The Orchestrator › Models › OpenAI

OpenAI: GPT-4o

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...

Specifications

ProviderOpenAI
Model IDopenai/gpt-4o
Context window128K tokens (128,000)
Modalitiestext + image + file → text
TokenizerGPT
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2024-05-13
Tracked since2026-11-14
PopularityNot in the ranked set
Reasoning—

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteropenai/gpt-4o$2.50$10.00128K
batchOpenRouteropenai/gpt-4o:batch$1.25$5.00128K
standardTrustedRouteropenai/gpt-4o$2.64$10.55128K
standardVercel AI Gatewayopenai/gpt-4o$2.50$10.00128K
fastVercel AI Gatewayopenai/gpt-4o:fast$4.25$17.00128K
batchVercel AI Gatewayopenai/gpt-4o:batch$1.25$5.00128K
standardCloudflareopenai/gpt-4o$1.25$5.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$1.25$5.00—
2026-11-14$2.50$10.00128K
2026-11-14$2.64$10.55128K
2026-11-14$2.50$10.00128K

Capabilities

Vision (image input)File inputAgentic tool useStructured outputsNo content storage (attested)Zero data retentionNo training on inputs (attested)

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

Supported parameters

frequency_penalty, logit_bias, logprobs, max_completion_tokens, max_tokens, prediction, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p, web_search_options