OpenAI: gpt-oss-120b (batch)

Name: OpenAI: gpt-oss-120b (batch)
Author: OpenRouter

deprecated

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.

Context

131K

Max output

118K

Input price

$0.03/1M tokens

Output price

$0.14/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDopenai/gpt-oss-120b:batch

ProviderOpenRouter

CreatorOpenAI

Familygpt-oss

License—

Parameters—

Statusdeprecated

Input modalitiestext

Output modalitiestext

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date2025-08-05

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weight—

Sourceofficial

Last updated2026-09-24

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.03

↓80%$0.15

Output

$0.14

↓77%$0.6

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Price history · $/1M input

$0.15

$0.03

Aug 31Sep 24

Date	Input	Output	Change
Aug 31, 2026	$0.15	$0.6	—
Sep 24, 2026118451a	$0.03	$0.136	↓80%

Input is ↓80% since Aug 31, 2026, from $0.15 to $0.03 per 1M tokens.

Family Comparison: gpt-oss

Model	Caps	Perf	Speed	Context	Max out	Pricing
OpenAI: gpt-oss-120b (free)	RVTS	—	—	131K	131K
OpenAI: gpt-oss-20b (free)	RVTS	—	—	131K	33K
OpenAI: gpt-oss-20b	RTS	—	—	131K	33K	$0.02$0.09
OpenAI: gpt-oss-20b (batch)	RVTS	—	—	131K	118K	$0.02$0.11
OpenAI: gpt-oss-120b (batch)	RVTS	—	—	131K	118K	$0.03$0.14
OpenAI: gpt-oss-120b	RTS	—	—	131K	118K	$0.04$0.17
OpenAI: gpt-oss-safeguard-20b	RVTS	—	—	131K	66K	$0.08$0.3

API

GET/v1/models/openrouter/openai/gpt-oss-120b:batch