All models · microsoft

Microsoft: Phi 4 pricing and limits

id microsoft/phi-4 · listed 2025-01-10 · knowledge cutoff 2024-06-30

Input (per 1M tokens)$0.070
Output (per 1M tokens)$0.140
Context window16,384 tokens
Max output14,745 tokens
Modalitiestext → text

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.11.

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

Cheaper on both input and output, with at least half the context

ModelIn / 1MOut / 1MContext
Auto Router (Beta)$-1000000.000$-1000000.0002,000,000
Pareto Code Router$-1000000.000$-1000000.0002,000,000
Auto Router$-1000000.000$-1000000.0002,000,000
Z.ai: GLM Flash Latest$0.052$0.1201,048,576
DeepSeek: DeepSeek V4 Flash 0731$0.044$0.1331,048,576
Thinking Machines: Inkling Small (free)freefree1,048,576
For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=microsoft/phi-4 (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=microsoft. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with microsoft. Agent Exchange