Microsoft Models API Cost Calculator & Comparison

Every Microsoft model, side by side — current API rates, context window, benchmarks, and a live calculator that ranks them at your exact workload. 2 active models, 2 with public pricing. Prices refreshed daily.

Models tracked

2

Active

2

With public pricing

2

Cheapest input

$0.07/1M

Calculate your Microsoft API cost at your workload.

Set your workload — every priced model ranks in real time.

Adjust the workload

Every model below updates in real time.

1,00010,00050,000250,0001M10M

Ranked by your monthly bill

No models with public pricing available to compare right now.

Pricing at a glance

Blended $/1M tokens across the lineup.

Blended price uses a 3-to-1 input/output ratio. Green bar = cheapest.

Quick picks

Best Microsoft model for your use case.

As of April 2026, Microsoft offers 2 active models via API, ranging from $0.065/1M to $0.62/1M input tokens. The most context-rich model handles up to 66K tokens. Models support tool use. All prices are USD per 1 million tokens.

Lowest cost

Phi 4

$0.065/1M input

Largest context

WizardLM-2 8x22B

66K tokens

Quality vs price

Microsoft benchmarks at a glance.

Each point is one model — X is blended $/1M tokens, Y is the average of available quality benchmarks. Larger bubbles mean larger context windows.

Per-model benchmark scores

ModelAvgScores
Phi 452.4
MMLU84.8GPQA Diamond56.1HumanEval82.6MATH80.4AA Intelligence Index10IFEval4.9BBH52.6MMLU Pro47.7
WizardLM-2 8x22B9.1
MT-Bench9.1

Open weights

Open Models from Microsoft

Microsoft ships 2 open-source or open-weights models you can self-host or fine-tune. Each links to its Hugging Face card.

Every model

Every Microsoft model — pricing, context & capabilities.

ModelContextInput /1MOutput /1M
Phi 416K$0.065$0.14
WizardLM-2 8x22B66K$0.62$0.62

FAQ

Questions fréquentes

Pricing patterns, best-known use cases, and how this provider stacks up.

Get instant answers from our AI agent

Microsoft API pricing ranges from $0.065 to $0.62 per 1M input tokens. Output tokens cost more than input on every model. Prices are per 1 million tokens (1M ≈ 750,000 words). Use the calculator above to estimate your monthly spend at your actual workload.
Phi 4 is the lowest-priced Microsoft model with public pricing at $0.065/1M input tokens. It suits high-volume tasks where cost matters most — classification, extraction, summarization, and similar workloads that don't need frontier reasoning.
WizardLM-2 8x22B is Microsoft's highest-tier model at $0.62/1M input. It delivers the most sophisticated reasoning, instruction-following, and nuance. For workloads that don't require frontier performance, a mid-tier model typically cuts inference costs substantially.
Phi 4, WizardLM-2 8x22B support function calling (tool use), required for agentic workflows. Agents need a model that reliably follows structured output schemas — test with your specific tool definitions before committing to production volumes.
Yes — Microsoft supports prompt caching (discounts for repeated context) and batch processing (accept a delay, cut costs ~50%). These rates appear in the table above under "Cached /1M" and "Batch /1M." Caching pays off quickly if your prompts share a long system prompt or document prefix across many calls.
Microsoft has historically adjusted prices when launching new model generations, often cutting rates to stay competitive. Buzzi.ai snapshots pricing daily — you can subscribe to price-drop alerts on any Microsoft model using the "Alert me" button on its detail page.
Use the main comparison wizard to run the same calculator across Microsoft, Anthropic, Google, Meta, Mistral, and 20+ other providers. Set your exact workload and get a ranked cost chart in under a minute.

Look wider

Compare Microsoft against other providers.

Open the full wizard — pick a use case, set your usage, and cross-compare against OpenAI, Anthropic, Google, and 20+ more.

Open the comparison wizard