BroadRouter

Phi-4 API pricing

Updated

2 providers tie for the cheapest standard price for Phi-4 on the 3:1 blend; DeepInfra charges USD 0.07 per 1M input tokens and USD 0.14 per 1M output tokens. The median across 3 standard prices is USD 0.07 / USD 0.14. Every price is read from the provider's own pricing page, checked 2026-11-15.

Microsoft · slug phi-4 · up to 131,072 tokens of context · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2025-07-09 (17 archived price points, 0 list-price changes): LLM API price history.

Does Microsoft sell Phi-4 directly?

Microsoft publishes no price for Phi-4 on its own API that we could find, so this page compares hosts only.

Phi-4 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.5× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Phi-4 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra tied cheapest
microsoft/phi-4
Notes and source quote
“$0.07 in $0.14 out / 1M tokens”
USD 0.07not publishedUSD 0.14USD 0.087516,384BFLOAT16DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2Featherless tied cheapest
microsoft/phi-4
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits). No cached price published.

“PRICING: INPUT $0.07 / OUTPUT $0.14”
USD 0.07not publishedUSD 0.14USD 0.087532,768FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
3Microsoft Azure
Notes and source quote

Foundry Models serverless (pay-as-you-go); no deployment type on the row, price shown for East US. Context column on page: "128K" (stored as 131072).

“Phi-4 128K $0.125 $0.50”
USD 0.125not publishedUSD 0.50USD 0.2188131,072not statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot
microsoft/phi-4
Notes and source quote

Flex service tier (0.8× standard).

“Flex (0.8×) $0.056 $0.112”
USD 0.056not publishedUSD 0.112USD 0.0716,384BFLOAT16DeepInfra page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Phi-4 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.
Monthly cost of three workloads on Phi-4, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfraUSD 8.82USD 18.90exceeds context
FeatherlessUSD 8.82USD 18.90exceeds context
Microsoft AzureUSD 20.25USD 37.50USD 270.00

For the support chatbot, the cheapest price (DeepInfra and 1 other, tied, USD 8.82 a month) saves USD 0 against the median (USD 8.82). For the coding agent the gap is USD 0 a month.

Which Phi-4 provider is cheapest for your traffic?

DeepInfra and Featherless share the lowest input price (USD 0.07) and the lowest output price (USD 0.14), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

Phi-4: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfra (no cache price)USD 0.0875 cheapestUSD 0.0875 cheapestUSD 0.0875 cheapest
Featherless (no cache price)USD 0.0875 cheapestUSD 0.0875 cheapestUSD 0.0875 cheapest
Microsoft Azure (no cache price)USD 0.2188USD 0.2188USD 0.2188

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

None of the 3 providers publishes a cached-input discount for Phi-4, so cache hits do not change the ranking.

Context windows differ: 131,072 tokens at Microsoft Azure; 32,768 tokens at Featherless; 16,384 tokens at DeepInfra. The cheapest row is not always the one that fits a long prompt.

What does Phi-4 cost in other languages?

The same text needs a different number of tokens in each language. With the Phi-4 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Phi-4:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.015DeepInfra
Arabic MSAUSD 0.050DeepInfra
HindiUSD 0.069DeepInfra
ChineseUSD 0.082DeepInfra
CodeUSD 0.018DeepInfra

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

Priced closest from other makers: NVIDIA Nemotron 3 Nano 30B A3B (NVIDIA, USD 0.0875) · DeepSeek V4 Flash 0731 (DeepSeek, USD 0.09) · Ling 3.0 Flash (inclusionAI, USD 0.09).

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 API cost per token?

From USD 0.07 per 1M input tokens (USD 0.00000007 per token) and USD 0.14 per 1M output tokens (USD 0.00000014 per token) at the cheapest standard price. The median of 3 standard prices is USD 0.07 input and USD 0.14 output. 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?

2 providers are tied for the cheapest: DeepInfra and Featherless, each USD 0.0875 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.07 (DeepInfra and 1 other, tied); for output alone, USD 0.14 (DeepInfra and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Microsoft sell Phi-4 on its own API?

Microsoft publishes no price for Phi-4 on its own API that we could find, so there is no maker price to compare. The cheapest host is DeepInfra at USD 0.07 / USD 0.14 per 1M tokens.

Does Phi-4 have cached input pricing?

None of the 3 standard prices includes a cached-input price, so budget repeated prompts at the full input price.

What is the Phi-4 context window?

Up to 131,072 tokens. 2 standard prices come with less, down to 16,384 tokens (DeepInfra and Featherless). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on Phi-4?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 138.60 a month at DeepInfra, USD 138.60 at the median price and USD 270.00 at Microsoft Azure. Try your own numbers.

Is there a batch, flex or priority price for Phi-4?

Yes: flex / spot from DeepInfra at USD 0.056 / USD 0.112 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Phi-4 free to use through an API?

No provider in our data lists a free price for Phi-4 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity