| Best For | Context | Input/1M | Output/1M | |
|---|---|---|---|---|
| GPT-5.5 | Latest flagship, reasoning | 1M | $5.00 | $30.00 |
| GPT-5.5 Pro | Maximum quality | 1M | $30.00 | $180.00 |
| GPT-5.4 | Affordable flagship, coding | 1M | $2.50 | $15.00 |
| GPT-5.4 Pro | Premium GPT-5.4 | 1M | $30.00 | $180.00 |
| GPT-5.4 Mini | Coding, subagents | 400K | $0.75 | $4.50 |
| GPT-5.4 Nano | Cheapest GPT-5.4 | 400K | $0.20 | $1.25 |
| GPT-5.2 | Previous flagship | 400K | $1.75 | $14.00 |
| GPT-5 / 5.1 | General purpose flagship | 400K | $1.25 | $10.00 |
| GPT-5 Mini | Balanced quality and cost | 400K | $0.25 | $2.00 |
| GPT-5 Nano | Classification, routing | 400K | $0.05 | $0.40 |
| GPT-4.1 | Long context (1M tokens) | 1M | $2.00 | $8.00 |
| GPT-4.1 Mini | Cost effective, long context | 1M | $0.40 | $1.60 |
| o3 | Complex reasoning, STEM | 200K | $2.00 | $8.00 |
| o4-mini | Fast reasoning | 200K | $1.10 | $4.40 |
| GPT-4o | Multimodal with vision | 128K | $2.50 | $10.00 |
| GPT-4o Mini | Cheap multimodal | 128K | $0.15 | $0.60 |
Reasoning token costs are hidden
o series models (o3, o4-mini, o1) generate internal reasoning tokens that are billed as output tokens but are not visible in the API response. A response showing 500 output tokens may actually consume 2,000 or more total tokens. Monitor o series usage carefully and avoid using these models for simple tasks where GPT-5 or GPT-4.1 would suffice.
1
Simple tasks
GPT-5 Nano or GPT-5.4 Nano ($0.05 to $0.20/1M input)
2
General purpose
GPT-5.4 Mini or GPT-5 Mini ($0.25 to $0.75/1M input)
3
Complex tasks
GPT-5.4 or GPT-5.2 ($1.75 to $2.50/1M input)
4
Deep reasoning
GPT-5.5 ($5.00/1M input, adjustable reasoning effort)
1
Simple tasks
GPT-5 Nano or GPT-5.4 Nano ($0.05 to $0.20/1M input)
2
General purpose
GPT-5.4 Mini or GPT-5 Mini ($0.25 to $0.75/1M input)
3
Complex tasks
GPT-5.4 or GPT-5.2 ($1.75 to $2.50/1M input)
4
Deep reasoning
GPT-5.5 ($5.00/1M input, adjustable reasoning effort)