GPT OSS 20b API Pricing 2026

Compare pricing, benchmarks, and providers for GPT OSS 20b. Find the best value for your use case.

Best LLMs for OpenClaw— Vote for which model works best with OpenClaw

101 out of our 303 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Last updated: February 7, 2026 at 08:06 AM

Overview

GPT OSS 20b was released on August 5, 2025. Pricing starts at $0.030 per million input tokens and $0.140 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$0.030

Output$0.140

per 1M tokens

Speed

Output266 tok/s

TTFT0.49s

median latency

Capabilities

Text only

Pricing Comparison

Compare GPT OSS 20b 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-20b	$0.030	$0.140	77.7	74.8	68.8	131,072	Try in Playground
IB Ibm-granite	Granite 4.0 Micro	$0.017	$0.110	—	—	—	131,000	Try in Playground
G Google	Gemma 3 4B	$0.017	$0.068	11.2	41.7	29.1	96,000	Try in Playground
MI Nousresearch	DeepHermes 3 Mistral 24B Preview	$0.020	$0.100	19.5	58.0	38.2	32,768	Try in Playground
G Google	Gemma 3n 4B	$0.020	$0.040	14.6	48.8	29.6	32,768	Try in Playground
M Meta-llama	Llama Guard 3 8B	$0.020	$0.060	—	—	—	131,072	Try in Playground
M Meta-llama	Llama 3.2 3B Instruct	$0.020	$0.020	8.3	34.7	25.5	131,072	Try in Playground
M Meta-llama	Llama 3.1 8B Instruct	$0.020	$0.050	11.6	47.6	25.9	16,384	Try in Playground
MI Mistral AI	Mistral Nemo	$0.020	$0.040	—	26.4	8.7	131,072	Try in Playground
M Meta-llama	Llama 3.2 1B Instruct	$0.027	$0.200	1.9	20.0	19.6	60,000	Try in Playground
MI Mistral AI	Mistral Small 3.1 24B	$0.030	$0.110	21.2	65.9	45.4	131,072	Try in Playground

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

Compare Providers

GPT OSS 20b is available from multiple providers with different pricing and availability.

Providers

$0.030

Cheapest Input/M

$0.140

Cheapest Output/M

DeepInfra

Best Price

Provider Pricing

13 models

Provider	Input $/M	Output $/M	Uptime
D DeepInfra Best Price	$0.030	$0.140	100.0%
P Parasail	$0.040	$0.200	-
C Chutes	$0.040	$0.150	98.5%
N Novita	$0.040	$0.150	99.5%
C Clarifai	$0.045	$0.180	98.3%
T Together	$0.050	$0.200	99.0%
W WandB	$0.050	$0.200	-
N Nebius	$0.050	$0.200	-
Amazon Bedrock	$0.070	$0.150	100.0%
F Fireworks	$0.070	$0.300	100.0%
Google	$0.070	$0.250	100.0%
Groq	$0.075	$0.300	100.0%
N NextBit	$0.100	$0.450	-

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

Compare GPT OSS 20b's benchmark performance against all models.

X-axis:

Y-axis:

Loading chart...

GPT-OSS-20b

Other models

Detailed Benchmark Scores

Intelligence

24.5 (60th pct)

Coding

18.5 (54th pct)

Math

89.3 (85th pct)

MMLU Pro

74.8 (44th pct)

GPQA

68.8 (62th pct)

LiveCodeBench

77.7 (84th pct)

AIME

Aider

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try GPT OSS 20b

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test GPT OSS 20b directly in your browser.

Open Playground

Compare GPT OSS 20b

Frequently Asked Questions

All OpenAI Models

See pricing for all OpenAI models.

View all OpenAI models →