Model Markets
Get Free API KeyAPI

OpenAI · Gpt Oss · active

gpt-oss-20b

gpt-oss-20b is an open-weight language model published by OpenAI.

openai/gpt-oss-20b
Statusactive
InputText
OutputText
Context128K
Total / active parameters20.9B / 3.6B
Licenseapache-2.0
APIYes
Open weights / self-hostYes / Yes

Provider availability

Serving endpoints and pricing

ProviderRoute modelTierInputOutputRegionObservedSource
openai/gpt-oss-20bStandard$0.030$0.14UnknownAug 28, 2026Provider-reported
openai/gpt-oss-20bStandard$0.075$0.30UnknownAug 28, 2026Provider-reported
openai/gpt-oss-20bStandard routing$0.030$0.13UnknownAug 28, 2026Provider-reported
openai/gpt-oss-20bServerless$0.050$0.20UnknownAug 28, 2026Provider-reported

This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.

Technical specification

Developer model IDopenai/gpt-oss-20b
Versiongpt-oss-20b
ReleasedNot reported
ArchitectureGptOssForCausalLM
Maximum outputUnknown
Knowledge cutoffNot reported

Capabilities

chatgenerationreasoningtools
ReasoningYes
VisionNo
Tool callingYes

Version lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesopenai/gpt-oss-20b, openai/gpt-oss-20b

Explicit unknowns

  • Release date
  • Maximum output
  • Knowledge cutoff

Comparable peers

Related model comparisons

All comparisons →
gpt-oss-20bvs gpt-oss-120bOpenAI · textgpt-oss-20bvs GPT-5.6 LunaOpenAI · textgpt-oss-20bvs GPT-5.6 SolOpenAI · textgpt-oss-20bvs GPT-5.6 TerraOpenAI · textgpt-oss-20bvs Ministral-3-14B-Reasoning-2512Mistral AI · textgpt-oss-20bvs NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA · textgpt-oss-20bvs granite-4.1-30bIBM · textgpt-oss-20bvs Olmo-3-32B-ThinkAi2 · textgpt-oss-20bvs Olmo-3.1-32B-InstructAi2 · textgpt-oss-20bvs Phi-4-mini-reasoningMicrosoft · textgpt-oss-20bvs Phi-4-reasoningMicrosoft · textgpt-oss-20bvs Olmo-3-7B-ThinkAi2 · text

Questions

gpt-oss-20b FAQs

What is gpt-oss-20b?+

gpt-oss-20b is an open-weight language model published by OpenAI. It is developed by OpenAI and its current sourced lifecycle status is active.

What inputs and outputs does gpt-oss-20b support?+

gpt-oss-20b's current record lists Text as input and Text as output.

How much context does gpt-oss-20b support?+

The current record lists a 131,072-token context window and does not report a maximum output length.

Is gpt-oss-20b available through an API?+

gpt-oss-20b is marked as API-available. The directly sourced provider records currently include DeepInfra, Groq, OpenRouter, and Together AI.

How large is gpt-oss-20b?+

The current record lists 20.9B total parameters and 3.6B active parameters. Its architecture is GptOssForCausalLM.

What capabilities and tasks does gpt-oss-20b support?+

gpt-oss-20b's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are text.

Can gpt-oss-20b be self-hosted?+

gpt-oss-20b is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.

Does gpt-oss-20b have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are openai/gpt-oss-20b.

Which models can gpt-oss-20b be compared with?+

The current compatible peer set includes gpt-oss-120b, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, and Ministral-3-14B-Reasoning-2512. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →

How current is the Model Markets record for gpt-oss-20b?+

gpt-oss-20b was last verified Aug 28, 2026 from OpenAI's primary source, “openai/gpt-oss-20b developer model repository.” The evidence is classified as official fact.

Primary evidence

Sources and observation date

openai/gpt-oss-20b developer model repositoryOpenAI · observed Aug 28, 2026