Phi 4 Mini Instruct API Benchmarks, Pricing & Provider Data
Compare Phi 4 Mini Instruct with another model
Choose a model to open its comparison page.
Phi 4 Mini Instruct benchmark, API pricing, and provider data cover 22 API providers, with prices starting at $0.0011/M.
Microsoft Phi 4 Mini Instruct is a compact instruction-tuned variant in the Phi series, optimized for quick responses and high throughput.
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 3 / 8
- Methodology
- V3.0
#1Math42Estimated2/4 Measured dimensions
#2Coding38.8Provisional1/4 Measured dimensions
#3Reasoning34.2Estimated2/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Rankings
Excels at
Detailed scores
Updated: Sep 5, 2026Speed & latency
undefined metric} other undefined metrics}}
Output speed46.6 tok/s#69 / 80Time to first token0.36 s#4 / 80
Speed & latency
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Agents
V3.0undefined metric} other undefined metrics}} · No data
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score38.880% interval22.8–54.71/4 Measured dimensionsLiveCodeBench12.6%#114 / 115
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score34.280% interval23.1–45.42/4 Measured dimensionsMMLU-Pro46.5%#127 / 129GPQA33.1%#213 / 217
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Knowledge
V3.0undefined metric} other undefined metrics}} · No data
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Score4280% interval30.2–53.82/4 Measured dimensionsAIME3.0%#65 / 68MATH-50069.6%#60 / 73
Math
V3.0undefined metric} other undefined metrics}} · Estimated
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
Pricing Comparison
Compare Phi 4 Mini Instruct API pricing across 22 providers. Prices range from $0.0011/M to $799.20/M. 6345ywz API offers the lowest rate at $0.0011/M.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | phi-4-mini-instruct | enterprise_emergency_standby | $57.53/M | $57.53/M | — | — | — | |
L1 100% L2 87% | microsoft/phi-4-mini-instruct | default | $0.080/M Cache read$0.080/M | $0.350/M | — | — | — | |
L1 100% | microsoft/phi-4-mini-instruct | default | $375.00/M | $375.00/M | — | — | — | |
L1 100% | phi-4-mini-instruct | default | $0.010/request | - | — | — | — | |
L1 100% | microsoft/phi-4-mini-instruct | default | $0.010/request | - | — | — | — | |
L1 99% | microsoft/phi-4-mini-instruct | default | $75.00/M | $75.00/M | — | — | — | |
L1 99% | microsoft/phi-4-mini-instruct | 0倍倍率分组 | $0.0011/M Cache read$0.0011/M | $0.0048/M | — | — | — | |
L1 80% | microsoft/phi-4-mini-instruct | 2api | $0.080/M Cache read$0.080/M | $0.350/M | — | — | — | |
L1 0% | microsoft/phi-4-mini-instruct | default | $799.20/M Cache read$799.20/M | $3496.50/M | — | — | — | |
L1 0% | microsoft/phi-4-mini-instruct | 懒人 | $0.080/M Cache read$0.080/M | $0.350/M | — | — | — | |
L1 0% | microsoft/phi-4-mini-instruct | default | $0.080/M Cache read$0.080/M | $0.350/M | — | — | — | |
L1 0% | phi-4-mini-instruct | default | $75.00/M | $75.00/M | — | — | — |
Alternatives & Similar Models
GPT-OSS
gpt-oss
GPT-OSS is an open-weight language model family designed for self-hosted inference, research, and cost-efficient alternatives to proprietary GPT-class models.
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
MiniMax M2.7
minimax-m2-7
MiniMax M2.7 is a high-tier M2-series model tuned for complex reasoning, long-context dialogue, and production-grade API workloads.
Qwen3.5
qwen3-5
Alibaba Qwen3.5 is a Qwen3 generation model with improved reasoning, multilingual support, and efficient inference for chat, coding, and agent applications.
Step 3.5 Flash
step-3-5-flash
Step 3.5 Flash is a fast and efficient language model, optimized for quick responses and high throughput.
Frequently Asked Questions
- What benchmark data does Phi 4 Mini Instruct include?
- LMSpeed shows Phi 4 Mini Instruct benchmark context, API price, output speed, first-token latency, and provider data across 22 providers when those signals are available.
- What is the Phi 4 Mini Instruct API price?
- Phi 4 Mini Instruct has pricing from 22 providers, ranging from $0.0011/M to $799.20/M. 6345ywz API has the lowest listed price.
- What does the Phi 4 Mini Instruct API pricing table include?
- The Phi 4 Mini Instruct API pricing table compares 22 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Phi 4 Mini Instruct API pricing?
- 6345ywz API currently has the lowest listed Phi 4 Mini Instruct price at $0.0011/M across 22 providers.
- Is Phi 4 Mini Instruct API free?
- Phi 4 Mini Instruct does not currently have a free API tier on LMSpeed. All 22 providers charge per token.