← model directory

openai

OpenAI: gpt-oss-20b

openai/gpt-oss-20b

↓ runs free on your own hardware⚙ tool calling

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...

specs & pricing
Type
text
Provider
openai
Model ID
openai/gpt-oss-20b
Capabilities
tools, reasoning
Context window
131K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.033 / 1M tokens
Output price
$0.14 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$0.18

$0.033 for a million input tokens plus $0.14 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

Run it on your own hardware

Estimated GPU memory for OpenAI: gpt-oss-20b (22B parameters), including the KV cache for a 8,192-token context.

Q4_K_M
~13.2 GBfits a 16 GB card
Q8_0
~22.2 GBfits a 24 GB card
FP16 / BF16
~41.0 GBfits a 48 GB card

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

/// initialize

Call OpenAI: gpt-oss-20b through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of OpenAI: gpt-oss-20b?
OpenAI: gpt-oss-20b accepts up to 131,072 tokens (131K) of context per request.
How much does OpenAI: gpt-oss-20b cost per million tokens?
Through Wide Area Intelligence, OpenAI: gpt-oss-20b costs $0.033 per 1M input tokens and $0.14 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $0.18.
Can I run OpenAI: gpt-oss-20b on my own hardware?
Yes — OpenAI: gpt-oss-20b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 13.2 GB of GPU memory with an 8,192-token context — it fits a single 16 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from openai

← browse all models