Microsoft API pricing
All 22 Microsoft models with a listed API price, cheapest input from $0.07 per 1M tokens. Sort by price, context window or benchmark, filter by capability, and copy the exact model ID for any serving provider. Listed prices from LiteLLM, OpenRouter and Vercel.
Models
22
with a listed price
Cheapest input
$0.07
per 1M tokens
Cheapest output
$0.10
per 1M tokens
Max context
256K
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Capability
| Phi 4 | Microsoft | Released Dec 11, 2024 | 16K | from $0.07 via DeepInfra | from $0.14 via DeepInfra | 5.9 | n/a | 57% | 3 providers |
| WizardLM-2 8x22B | Microsoft | First listed Jul 2025 | 66K | from $0.48 via DeepInfra | from $0.48 via DeepInfra | n/a | n/a | n/a | 3 providers |
| Phi 3 Mini 128k Instruct | Microsoft | Released Apr 23, 2024 | 131K | from $0.10 via Fireworks AI | from $0.10 via Fireworks AI | n/a | n/a | n/a | 2 providers |
| Mai Thinking 1 | Microsoft | First listed Sep 2026 | 256K | from $2.00 via Aihubmix | from $8.00 via Aihubmix | n/a | n/a | n/a | 2 providers |
| Phi 4 Mini Instruct | Microsoft | Released Jul 26, 2025 | 131K | $0.075 via Azure | $0.30 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-4-mini-instruct |
| Phi 4 Mini Reasoning | Microsoft | Released Dec 11, 2024 | 131K | $0.075 via Azure | $0.30 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-4-mini-reasoning |
| Phi 4 Multimodal Instruct | Microsoft | Released Jul 26, 2025 | 131K | $0.08 via Azure | $0.32 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-4-multimodal-instruct |
| Phi 2 3B | Microsoft | First listed Dec 2025 | 2K | $0.10 via Fireworks AI | $0.10 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/phi-2-3b |
| Phi 4 Reasoning | Microsoft | Released Dec 11, 2024 | 33K | $0.125 via Azure | $0.50 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-4-reasoning |
| Phi 3.5 Mini Instruct | Microsoft | First listed Nov 2024 | 128K | $0.13 via Azure | $0.52 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3.5-mini-instruct |
| Phi 3.5 Vision Instruct | Microsoft | First listed Nov 2024 | 128K | $0.13 via Azure | $0.52 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3.5-vision-instruct |
| Phi 3 Mini 4k Instruct | Microsoft | Released Apr 23, 2024 | 4K | $0.13 via Azure | $0.52 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3-mini-4k-instruct |
| Phi 3 Small 128k Instruct | Microsoft | Released Apr 23, 2024 | 128K | $0.15 via Azure | $0.60 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3-small-128k-instruct |
| Phi 3 Small 8k Instruct | Microsoft | Released Apr 23, 2024 | 8K | $0.15 via Azure | $0.60 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3-small-8k-instruct |
| Phi 3.5 MoE Instruct | Microsoft | First listed Nov 2024 | 128K | $0.16 via Azure | $0.64 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3.5-MoE-instruct |
| Phi 3 Medium 128k Instruct | Microsoft | Released Apr 23, 2024 | 128K | $0.17 via Azure | $0.68 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3-medium-128k-instruct |
| Phi 3 Medium 4k Instruct | Microsoft | Released Apr 23, 2024 | 4K | $0.17 via Azure | $0.68 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/Phi-3-medium-4k-instruct |
| Phi 3 Vision 128k Instruct | Microsoft | First listed Dec 2025 | 32K | $0.20 via Fireworks AI | $0.20 via Fireworks AI | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/phi-3-vision-128k-instruct |
| Mai Cyber 1 Flash | Microsoft | First listed Sep 2026 | 256K | $0.60 via Azure | $3.50 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/MAI-Cyber-1-Flash |
| Mai Code 1 Flash | Microsoft | First listed Jun 2026 | 128K | $0.75 via Github Copilot | $4.50 via Github Copilot | n/a | n/a | n/a | github_copilot/mai-code-1-flash |
| Mai Code 1 Flash Internal | Microsoft | First listed Jun 2026 | 128K | $0.75 via Github Copilot | $4.50 via Github Copilot | n/a | n/a | n/a | github_copilot/mai-code-1-flash-internal |
| Mai Ds R1 | Microsoft | First listed Jul 2025 | 128K | $1.35 via Azure | $5.40 via Azure | n/a | n/a | n/a | Azure cheapest azure_ai/MAI-DS-R1 |
Input $/1M
from$0.07
via DeepInfraOutput $/1M
from$0.14
via DeepInfraIntelligence5.93 providers
Input $/1M
from$0.48
via DeepInfraOutput $/1M
from$0.48
via DeepInfraIntelligencen/a3 providers
Input $/1M
from$0.10
via Fireworks AIOutput $/1M
from$0.10
via Fireworks AIIntelligencen/a2 providers
Reasoning modelInput $/1M
from$2.00
via AihubmixOutput $/1M
from$8.00
via AihubmixIntelligencen/a2 providers
Input $/1M
$0.075
via AzureOutput $/1M
$0.30
via AzureIntelligencen/aAzure
Input $/1M
$0.075
via AzureOutput $/1M
$0.30
via AzureIntelligencen/aAzure
Input $/1M
$0.08
via AzureOutput $/1M
$0.32
via AzureIntelligencen/aAzure
Input $/1M
$0.10
via Fireworks AIOutput $/1M
$0.10
via Fireworks AIIntelligencen/aFireworks AI
Reasoning modelInput $/1M
$0.125
via AzureOutput $/1M
$0.50
via AzureIntelligencen/aAzure
Input $/1M
$0.13
via AzureOutput $/1M
$0.52
via AzureIntelligencen/aAzure
Input $/1M
$0.13
via AzureOutput $/1M
$0.52
via AzureIntelligencen/aAzure
Input $/1M
$0.13
via AzureOutput $/1M
$0.52
via AzureIntelligencen/aAzure
Input $/1M
$0.15
via AzureOutput $/1M
$0.60
via AzureIntelligencen/aAzure
Input $/1M
$0.15
via AzureOutput $/1M
$0.60
via AzureIntelligencen/aAzure
Input $/1M
$0.16
via AzureOutput $/1M
$0.64
via AzureIntelligencen/aAzure
Input $/1M
$0.17
via AzureOutput $/1M
$0.68
via AzureIntelligencen/aAzure
Input $/1M
$0.17
via AzureOutput $/1M
$0.68
via AzureIntelligencen/aAzure
Input $/1M
$0.20
via Fireworks AIOutput $/1M
$0.20
via Fireworks AIIntelligencen/aFireworks AI
Reasoning modelInput $/1M
$0.60
via AzureOutput $/1M
$3.50
via AzureIntelligencen/aAzure
Input $/1M
$0.75
via Github CopilotOutput $/1M
$4.50
via Github CopilotIntelligencen/aGithub Copilot
Input $/1M
$0.75
via Github CopilotOutput $/1M
$4.50
via Github CopilotIntelligencen/aGithub Copilot
Reasoning modelInput $/1M
$1.35
via AzureOutput $/1M
$5.40
via AzureIntelligencen/aAzure
1–22 of 22 models
Page 1 of 1
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 2 prices older, back to Oct 9, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI