gpt-oss-20b

openai/gpt-oss-20b

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...

InputText
OutputText
Input / Outputclub$0.0742 / $0.159per 1M tokens · USD
Context window131.1Ktoken
Maximum output118Ktoken

Pricing

Current model usage rates. Choose your plan to see its published prices.

Pricing
UsagePricing
InputUS$0.0742/ 1M token
OutputUS$0.159/ 1M token

Membership and model usage are billed separately. Compare plans

Capabilities

Input
Text
Output
Text
Context window
131,072 token
Maximum output
117,964 token
Reasoning
high · medium · low

Providers

Model supply available through Vecbase.

Via OpenRouter

Access is subject to your account’s permissions and model availability.

Frequently asked questions

What is gpt-oss-20b, and who develops it?

gpt-oss-20b is a model from OpenAI. Its model ID on Vecbase is openai/gpt-oss-20b. 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...

How much does gpt-oss-20b cost on Vecbase?

For gpt-oss-20b, the Club plan lists USD 0.0742 per 1 million input tokens and USD 0.159 per 1 million output tokens, as of 10/22/2026, 9:26:00 PM UTC. See the pricing table for cache rates, input-length tiers and other usage types. Membership fees are separate.

How many tokens fit in gpt-oss-20b’s context window?

gpt-oss-20b has a context window of 131,072 tokens. Input and output must fit within the limits of the API you use.

What is the maximum output length for gpt-oss-20b?

gpt-oss-20b can generate up to 117,964 tokens per response. Your API or request settings may set a lower limit.

Can gpt-oss-20b call tools in an agent workflow?

Yes. gpt-oss-20b supports tool calling. Your application provides the tool definitions and runs the tools the model requests.

Does gpt-oss-20b support structured outputs?

Yes. gpt-oss-20b supports structured output. Set the required format in your API request and check the returned data before using it.

Which input and output formats does gpt-oss-20b support?

gpt-oss-20b accepts Text and produces Text.

Which providers make gpt-oss-20b available through Vecbase?

Vecbase offers gpt-oss-20b through OpenRouter. Availability may vary by provider.

Which model ID should an agent use to request gpt-oss-20b?

Use openai/gpt-oss-20b as the model identifier for gpt-oss-20b. See Vecbase’s API documentation for authentication, required inputs and supported request formats.

Which reasoning settings are listed for gpt-oss-20b?

gpt-oss-20b supports these reasoning levels: high, medium, and low. Available options depend on your API.

What does an agent need to access gpt-oss-20b through Vecbase?

To use gpt-oss-20b, you need an authenticated account with the required permissions, sufficient balance and the relevant capability enabled. See the documentation for setup.

Is a release date available for gpt-oss-20b?

We do not yet have a confirmed release date for gpt-oss-20b.

Which models can I compare with gpt-oss-20b on Vecbase?

You can compare gpt-oss-20b with GPT Mini Latest (openai/gpt-mini-latest), GPT-5.5 (openai/gpt-5.5), and GPT-5.6 Luna (openai/gpt-5.6-luna). Check their capabilities and prices to find the best fit for your task.