GPT OSS 20B

by OpenAIChatretires 2026-10-21

Open-weight GPT model for self-hosted reasoning and instruction-following workloads

Context
131K tokens
Max output
32,768 tokens
Released
2025-08-05
Weights
Open

openai/gpt-oss-20b-maas · also seen as vertex_ai/openai/gpt-oss-20b-maas

Specifications

Full facts as recorded, incl. what is unknown.

Released
2025-08-05
Weights
Open
Input
Text
Output
Text
Context window
131,072 max across endpoints
Max output
32,768
Providers
1
Epoch Capabilities Index
not evaluated
Direct price range
no comparable direct price
More details
Last updated
2025-08-05
Knowledge cutoff

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured output
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from OpenAI

Newest OpenAI models in the catalogue. All OpenAI models

ModelReleasedContextListed price
GPT-6.1 Sol Ultrafast2026-10-081.05Mfrom $12
GPT-6 Luna Decisions2026-10-061.05Munpriced
GPT-6.1 Sol2026-09-291.05Mfrom $2.00
GPT-6.1 Sol Pro2026-09-291.05Mfrom $2.00
GPT-6 Luna2026-09-221.05Mfrom $0.10
GPT-6 Sol2026-09-221.05Mfrom $2.00
GPT-6 Sol Pro2026-09-221.05Mfrom $2.00
GPT-6 Luna Pro2026-09-221.05Mfrom $0.10
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model