Compare
Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.
Monthly bill
Token models use the token counts. Other models use units times the flat rate.
Lowest bill: OpenAI: GPT Mini Latest · $5.25
Add another
Search by name, then add up to four.
| OpenAI: GPT Mini Latest | Google: Gemini 3.5 Flash (batch) | |
|---|---|---|
| Provider | OpenAI | |
| Modality | text, image | text, image, video, audio |
| Context | 400K | 1.0M |
| Input | $0.75/1M | $0.75/1M |
| Output | $4.5/1M | $4.5/1M |
| Cache read | $0.075/1M | $0.075/1M |
Tiers and extras
- OpenAI: GPT Mini Latest
- Web search: $0.01 per request
- Google: Gemini 3.5 Flash (batch)
- Web search: $0.014 per request; Image input: $0.75 per 1M tokens; Audio: $1.5 per 1M tokens; Audio cache: $0.15 per 1M tokens; Reasoning: $4.5 per 1M tokens