capable AI and model transparency.

Copy link to headingFrequently Asked Questions

What does 'open-source' mean for GPT OSS 120B?
The model weights are publicly available. You can inspect and audit the model while using it through managed APIs.
How does GPT OSS 120B compare to GPT-5?
GPT-5 is OpenAI's closed-source general-purpose model with higher capability. GPT OSS 120B offers strong general-purpose performance with the advantage of open weights and model transparency.
What context window does GPT OSS 120B support?
131.1K tokens, providing substantial capacity for document processing and extended conversations.
How does AI Gateway handle authentication for GPT OSS 120B?
AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

Your use is subject to OpenAI's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

GPT OSS 120B

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Tool calling

Copy link to headingMore models by OpenAI

Copy link to headingAbout GPT OSS 120B

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use GPT OSS 120B

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions