Phi-4-reasoning API pricing
Updated
The cheapest standard price for Phi-4-reasoning is Microsoft Azure at USD 0.125 per 1M input tokens and USD 0.50 per 1M output tokens. Every price is read from the provider's own pricing page, checked 2026-11-14.
Does Microsoft sell Phi-4-reasoning directly?
Microsoft publishes no price for Phi-4-reasoning on its own API that we could find, so this page compares hosts only.
Phi-4-reasoning price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Microsoft Azure cheapestNotes and source quoteFoundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: "32K" (stored as 32768). “Phi-4-reasoning 32K $0.125 $0.50” | USD 0.125 | not published | USD 0.50 | USD 0.2188 | 32,768 | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Phi-4-reasoning cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Microsoft Azure | USD 20.25 | USD 37.50 | exceeds context |
Estimate your own bill
- LLM API cost calculator with Phi-4-reasoning preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Phi-4-reasoning compare with other Microsoft models?
The Microsoft models whose cheapest standard price is closest to Phi-4-reasoning's (USD 0.2188 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Phi-4 | USD 0.07 | USD 0.14 | 131,072 | 3 |
Priced closest from other makers: DeepSeek V4.1 Flash (DeepSeek, USD 0.21) · Hy3 (Tencent, USD 0.231) · DeepSeek V3.2 (DeepSeek, USD 0.234).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Phi-4-reasoning API cost per token?
From USD 0.125 per 1M input tokens (USD 0.000000125 per token) and USD 0.50 per 1M output tokens (USD 0.0000005 per token) at the cheapest standard price. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Phi-4-reasoning?
Microsoft Azure is the only provider with a paid standard price, USD 0.125 input and USD 0.50 output per 1M tokens, so there is nothing to rank yet.
Does Microsoft sell Phi-4-reasoning on its own API?
Microsoft publishes no price for Phi-4-reasoning on its own API that we could find, so there is no maker price to compare. The cheapest host is Microsoft Azure at USD 0.125 / USD 0.50 per 1M tokens.
Does Phi-4-reasoning have cached input pricing?
The only standard price has no cached-input price, so budget repeated prompts at the full input price.
What is the Phi-4-reasoning context window?
32,768 tokens on every provider that states it.
How much does a coding agent cost per month on Phi-4-reasoning?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 270.00 a month at Microsoft Azure. Most of the input is cached, so the cache price matters as much as the input price. Try your own numbers.
Is Phi-4-reasoning free to use through an API?
No provider in our data lists a free price for Phi-4-reasoning as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.