OpenAITool use

gpt-oss-20b pricing

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 lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs. This page tracks 9 listings in total. Highlighted lows are $0.020 per million input and $0.100 per million output (see table for which seller matches each).

131K context·9 providers·verified May 2, 2026
Best input$0.020per 1M tokens · Openrouter
Best output$0.100per 1M tokens · Openrouter

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 9 offers are listed for gpt-oss-20b. Best input in this view: Openrouter.

O
Openrouter
Input / 1M
$0.020
Output / 1M
$0.100
W
Wandb
Input / 1M
$5000.00
Output / 1M
$20000.00
O
Ovhcloud
Input / 1M
$0.040
Output / 1M
$0.150
N
Novita
Input / 1M
$0.040
Output / 1M
$0.150
D
DeepInfra
Input / 1M
$0.040
Output / 1M
$0.150
R
Replicate
Input / 1M
$0.090
Output / 1M
$0.360
FA
Fireworks AI
Input / 1M
$0.050
Output / 1M
$0.200
TA
Together AI
Input / 1M
$0.050
Output / 1M
$0.200
G
Groq
Input / 1M
$0.075
Output / 1M
$0.300
Cached in: $0.037

Input vs output · per provider

Cost calculator

Use this block to stress test gpt-oss-20b cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.020/M·Out: $0.100/M

0.002000¢ / req

0.005000¢ / req

Daily
$0.70
Monthly
$21
Annual
$255

Model specifications

These fields describe gpt-oss-20b as we store it (source: OpenAI). They sit next to price so buyers can check limits and tools in one place.

Context window
131,072 tokens
Max output
131,072 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Aug 2025
Primary provider
OpenAI
Model family
N/A

Compare gpt-oss-20b

Open a pair page to see gpt-oss-20b next to another model with a shared provider matrix. 6 shortcuts below.

Frequently asked questions

Answers pull from the same numbers you see on this page. The short model note from our index: 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 lower-latency...

Yes. gpt-oss-20b is available on Openrouter, Wandb, Ovhcloud, Novita, DeepInfra, Replicate, Fireworks AI, Together AI, Groq.

Also from OpenAI

Other models by OpenAI with live pricing in our catalog.