The Orchestrator › Models › OpenAI

OpenAI: GPT-4o-mini

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Specifications

ProviderOpenAI
Model IDopenai/gpt-4o-mini
Context window128K tokens (128,000)
Modalitiestext + image + file → text
TokenizerGPT
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2024-07-18
Tracked since2026-11-14
PopularityNot in the ranked set
Reasoning—

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteropenai/gpt-4o-mini$0.15$0.6128K
batchOpenRouteropenai/gpt-4o-mini:batch$0.075$0.3128K
standardTrustedRouteropenai/gpt-4o-mini$0.158$0.633128K
standardVercel AI Gatewayopenai/gpt-4o-mini$0.15$0.6128K
fastVercel AI Gatewayopenai/gpt-4o-mini:fast$0.25$1.00128K
batchVercel AI Gatewayopenai/gpt-4o-mini:batch$0.075$0.3128K
standardCloudflareopenai/gpt-4o-mini$0.075$0.3—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$0.075$0.3—
2026-11-14$0.15$0.6128K
2026-11-14$0.158$0.633128K
2026-11-14$0.15$0.6128K

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