Ways to buy 2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 OpenAI APIThe lab's own API · cached $1.25 | $2.5 | $10 | $2.5 / $10List price | $1.25 | List price |
 Azure AI FoundryDefault region | $2.5 | $10 | $2.5 / $10Same as list | n/a | Same as list |
USD per 1M tokens; batch $1.25 in, $5 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $450.00 direct.
Helicone$450.00+0%
Kong AI Gateway$450.00+0%
LiteLLM$450.00+0%
Vercel AI Gateway$450.00+0%
Cloudflare AI Gateway$472.50+5%
Requesty$472.50+5%
Eden AI$474.75+5.5%
OpenRouter$474.75+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| GPT-6 Luna OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Luna Pro OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Sol OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
| GPT-6 Sol Pro OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
 Claude Opus 5.5Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · |
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Gemini 3.1 Pro PreviewGoogle · 1MCheapest: $2.25 on Google Vertex AI (global-flex) | $2 | $12 | $2 / $12 | $4.5 | 1M | $2.25 on Google Vertex AI (global-flex) | · |
| Muse Spark 1.1 Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
About GPT-4o
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.
Takes text, image, files in and returns text. First listed Jun 19, 2024. Up to 16K output tokens. Blended price $4.38 per 1M tokens at 3 input to 1 output. Model id gpt-4o.
Price history
List price since Jun 19, 2024, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
| Seen | Model | Old price | New price | Change |
|---|---|---|---|---|
| Apr 10, 2025 | GPT-4oCached input Free to $1.25 | Cached input Free | Cached input $1.25 | |
| Oct 6, 2024 | GPT-4oInput $5 to $2.5, Output $15 to $10 | Input $5Output $15 | Input $2.5Output $10 | -50% |
Questions
How much does GPT-4o cost?
$2.5 per million input tokens and $10 per million output tokens, with cached input at $1.25, or $1.25 and $5 through the Batch API.
What is the context window of GPT-4o?
128K tokens, with up to 16K tokens of output.
Where is GPT-4o cheapest?
Of 2 routes tracked, Azure AI Foundry is cheapest at $2.5 input and $10 output per million tokens.
Has GPT-4o's price changed?
Yes. The output price went from $15 to $10, first seen Oct 6, 2024.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.