Every Deep Infra Phi-4 rate we track, compared against 2 providers serving the same model.
Deep Infra currently has the cheapest Phi-4 input price among the 2 providers we track.
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.070/1M | $0.140/1M |
| Standard | $0.070/1M | $0.140/1M |
Deep Infra is an AI inference cloud that provides serverless APIs for 100+ models and dedicated GPU rentals. Features OpenAI-compatible endpoints, custom model deployments, and infrastructure optimized for scale.
Deep Infra serves Phi-4 from $0.070 per 1M input tokens, across 2 tracked pricing modes. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Of the 2 providers we track serving Phi-4, Deep Infra currently has the lowest input price. Rates change often, and throughput and latency differ between providers — check the comparison above before committing.
We track 2 Phi-4 offerings from Deep Infra. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.