Get an email when this model's blended price drops. No account needed.
One email per drop. Unsubscribe anytime.
Daily blended price ($/1M) — recorded each day, builds into a trend over time.
Typical 3:1 output-to-input mix, per 1M tokens
Source: litellm
Complex reasoning, analysis, planning and multi-step problem solving where answer quality matters more than raw cost.
Microsoft Phi 4 Reasoning is a 14B open-weight reasoning model for math, science, coding, and instruction-following workloads.
phi-4-reasoning is a Reasoning model from Microsoft (US). HotON.ai tracks it at $0.13 per 1M input tokens and $0.50 per 1M output tokens, with a 33K-token context window. Its composite efficiency score is 88/100 at an estimated $0.001 per successful task.
phi-4-reasoning is tracked at $0.13 per 1M input tokens and $0.50 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.41 per 1M tokens. Figures are illustrative demo data.
Complex reasoning, analysis, planning and multi-step problem solving where answer quality matters more than raw cost.
phi-4-reasoning supports up to a 33K-token context window — large enough for long documents and extended conversations in a single request.
Within the HotON.ai tracked set, phi-4-reasoning is cheaper than 75% of models on input price and ranks #332 of 535 by overall efficiency.
Yes — qwen3-30b-a3b-thinking-2507 is a lower-cost option at $0.40 per 1M output tokens, while still covering similar Reasoning use cases. Compare them side by side on HotON.ai.
Ready to paste into articles, papers or AI prompts — prices and date refresh with the live data.
HotON.ai — phi-4-reasoning (Microsoft): $0.13/1M input, $0.50/1M output. https://hoton.ai/en/models/microsoft-phi-4-reasoningPricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Efficiency is a modeled composite of real price and context.