Unknown providerLLMactive

Microsoft Phi-3 API Pricing

2 available providers and 1 live price sources tracked, including 0 official provider.

Data snapshot:

Official input / 1M
Lowest input / 1M$0.10
Maximum input gapNot a service-quality measure
Comparable providers21 live

Microsoft Phi-3 provider prices and multipliers

No complete verified official input/output baseline is currently recorded, so provider quotes are shown without multipliers.

Providers: 2Market low: $0.10Lowest observed: $0.10Lowest input multiplier:
Official input baselineOfficial output baselinePrice multipliers do not measure stability, rate limits, refunds, or service quality.
Microsoft Phi-3 provider price and evidence comparison
Provider / operatorInput / 1M tokensOutput / 1M tokensvs officialPrice evidencePublic operating historyAPI docsRefund policyPayment / invoice
Fireworks AIunknown$0.10$0.10
In Out
Live API pricePlatform pageObserved: UnknownView docsNot providedvisa · mastercardunknown
Novita AIunknown$0.14$0.14
In Out
UnreviewedPlatform pageObserved: UnknownView docsNot providedvisa · mastercardunknown

Platform-submitted information or domain verification does not mean the price was independently checked and is not a ComputeUnion guarantee of pricing, availability, refunds, compliance, invoices, or service quality.

External capability references

Only source results safely mapped to the official model name are shown.

No safely matched external result is available; adjacent model scores are not substituted.

FAQ

How is Microsoft Phi-3 API priced?

Input and output tokens are billed separately. A complete official input/output baseline is not currently recorded, so provider quotes are normalized per million tokens.

Which provider is cheapest for Microsoft Phi-3?

The lowest recorded input price is $0.10/1M tokens from Fireworks AI; verify provider terms and the observation date before production use.

How do official and relay prices differ?

Official and relay channels can differ in price, latency, limits, and service terms; evaluate them separately for production traffic.