The Orchestrator › Models › OpenAI

OpenAI: GPT-5.4

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

Specifications

ProviderOpenAI
Model IDopenai/gpt-5.4
Context window1.1M tokens (1,050,000)
Modalitiestext + image + file → text
TokenizerGPT
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-03-05
Tracked since2026-11-14
PopularityNot in the ranked set
ReasoningSupported

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteropenai/gpt-5.4$2.50$15.001.1M
batchOpenRouteropenai/gpt-5.4:batch$1.25$7.501.1M
standardTrustedRouteropenai/gpt-5.4$2.64$15.821.1M
standardVercel AI Gatewayopenai/gpt-5.4$2.50$15.001.1M
fastVercel AI Gatewayopenai/gpt-5.4:fast$5.00$30.001.1M
batchVercel AI Gatewayopenai/gpt-5.4:batch$1.25$7.501.1M
standardCloudflareopenai/gpt-5.4$2.50$15.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$2.50$15.00—
2026-11-14$2.50$15.001.1M
2026-11-14$2.64$15.821.1M
2026-11-14$2.50$15.001.1M

Capabilities

Vision (image input)File inputAgentic tool useStructured outputs1M+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)

Trust flags come from TrustedRouter's per-provider attestations.

Supported parameters

include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools, verbosity