OpenAI: gpt-oss-120b (batch)

OpenAIOpen weights

OpenAI: gpt-oss-120b (batch) by OpenAI costs $0.03 per 1M input tokens and $0.14 per 1M output tokens, with a 131K-token context window.

Pricing

Input (per 1M tokens)

$0.03

Output (per 1M tokens)

$0.14

Cached input (per 1M)

—

Specifications

Provider: OpenAI
Context window: 131K tokens
Parameters: 117B
Released: Aug 2025
Open weights: Yes
Frontier model: No
Hugging Face: openai/gpt-oss-120b

Benchmarks

Epoch Capabilities Index: 139.9
GPQA Diamond: 75.8
LMArena (Chatbot Arena) Elo: 1365.4
SWE-bench Verified: 26.0

Speed & latency

Time to first token

0.17s

Output speed

1006 tok/s

Fastest host: cerebras (via hf-router).

Compare OpenAI: gpt-oss-120b (batch) with…

OpenAI: gpt-oss-120b (batch) vs OpenAI: GPT-5.6 Sol Pro$10.00/1M OpenAI: gpt-oss-120b (batch) vs OpenAI: GPT-6.1 Sol Pro$10.00/1M OpenAI: gpt-oss-120b (batch) vs OpenAI: GPT-6.1 Sol Pro (batch)$5.00/1M OpenAI: gpt-oss-120b (batch) vs OpenAI: GPT-6.1 Sol$10.00/1M OpenAI: gpt-oss-120b (batch) vs OpenAI: GPT-6.1 Sol (batch)$5.00/1M OpenAI: gpt-oss-120b (batch) vs OpenAI: GPT-6 Luna Pro$0.50/1M

FAQ

How much does OpenAI: gpt-oss-120b (batch) cost?

OpenAI: gpt-oss-120b (batch) is priced at $0.03 per 1M input tokens and $0.14 per 1M output tokens. Output tokens cost more than input.

What is OpenAI: gpt-oss-120b (batch)'s context window?

OpenAI: gpt-oss-120b (batch) supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.

Is OpenAI: gpt-oss-120b (batch) open weight?

Yes — OpenAI: gpt-oss-120b (batch) has openly available weights.

Data as of 2026-10-14. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.