OpenAI: gpt-oss-20b

OpenAI: gpt-oss-20b is a large language model from OpenAI. It costs $0.018 per million input tokens and $0.090 per million output tokens. Its context window is 131K tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weights

Input / 1M tokens: $0.018
Output / 1M tokens: $0.090
Cached input / 1M: $0.0090
Context window: 131K

Who serves it cheapest

10 hosts serve gpt-oss-20b. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: gpt-oss-20b, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
DarkbloomCheapestfp8	$0.018	$0.090	131K	-	95.0%
AkashMLfp4	$0.020	$0.100	131K	-	100.0%
CoreWeavefp4	$0.030	$0.130	131K	-	100.0%
DekaLLMbf16	$0.029	$0.140	131K	-	100.0%
DeepInfrabf16	$0.030	$0.140	131K	-	99.7%
Parasailfp4	$0.030	$0.150	131K	-	99.9%
SiliconFlowfp8	$0.040	$0.180	131K	-	89.2%
Amazon Bedrock	$0.070	$0.150	131K	-	100.0%
Google	$0.070	$0.250	131K	-	99.0%
Groq	$0.075	$0.300	131K	-	99.9%

The spread between Darkbloom and Groq is 3.6× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index: 10.0

About gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Specifications

OpenAI: gpt-oss-20b specifications
Model ID	`openai/gpt-oss-20b`
Provider	OpenAI
Context window	131K tokens
Max output	33K tokens
Input modalities	text
Output modalities	text
Knowledge cutoff	2024-06-30
Open weights	Yes - openai/gpt-oss-20b
Released	August 5, 2025

Cheaper alternatives

Models that cost less than gpt-oss-20b while keeping at least half its context window and every input modality it supports.

Ling 3.0 Flash

$0.021 in · $0.063 out

1.1× cheaper

Summarize

$0.040 in · Free out

1.2× cheaper

Extract

$0.040 in · Free out

1.2× cheaper

Mistral Nemo

$0.029 in · $0.030 out

1.2× cheaper

Dots3-Note Preview (free)

Free in · Free out

Frequently asked

How much does OpenAI: gpt-oss-20b cost?

$0.018 per million input tokens and $0.090 per million output tokens. Cached input reads cost $0.0090 per million tokens.

What is the context window of OpenAI: gpt-oss-20b?

131K tokens, with up to 33K tokens of output per request.

Which provider serves OpenAI: gpt-oss-20b cheapest?

Darkbloom at $0.018 per million input tokens - 3.6× cheaper than Groq, the most expensive of the 10 hosts serving it.

Confirm against the source: OpenAI official pricing.