Skip to content

Model vendor

OpenAI models: API pricing and providers

37 OpenAI models with OpenAI's published list rates and the providers that serve each one. You call them through INFRO on a provider account you connect; that account bills you, and INFRO adds 0% to model spend.

Rates checked 2026-10-05.

OpenAI models

ModelModalityList rateProviders
GPT-6 Astra
openai/gpt-6-astra
Frontier reasoning
Text$10 per 1M input tokens and $50 per 1M output tokens, with cached input at $1.00 per 1M tokens6
GPT-6 Sol
openai/gpt-6-sol
Everyday reasoning
Text$2.00 per 1M input tokens and $10 per 1M output tokens, with cached input at $0.20 per 1M tokens6
GPT-6 Luna
openai/gpt-6-luna
High-volume execution
Text$0.10 per 1M input tokens and $0.50 per 1M output tokens, with cached input at $0.01 per 1M tokens6
GPT-5.6 Sol
openai/gpt-5.6-sol
Frontier reasoning
Text$4.00 per 1M input tokens and $20 per 1M output tokens, with cached input at $0.40 per 1M tokens6
GPT-5.6 Terra
openai/gpt-5.6-terra
Everyday reasoning
Text$2.00 per 1M input tokens and $12 per 1M output tokens, with cached input at $0.20 per 1M tokens6
GPT-5.6 Luna
openai/gpt-5.6-luna
High-volume execution
Text$0.20 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.02 per 1M tokens6
gpt-oss-120b
openai/gpt-oss-120b
Open-weight reasoning
Text$0.15 per 1M input tokens and $0.60 per 1M output tokens9
GPT-6 Luna (Decisions)
openai/gpt-6-luna-decisions
Structured decisions
Text$0.10 per 1M input tokens and output tokens free, with cached input at $0.01 per 1M tokens3
GPT-6.1 Sol
openai/gpt-6.1-sol
Near-Astra reasoning and agentic coding
Text$2.00 per 1M input tokens and $10 per 1M output tokens, with cached input at $0.10 per 1M tokens3
GPT-5.5
openai/gpt-5.5
Previous-generation flagship
Text$5.00 per 1M input tokens and $30 per 1M output tokens, with cached input at $0.50 per 1M tokens3
GPT-5.5 Pro
openai/gpt-5.5-pro
High-compute reasoning
Text$30 per 1M input tokens and $180 per 1M output tokens3
GPT-5.4
openai/gpt-5.4
Previous-generation general model
Text$2.50 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.25 per 1M tokens3
GPT-5.4 mini
openai/gpt-5.4-mini
Small fast general model
Text$0.75 per 1M input tokens and $4.50 per 1M output tokens, with cached input at $0.075 per 1M tokens3
GPT-5.4 nano
openai/gpt-5.4-nano
Smallest low-cost model
Text$0.20 per 1M input tokens and $1.25 per 1M output tokens, with cached input at $0.02 per 1M tokens3
GPT-5.4 Pro
openai/gpt-5.4-pro
High-compute reasoning
Text$30 per 1M input tokens and $180 per 1M output tokens3
GPT-5.3 Codex
openai/gpt-5.3-codex
Agentic coding
Text$1.75 per 1M input tokens and $14 per 1M output tokens, with cached input at $0.175 per 1M tokens3
o3
openai/o3
Reasoning
Text$2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.50 per 1M tokens3
o3-pro
openai/o3-pro
High-compute reasoning
Text$20 per 1M input tokens and $80 per 1M output tokens3
GPT-4.1
openai/gpt-4.1
Non-reasoning general model
Text$2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.50 per 1M tokens3
GPT-4.1 mini
openai/gpt-4.1-mini
Non-reasoning small model
Text$0.40 per 1M input tokens and $1.60 per 1M output tokens, with cached input at $0.10 per 1M tokens3
GPT-4o
openai/gpt-4o
Legacy multimodal chat
Text$2.50 per 1M input tokens and $10 per 1M output tokens, with cached input at $1.25 per 1M tokens3
GPT-4o mini
openai/gpt-4o-mini
Legacy small multimodal chat
Text$0.15 per 1M input tokens and $0.60 per 1M output tokens, with cached input at $0.075 per 1M tokens3
gpt-oss-20b
openai/gpt-oss-20b
Small open-weight reasoning model
Text$0.075 per 1M input tokens and $0.30 per 1M output tokens4
GPT Image 2
openai/gpt-image-2
Image generation & editing
Image$0.053 per image8
GPT Image 2.5 Sunburst
openai/gpt-image-2.5-sunburst
Image generation & editing
Image$0.013 per image7
GPT Image 2.5 Flare
openai/gpt-image-2.5-flare
Fast image generation & editing
Image$0.013 per image7
GPT Image 1.5
openai/gpt-image-1.5
Image generation & editing
Image$0.034 per image6
GPT Image 1 Mini
openai/gpt-image-1-mini
Low-cost image generation
Image$0.011 per image5
GPT Image 1
openai/gpt-image-1
Image generation & editing
Image$0.042 per image5
Whisper v3 Turbo
openai/whisper-v3-turbo
Transcription
Audio$0.04 per audio hour2
TTS-1
openai/tts-1
Text-to-speech, speed-optimized
Audio$15 per 1M characters3
TTS-1 HD
openai/tts-1-hd
Text-to-speech, quality-optimized
Audio$30 per 1M characters3
GPT-Transcribe
openai/gpt-transcribe
Speech-to-text
Audio$0.27 per audio hour3
Whisper Large v3
openai/whisper-large-v3
Speech-to-text
Audio$0.09 per audio hour3
Whisper
openai/whisper-1
Speech-to-text with timestamps
Audio$0.36 per audio hour4
GPT-4o Transcribe
openai/gpt-4o-transcribe
Speech-to-text
Audio$0.36 per audio hour4
GPT-4o mini Transcribe
openai/gpt-4o-mini-transcribe
Speech-to-text
Audio$0.18 per audio hour4

OpenAI models: questions

Which OpenAI models does this reference list?
37 OpenAI models: 23 text, 6 image and 8 audio. Each has its own page with OpenAI's list rate and the providers that serve it.
Which providers serve OpenAI models?
OpenAI, Azure OpenAI, AWS Bedrock, OpenRouter, KIE, LaoZhang API, Groq, Together AI and 4 more. You connect your own account with any of them; INFRO routes between the ones you connect.
What is the lowest OpenAI input rate listed?
gpt-oss-20b, at $0.075 per 1M input tokens and $0.30 per 1M output tokens on OpenAI's list (checked 2026-10-05).
Does INFRO add a markup to OpenAI model usage?
No. Your OpenAI or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.

Other model vendors

Search and filter every model