gpt-oss-20b (batch)

OpenAItext → textHugging Face OpenRouter

The cheapest provider for gpt-oss-20b (batch) is Darkbloom at $0.036 per 1M tokens (blended), charging $0.018 per 1M input and $0.09 per 1M output tokens. 11 providers serve it; the most expensive charges 3.6× as much. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

Best price

$0.036

at Darkbloom

Input / output

$0.018 / $0.09

per 1M tokens

Providers

3.6× spread

7 days

—

best price

30 days

—

best price

Context

128K

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for OpenAI: gpt-oss-20b (batch), USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
DarkbloomCheapest fp8	$0.018	$0.09	$0.036	best	128K	99.8%	Oct 3
AkashML fp4	$0.02	$0.10	$0.04	+11%	128K	99.5%	Oct 3
CoreWeave fp4	$0.03	$0.13	$0.055	+53%	128K	100%	Oct 3
DekaLLM bf16	$0.029	$0.14	$0.0568	+58%	128K	99.5%	Oct 3
DeepInfra bf16	$0.03	$0.14	$0.0575	+60%	128K	100%	Oct 3
Parasail fp4	$0.03	$0.15	$0.06	+67%	128K	100%	Oct 3
Novita fp4	$0.04	$0.15	$0.0675	+88%	128K	99.8%	Oct 3
SiliconFlow fp8	$0.04	$0.18	$0.075	+108%	128K	94.2%	Oct 3
Amazon Bedrock	$0.07	$0.15	$0.09	+150%	128K	99.9%	Oct 3
Amazon Bedrockeu-west-1	$0.07	$0.15	$0.09	+150%	128K	100%	Oct 3
Googleus-central1	$0.07	$0.25	$0.115	+219%	128K	98.2%	Oct 3
Groq	$0.075	$0.30	$0.131	+265%	128K	98.0%	Oct 3

DarkbloomCheapest
$0.036
$0.018 in · $0.09 out
best
128K ctx99.8% uptimefp8
AkashML
$0.04
$0.02 in · $0.10 out
+11%
128K ctx99.5% uptimefp4
CoreWeave
$0.055
$0.03 in · $0.13 out
+53%
128K ctx100% uptimefp4
DekaLLM
$0.0568
$0.029 in · $0.14 out
+58%
128K ctx99.5% uptimebf16
DeepInfra
$0.0575
$0.03 in · $0.14 out
+60%
128K ctx100% uptimebf16
Parasail
$0.06
$0.03 in · $0.15 out
+67%
128K ctx100% uptimefp4
Novita
$0.0675
$0.04 in · $0.15 out
+88%
128K ctx99.8% uptimefp4
SiliconFlow
$0.075
$0.04 in · $0.18 out
+108%
128K ctx94.2% uptimefp8
Amazon Bedrock
$0.09
$0.07 in · $0.15 out
+150%
128K ctx99.9% uptime
Amazon Bedrock
eu-west-1
$0.09
$0.07 in · $0.15 out
+150%
128K ctx100% uptime
Google
us-central1
$0.115
$0.07 in · $0.25 out
+219%
128K ctx98.2% uptime
Groq
$0.131
$0.075 in · $0.30 out
+265%
128K ctx98.0% uptime

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
Darkbloom	$0.009
CoreWeave	$0.03
DekaLLM	$0.029
Parasail	$0.02
Groq	$0.0375

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

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...

Released: Aug 5, 2025
First tracked: Oct 3, 2026
Canonical slug: openai/gpt-oss-20b
Weights: openai/gpt-oss-20b