Skip to content

gpt-oss-20b

text → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.036

at AkashML

Input / output
$0.018 / $0.09
Providers
10
Spread
5.8×
7 days
+60.0%
30 days
0%
Context
128K
Prices per 1M tokens, blended: AkashML $0.036, Darkbloom $0.036, DeepInfra (bf16/flex) $0.046, CoreWeave $0.055, DekaLLM $0.0568, DeepInfra $0.0575, Parasail $0.06, SiliconFlow $0.075, Amazon Bedrock $0.09, Amazon Bedrock (eu-west-1) $0.09, Groq $0.131, PrimeIntellect $0.209.

Providers

  • AkashMLCheapest
    $0.036
    $0.018 in · $0.09 out
    ref vs ref
    128K ctx100% uptimefp4
  • $0.036
    $0.018 in · $0.09 out
    ref vs ref
    128K ctx100% uptimefp8
  • bf16/flex
    $0.046
    $0.024 in · $0.112 out
    +28% vs ref
    128K ctx98.7% uptimebf16
  • $0.055
    $0.03 in · $0.13 out
    +53% vs ref
    128K ctx99.7% uptimefp4
  • $0.0568
    $0.029 in · $0.14 out
    +58% vs ref
    128K ctx94.5% uptimebf16
  • $0.0575
    $0.03 in · $0.14 out
    +60% vs ref
    128K ctx99.9% uptimebf16
  • $0.06
    $0.03 in · $0.15 out
    +67% vs ref
    128K ctx99.8% uptimefp4
  • $0.075
    $0.04 in · $0.18 out
    +108% vs ref
    128K ctx89.1% uptimefp8
  • $0.09
    $0.07 in · $0.15 out
    +150% vs ref
    128K ctx99.9% uptime
  • $0.09
    $0.07 in · $0.15 out
    +150% vs ref
    128K ctx99.9% uptime
  • $0.131
    $0.075 in · $0.30 out
    +265% vs ref
    128K ctx100% uptime
  • $0.209
    $0.186 in · $0.278 out
    +481% vs ref
    128K ctx99.9% uptimefp4
Blended = (3 × input + output) / 4. Ref $0.036 = median of cheapest 20%.

Price history

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

Prices in USD / 1M tokens.

Other pricing

Offered byCache read
AkashML, Darkbloom$0.009
DeepInfra (bf16/flex)$0.012
CoreWeave$0.03
DekaLLM$0.029
DeepInfra$0.015
Parasail$0.02
Groq$0.0375
PrimeIntellect$0.167

Changes

About

The cheapest provider for gpt-oss-20b is AkashML at $0.036 per 1M tokens (blended), charging $0.018 per 1M input and $0.09 per 1M output tokens. 10 providers serve it; the most expensive charges 5.8× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

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