Phi-4-mini-reasoning is a lightweight open model designed for advanced mathematical reasoning and logic-intensive problem-solving. It is particularly well-suited for tasks such as formal proofs, symbolic computation, and solving multi-step word problems. With its efficient architecture, the model balances high-quality reasoning performance with cost-effective deployment, making it ideal for educational applications, embedded tutoring, and lightweight edge or mobile systems. Phi-4-mini-reasoning supports a 128K token context length, enabling it to process and reason over long mathematical problems and proofs. Built on synthetic and high-quality math datasets, the model leverages advanced fine-tuning techniques such as supervised fine-tuning and preference modeling to enhance reasoning capabilities. Its training incorporates safety and alignment protocols, ensuring robust and reliable performance across supported use cases.
AiHubmix-Phi-4-mini-reasoning vs kimi-k3
Output tokens cost $0.12 per million on AiHubmix-Phi-4-mini-reasoning and $15.00 per million on kimi-k3. Input tokens cost $0.12 per million on AiHubmix-Phi-4-mini-reasoning and $3.00 per million on kimi-k3. Cached input tokens are billed at $0.12 per million on AiHubmix-Phi-4-mini-reasoning and $0.30 per million on kimi-k3. Context lengths are 128,000 tokens on AiHubmix-Phi-4-mini-reasoning and 1,048,576 tokens on kimi-k3. On the LMArena coding leaderboard AiHubmix-Phi-4-mini-reasoning scores 1306 and kimi-k3 scores 1531.
Kimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
Tokens / day
Requests / day
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Throughput (tok/s)
TTFT (s)
Uptime (%)
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: AiHubmix-Phi-4-mini-reasoning, kimi-k3?
AiHubmix-Phi-4-mini-reasoning: $0.12/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
kimi-k3: 1531; AiHubmix-Phi-4-mini-reasoning: 1306 (LMArena coding leaderboard).
How large is each context window?
AiHubmix-Phi-4-mini-reasoning accepts 128,000 and kimi-k3 accepts 1,048,576 input tokens. Maximum output per request is 4,000 tokens on AiHubmix-Phi-4-mini-reasoning and 1,048,576 tokens on kimi-k3.
What inputs and capabilities does each model support?
AiHubmix-Phi-4-mini-reasoning accepts text input; kimi-k3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call AiHubmix-Phi-4-mini-reasoning and kimi-k3 with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
