Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-5.4A month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-5.4 | |
|---|---|
| Input per 1M | $2.5 |
| Output per 1M | $15 |
| Cached input | $0.25 |
| Batch in / out | $1.25 / $7.5 |
| Blended (3:1) | $5.63 |
| Context | 1.05M |
| Routes | 9 |
| Released | Mar 5, 2026 |
| Leadersboard score | 2 (#45) |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Every route
GPT-5.4
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI flex, cheapest · cached $0.125 | $1.25 | $7.5 | $1.25 / $7.5-50% vs list | $0.125 | -50% vs list |
| OpenAI API The lab's own API · cached $0.25 | $2.5 | $15 | $2.5 / $15List price | $0.25 | List price |
 Azure AI FoundryDefault region · cached $0.25 | $2.5 | $15 | $2.5 / $15Same as list | $0.25 | Same as list |
 Databricks Mosaic AI Gateway + Foundation Model APIsFrom the platform pricing page | $2.5 | $15 | $2.5 / $15Same as list | n/a | Same as list |
 AWS Bedrockus-east-1 · cached $0.275 | $2.75 | $16.5 | $2.75 / $16.5+10% vs list | $0.275 | +10% vs list |
| Azure AI Foundry eu · cached $0.275 | $2.75 | $16.5 | $2.75 / $16.5+10% vs list | $0.275 | +10% vs list |
| Azure AI Foundry us · cached $0.275 | $2.75 | $16.5 | $2.75 / $16.5+10% vs list | $0.275 | +10% vs list |
 Snowflake Cortex AI (AI_COMPLETE)From the platform pricing page | $3 | $18 | $3 / $18+20% vs list | n/a | +20% vs list |
| OpenAI fast · cached $0.5 | $5 | $30 | $5 / $30+100% vs list | $0.5 | +100% vs list |
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.