II.
ModelVersion overview
Reference · livemodel:gpt-5.4-nano@current
GPT-5.4 Nano overview
Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for model:gpt-5.4-nano@current.
Attributes
displayName
GPT-5.4 Nano
supportsExtendedThinking
false
modelFamilyId
versionRange
>=5.4.0 <5.5.0
kind
reasoning
contextWindowTokens
400000
costPerMTokInput
0.2
costPerMTokCachedInput
0.02
costPerMTokOutput
1.25
supportsThinking
true
thinkingEffortLevels
- low
- medium
- high
- xhigh
supportsThinkingBudgetTokens
false
modalities
- text
- image
modalityDirections
- kindtextdirectioninput
- kindimagedirectioninput
- kindtextdirectionoutput
releaseDate
2026-03-17
lifecycleStatus
ga
lifecycleStatusChangedAt
2026-03-17
knowledgeCutoffDate
2025-08-31
safetyTier
openai-preparedness-high
modelCardUrl
supportsFineTuning
false
regions
- global
Outgoing edges
belongs_to_family1
- model-family:gpt-5·ModelFamilyGPT-5
realizes1
- layer:1-model·LayerModel
served_by1
- provider:openai·ModelProviderProductOpenAI
speaks2
- model-transport:openai-responses·ModelTransportProtocolOpenAI Responses
- model-transport:openai-chat-completions·ModelTransportProtocolOpenAI Chat Completions
supports5
- capability:supports-batch-api·CapabilitySupports batch API
- capability:parallel-tool-calls·CapabilityParallel tool calls
- capability:supports-prompt-caching·CapabilitySupports prompt caching
- capability:streaming·CapabilityStreaming
- capability:supports-tool-use·CapabilitySupports tool use
supports_effort_level4
- effort-level:minimal·EffortLevelEffort: minimal
- effort-level:low·EffortLevelEffort: low
- effort-level:medium·EffortLevelEffort: medium
- effort-level:high·EffortLevelEffort: high
version_of1
- model-family:gpt-5·ModelFamilyGPT-5
Incoming edges
about_subject1
serves1
- provider:openai·ModelProviderProductOpenAI