| Phi 4 | GPT-5.5 | |
|---|---|---|
| Input, per 1M tokens | $0.07 | $5.00 |
| Output, per 1M tokens | $0.14 | $30.00 |
| Context window | 16K | 1.05M |
| Classification or routing (600 tokens in, 10 out), per 1,000 | $0.0434 | $3.30 |
| Chat reply (2,000 in, 400 out), per 1,000 | $0.196 | $22.00 |
| Retrieval-augmented answer (8,000 in, 500 out), per 1,000 | $0.63 | $55.00 |
| Confidence signal | no | no |
| Tool calling | no | yes |
Which one should carry your traffic?
If Phi 4 answers your requests as well as GPT-5.5, moving that traffic saves 99% on chat-shaped requests. Averages cannot tell you whether it does for your requests. Phi 4 does not expose a confidence signal through OpenRouter, so Gimbix would test it as a full replacement rather than a first answer.
Phi 4 profile · GPT-5.5 profile · Measure it on your traffic