Inflection: Inflection 3 Pi
Inflection 3 Pi is a text-only model with an 8,000-token context window and a 1,024-token output cap. It does not support tool use, reasoning modes, or structured output, which limits its utility for agentic workflows or applications requiring formatted data extraction. Input and output are restricted to text, so multimodal tasks are outside its scope entirely. On pricing, it sits at $2.50 per million input tokens and $10.00 per million output tokens, a rate that is neither budget-tier nor premium by current market standards. The more significant issue for buyers is the absence of any independent benchmark coverage, meaning there is no published performance data to anchor a capability comparison. Teams that require verified quality metrics before deployment should treat this model as unproven. It may suit developers already within the Inflection ecosystem who are willing to evaluate it through their own internal testing rather than relying on third-party results.
- Model ID
- inflection/inflection-3-pi
- Vendor
- inflection
- Released
- October 2024
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 1,024 tokens
- Tool Calling
- not supported
- Structured Output
- not supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $2.50/M input and $10.00/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.09 |
| Classify 1,000 customer emails | 500k in / 50k out | $1.75 |
| A month of a busy support chatbot | 5M in / 2M out | $32.50 |
Similar models
Quick answers
- How much does Inflection: Inflection 3 Pi cost?
- $2.50 per million input tokens and $10.00 per million output tokens.
- What is Inflection: Inflection 3 Pi's context window?
- 8,000 tokens, roughly 12 pages of text in a single request.
- Can Inflection: Inflection 3 Pi process images?
- No, it is text-only on the input side.