← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Phi 4 Pricing
Microsoft · microsoft-phi-4
Input / 1M tokens
$0.070
Output / 1M tokens
$0.140
Context window
16,384 tokens
≈ 22 pages of text
Max output
16,384 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0001
1,000 requests / month$0.14/mo10,000 requests / month$1.40/mo100,000 requests / month$14.00/moEstimate your own workloadOpens the calculator with Phi 4 preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Strong instruction following and basic reasoning at very low inference cost; suitable for high-volume local or edge deployments.
The business tradeoff
Smaller scale produces measurable gaps on complex multi-step reasoning and specialized knowledge; 16k context limits long-document use cases.
Head-to-head
Vendor list rates, as of Jun 23, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.