GPT OSS 120b API Pricing 2026

Compare pricing, benchmarks, and providers for GPT OSS 120b. Find the best value for your use case.

Sponsor Price Per Token— Reach 5000+ developers comparing LLM APIs

116 out of our 296 tracked models have had a price change in January.

Make informed model choices with updates on pricing, new releases, and tools with our weekly newsletter.

Last updated: January 16, 2026 at 08:05 AM

Overview

GPT OSS 120b was released on August 5, 2025. Pricing starts at $0.039 per million input tokens and $0.190 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through OpenAI.

Context Window

131K

tokens

Pricing

Input$0.039

Output$0.190

per 1M tokens

Speed

Output338 tok/s

TTFT0.42s

median latency

Capabilities

Text only

Pricing Comparison

Compare GPT OSS 120b with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Coding	MMLU	GPQA	Context	Actions
O OpenAI	GPT-OSS-120b	$0.039	$0.190	87.8	80.8	78.2	131,072	Try
MI Mistral AI	Mistral Small 3.1 24B	$0.030	$0.110	21.2	65.9	45.4	131,072	Try
MI Mistral AI	Mistral Small 3	$0.030	$0.110	—	—	—	32,768	Try
QW Qwen	Qwen2.5 Coder 7B Instruct	$0.030	$0.090	12.6	47.3	33.9	32,768	Try
G Google	Gemma 3 12B	$0.030	$0.100	13.7	59.5	34.9	131,072	Try
M Deepseek	R1 Distill Llama 70B	$0.030	$0.110	26.6	79.5	40.2	131,072	Try
QW Qwen	Qwen2.5 Coder 32B Instruct	$0.030	$0.110	29.5	63.5	41.7	32,768	Try
G Google	Gemma 2 9B	$0.030	$0.090	—	31.9	14.8	8,192	Try
M Meta-llama	Llama 3 8B Instruct	$0.030	$0.060	9.6	40.5	29.6	8,192	Try
AM Amazon	Nova Micro 1.0	$0.035	$0.140	14.0	53.1	35.8	128,000	Try
CO Cohere	Command R7B (12-2024)	$0.037	$0.150	—	—	—	128,000	Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

GPT OSS 120b is available from multiple providers with different pricing and availability.

Providers

$0.020

Cheapest Input/M

$0.100

Cheapest Output/M

GMICloud

Best Price

Provider Pricing

22 models

Provider	Input $/M	Output $/M	Uptime
G GMICloud Best Price	$0.020	$0.100	99.6%
C Chutes	$0.040	$0.180	100.0%
OpenRouter	$0.040	$0.400	-
S SiliconFlow	$0.050	$0.450	100.0%
N NCompass	$0.050	$0.280	100.0%
N Novita	$0.050	$0.250	100.0%
C Clarifai	$0.090	$0.360	98.3%
Google	$0.090	$0.360	99.7%
P Phala	$0.100	$0.490	-
A AtlasCloud	$0.100	$0.200	-
B BaseTen	$0.100	$0.500	99.9%
P Parasail	$0.120	$0.750	-
S SambaNova	$0.140	$0.950	100.0%
T Together	$0.150	$0.600	-
W WandB	$0.150	$0.600	100.0%
N Nebius	$0.150	$0.600	99.9%
C Crusoe	$0.150	$0.600	69.5%
Amazon Bedrock	$0.150	$0.600	-
Groq	$0.150	$0.600	100.0%
F Fireworks	$0.150	$0.600	100.0%
D DeepInfra	$0.150	$0.600	-
C Cerebras	$0.350	$0.750	100.0%

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

Compare GPT OSS 120b's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

GPT-OSS-120b

Other models

Detailed Benchmark Scores

Intelligence

32.9 (82th pct)

Coding

27.6 (74th pct)

Math

93.4 (94th pct)

MMLU Pro

80.8 (68th pct)

GPQA

78.2 (83th pct)

LiveCodeBench

87.8 (97th pct)

AIME

Aider

41.8 (22th pct)

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try GPT OSS 120b

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test GPT OSS 120b directly in your browser.

Open Playground

Compare GPT OSS 120b

Frequently Asked Questions

All OpenAI Models

See pricing for all OpenAI models.

View all OpenAI models →