token.app › OpenAI › gpt-oss-120b (batch)

gpt-oss-120b (batch) pricing & benchmarks

gpt-oss-120b (batch) is available from OpenAI at $0.030 per million input tokens and $0.136 per million output tokens ($0.056 blended at 3:1). It accepts up to 131,072 tokens of context. 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 optimize…

Pricing

Per million tokens · OpenRouter

Input$0.030

Output$0.136

Blended (3:1)$0.056

Specification

openai/gpt-oss-120b:batch

Context window131K

Max output118K

ReleasedAug 2025

LicenceOpen weights

Modalitiesin:text, out:text

No independently-run benchmark scores are published for gpt-oss-120b (batch) yet. We show nothing rather than reprinting an unverified figure.

Compare gpt-oss-120b (batch)

gpt-oss-120b (batch) vs Gemini 3.7 Flash gpt-oss-120b (batch) vs Grok 4.6 gpt-oss-120b (batch) vs DeepSeek V4 Flash 0731 gpt-oss-120b (batch) vs Inkling Small gpt-oss-120b (batch) vs Qwen3.7 Flash gpt-oss-120b (batch) vs Claude Opus 5 gpt-oss-120b (batch) vs Gemini 3.6 Flash gpt-oss-120b (batch) vs Gemini 3.5 Flash Lite

FAQ

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

gpt-oss-120b (batch) costs $0.030 per million input tokens and $0.136 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.056 per million tokens.

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

gpt-oss-120b (batch) accepts up to 131,072 tokens of context, and can generate up to 117,964 output tokens.