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 12 listings in total. Highlighted lows are $0.015 per million input and $0.070 per million output (see table for which seller matches each).

131K context·12 providers·verified Sep 20, 2026
Best input$0.015per 1M tokens · Darkbloom
Best output$0.070per 1M tokens · Darkbloom

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 12 offers are listed for gpt-oss-20b. Best input in this view: Darkbloom.

C
Cloudflare
Input / 1M
$0.200
Output / 1M
$0.300
D
Darkbloom
Input / 1M
$0.015
Output / 1M
$0.070
D
DeepInfra
Input / 1M
$0.030
Output / 1M
$0.140
FA
Fireworks AI
Input / 1M
$0.070
Output / 1M
$0.300
Cached in: $0.035
G
Groq
Input / 1M
$0.075
Output / 1M
$0.300
Cached in: $0.037
N
Novita
Input / 1M
$0.040
Output / 1M
$0.150
O
Openrouter
Input / 1M
$0.030
Output / 1M
$0.130
Cached in: $0.030
O
Ovhcloud
Input / 1M
$0.040
Output / 1M
$0.150
R
Replicate
Input / 1M
$0.090
Output / 1M
$0.360
T
Tensormesh
Input / 1M
$0.070
Output / 1M
$0.280
Cached in: $0.0000
TA
Together AI
Input / 1M
$0.050
Output / 1M
$0.200
W
Wandb
Input / 1M
$0.030
Output / 1M
$0.130

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: $0.200/M·Out: $0.300/M

0.020000¢ / req

0.015000¢ / req

Daily
$3.50
Monthly
$105
Annual
$1.3K

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.

Locked

Compare with

Pick a model on both sides.

Popular gpt-oss-20b comparisons

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 Cloudflare, Darkbloom, DeepInfra, Fireworks AI, Groq, Novita, Openrouter, Ovhcloud, Replicate, Tensormesh, Together AI, Wandb.

Related models

Models close to gpt-oss-20b by family, provider, and context window — each with live pricing in our catalog.