Groq

Groq: GPT OSS 120B (Groq)

stable

GPT OSS 120B (Groq) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

openai__gpt-oss-120bgpt-ossreleased Aug 5, 2025
ProviderQuick start
Context
131.1K
tokens
Max output
65.5K
tokens
Input
$0.15
per 1M
Output
$0.60
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
Groq
Groq
131.1K$0.15$0.60

Pricing

ItemPriceUnit
Input$0.15per 1M tokens
Output$0.60per 1M tokens
Cache read$0.075per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
openai__gpt-oss-120b
Family
gpt-oss
Status
stable
Knowledge
-
Released
Aug 5, 2025
Gateway Config
API
2024-01-01
Auth
GROQ_API_KEY
Discovery
static
Provider type
meta

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@groq/openai__gpt-oss-120b",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.groq.com/openai/v1
Chat completions
https://api.groq.com/openai/v1/chat/completions
Model
openai__gpt-oss-120b
Auth env
GROQ_API_KEY

GPT OSS 120B (Groq) FAQ

How much does the GPT OSS 120B (Groq) API cost?

Through Groq, GPT OSS 120B (Groq) costs $0.15 per 1M input tokens and $0.60 per 1M output tokens.

What is the context window of GPT OSS 120B (Groq)?

GPT OSS 120B (Groq) accepts up to 131.1K tokens of context and returns up to 65.5K output tokens on Groq.

What can GPT OSS 120B (Groq) do?

GPT OSS 120B (Groq) supports chat, function calling and reasoning. It accepts text input.

How do I call GPT OSS 120B (Groq) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @groq/openai__gpt-oss-120b. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.