OpenAI • Flagship Multimodal

GPT-4o API Pricing & Cost Calculator

Best suited for: Complex multi-step customer facing workflows, vision + JSON structured outputs. Standard input costs $2.500 per 1M tokens ($1.250 with prompt caching) and output costs $10.00 per 1M tokens.

Deploy GPT-4o on OpenAI →
Standard Input / 1M
$2.500
Cached Input / 1M
$1.250
Output Tokens / 1M
$10.00
Context Window
128,000 tok
Throughput Speed
85 tok/s
Est. 5k Req/Day Spend
$1303.12/mo

Token Volume Cost Conversion Table (GPT-4o)

Token Volume Approx. English Words Un-cached Input Cost Cached Input Cost Output Generation Cost
10,000 tokens~7,500 words$0.0250$0.0125$0.1000
100,000 tokens~75,000 words$0.2500$0.1250$1.0000
1,000,000 tokens~750,000 words$2.5000$1.2500$10.0000
10,000,000 tokens~7,500,000 words$25.0000$12.5000$100.0000
100,000,000 tokens~75,000,000 words$250.0000$125.0000$1000.0000

Compare GPT-4o Against Other Frontier APIs

GPT-4o vs GPT-4o miniCompare pricing, caching & speed GPT-4o vs OpenAI o3-miniCompare pricing, caching & speed GPT-4o vs Claude 3.7 SonnetCompare pricing, caching & speed GPT-4o vs Claude 3.5 HaikuCompare pricing, caching & speed GPT-4o vs Gemini 2.5 ProCompare pricing, caching & speed GPT-4o vs Gemini 2.5 FlashCompare pricing, caching & speed GPT-4o vs Gemini 2.0 Flash-LiteCompare pricing, caching & speed GPT-4o vs DeepSeek-V3 (Chat)Compare pricing, caching & speed GPT-4o vs DeepSeek-R1 (Reasoner)Compare pricing, caching & speed GPT-4o vs Llama 3.3 70B Versatile (Groq)Compare pricing, caching & speed GPT-4o vs Llama 3.1 8B Instant (Groq)Compare pricing, caching & speed GPT-4o vs Qwen 2.5 Coder 32B (Together AI)Compare pricing, caching & speed GPT-4o vs DeepSeek R1 Fast (Fireworks AI)Compare pricing, caching & speed GPT-4o vs Mistral Large 2Compare pricing, caching & speed GPT-4o vs Mistral Small 3Compare pricing, caching & speed GPT-4o vs Perplexity Sonar ProCompare pricing, caching & speed GPT-4o vs Cohere Command R+Compare pricing, caching & speed