OpenAI — Coding Model

GPT-OSS 120B API — 128k tokens context.

GPT-OSS 120B is OpenAI's open-weight 120B reasoning model, served through IN2PETA at 128k context. It is careful with maths and code, and costs roughly a third of Claude Sonnet class output pricing. It is available from the Go plan upward.

Model ID

gpt-oss-120b

$0.15Input / 1M
$0.60Output / 1M

GPT-OSS 120B specifications

Model IDgpt-oss-120b
VendorOpenAI
Usage tierTier 2
Context window128k tokens
QuantizationMXFP4
Input$0.15 per 1M tokens
Output$0.60 per 1M tokens
Cache read$0.01 per 1M tokens
Approx. output speed~150 tokens/sec

Why run GPT-OSS 120B on IN2PETA

  • OpenAI open-weight 120B
  • Strong at maths and code
  • Available from Go upward
  • OpenAI-compatible endpoint — switch providers by changing one base URL, not by rewriting your client.

Calling the GPT-OSS 120B API

GPT-OSS 120B is served from an OpenAI-compatible gateway. Change your base URL and API key, and existing OpenAI clients work unchanged.

curl https://code.in2peta.com/v1/coding/chat/completions \
  -H "Authorization: Bearer $IN2PETA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-120b",
    "messages": [{"role": "user", "content": "Explain this function"}]
  }'

Set ANTHROPIC_BASE_URL to the same host to point Claude Code at the same gateway. See Getting Started for key setup, and Coding Endpoints for the full API reference.

Plans that include GPT-OSS 120B

FreeFree

Not included

Starter$2/mo

Not included

Go$5/mo

Includes this model

Pro$15/mo

Includes this model

Frequently asked questions

How do I access the GPT-OSS 120B API?

Point any OpenAI-compatible client at https://code.in2peta.com and send requests to /v1/coding/chat/completions with "model": "gpt-oss-120b". The gateway is OpenAI-compatible, so existing SDKs work by changing the base URL and API key.

How much does the GPT-OSS 120B API cost?

GPT-OSS 120B is $0.15 per million input tokens and $0.6 per million output tokens, with cache reads at $0.015 per million. There is no per-request fee on top of token usage.

Which IN2PETA plans include GPT-OSS 120B?

GPT-OSS 120B is available on Go ($5/mo), Pro ($15/mo). Requests for a model outside your plan return HTTP 403 with the allowed model list in the error body.

What is the context window of GPT-OSS 120B?

GPT-OSS 120B serves a 128k tokens context window and runs MXFP4 quantised on IN2PETA.

Start with GPT-OSS 120B today

GPT-OSS 120B is available from the Go plan at $5/month.