What is the cheapest gpt-oss-20b API provider?

Darkbloom is the cheapest healthy provider we track at $0.018 per 1M input tokens and $0.09 per 1M output tokens.

How much does gpt-oss-20b cost?

Across 8 providers, input prices range from $0.018 to $0.075 per 1M tokens and output prices from $0.09 to $0.30.

What is gpt-oss-20b’s context window?

gpt-oss-20b supports up to 131K tokens, but some providers serve a smaller context window — check the table before choosing.

OpenAI · open weights

gpt-oss-20b API pricing by provider

gpt-oss-20b is available from 8 providers. The cheapest is Darkbloom at $0.018 input / $0.09 output per 1M tokens (FP8). The priciest host, Groq, charges 3.6x the cheapest.

Prices from the OpenRouter API, retrieved October 26, 2026. Weights: openai/gpt-oss-20b.

Provider	Precision	Input / 1M	Output / 1M	Document Q&A / month	Context	Max output
Darkbloom	fp8	$0.018	$0.09	$9.90	131K	33K
AkashML	fp4	$0.02	$0.10	$11.00	131K	118K
CoreWeave	fp4	$0.03	$0.13	$15.90	131K	118K
DekaLLM	bf16	$0.029	$0.14	$15.80	131K	118K
DeepInfra	bf16	$0.03	$0.14	$16.20	131K	118K
Parasail	fp4	$0.03	$0.15	$16.50	131K	118K
Amazon Bedrock	—	$0.07	$0.15	$32.50	131K	118K
Groq	—	$0.075	$0.30	$39.00	131K	66K

Sorted by blended price (3 input : 1 output). Document Q&A assumes 50,000 questions a month with 8,000 input and 600 output tokens each. Precision is reported by the provider; “—” means not disclosed.

Frequently asked questions

What is the cheapest gpt-oss-20b API provider?: Darkbloom is the cheapest healthy provider we track at $0.018 per 1M input tokens and $0.09 per 1M output tokens.
How much does gpt-oss-20b cost?: Across 8 providers, input prices range from $0.018 to $0.075 per 1M tokens and output prices from $0.09 to $0.30.
What is gpt-oss-20b’s context window?: gpt-oss-20b supports up to 131K tokens, but some providers serve a smaller context window — check the table before choosing.

Frequently asked questions

Other open-weight models