Microsoft Azure: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Microsoft Azure for your use-case.
Most Intelligent
Updated
Claude Fable 5 (with fallback)
GPT-5.6 Sol (max)GPT-5.6 Sol (xhigh)GPT-5.6 Sol (high)Claude Opus 4.7 (max)Intelligence index
Total 79 models
Fastest
Llama 4 Maverick (FP8)gpt-oss-120b (low)gpt-oss-120b (high)GPT-5.4 mini (xhigh)GPT-4.1 nanoOutput speed
Total 79 models
Lowest Price
GPT-5 nano (high)GPT-5 nano (medium)GPT-4.1 nanoGPT-4o miniPhi-4Blended price (per 1M tokens)
Total 79 models
Azure offers 79 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Azure are Claude Fable 5 (with fallback) (50), GPT-5.6 Sol (max) (47), and GPT-5.6 Sol (xhigh) (44).
- For output speed, the fastest models are Llama 4 Maverick (FP8) (385 t/s), gpt-oss-120b (low) (331 t/s), and gpt-oss-120b (high) (313 t/s). Speed varies significantly across models, with a 55% difference between the fastest and slowest.
- For latency, Phi-4 Mini (0.85s), Llama 4 Scout (0.86s), and Phi-4 Multimodal (0.87s) offer the lowest time to first answer token.
- For pricing, GPT-5 nano (high) ($0.05), GPT-5 nano (medium) ($0.05), and GPT-4.1 nano ($0.08) offer the lowest blended prices per 1M tokens. Prices vary up to 3.0x across models.
- For context window size, GPT-5.4 (xhigh) (1M), Claude Fable 5 (with fallback) (1M), and Claude Opus 4.7 (max) (1M) support the largest context windows on Azure.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic knowledge work, (Elo-500)/2000
Agentic real-world work tasks, (Elo-500)/2000
Agentic SaaS workflows
Agentic coding & terminal use
Coding
Reasoning & knowledge
Professional document reasoning, All-pass
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Instruction following
Agentic tool use
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Claude Fable 5 (with fallback) | 1M | Proprietary | 50 | $43.25 | 65 | 86.61 | 94.36 | -- | |||
GPT-5.6 Sol (xhigh) | 524k | Proprietary | 44 | $1.26 | 82 | 32.37 | 38.46 | -- | |||
GPT-5.6 Sol (high) | 524k | Proprietary | 42 | $0.85 | 77 | 9.56 | 16.06 | -- | |||
Claude Opus 4.7 (max) | 1M | Proprietary | 41* | -- | 46 | 23.26 | 34.07 | -- | |||
GPT-5.4 (xhigh) | 1.05M | Proprietary | 39* | -- | 101 | 150.08 | 155.03 | -- | |||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $4.75 | 79 | 159.22 | 165.56 | -- | |||
GPT-5.6 Terra (xhigh) | 524k | Proprietary | 38 | $0.67 | 99 | 19.10 | 24.14 | -- | |||
GPT-5.5 (high) | 524k | Proprietary | 37 | $1.13 | 71 | 17.80 | 24.86 | -- | |||
GPT-5.6 Luna (xhigh) | 524k | Proprietary | 35 | $0.09 | 132 | 48.03 | 51.81 | -- | |||
GPT-5.6 Terra (high) | 524k | Proprietary | 34 | $0.35 | 91 | 2.36 | 7.87 | -- | |||
GPT-5.6 Luna (high) | 524k | Proprietary | 32 | $0.05 | 132 | 13.58 | 17.35 | -- | |||
Claude Opus 4.6 (max) | 1M | Proprietary | 32* | -- | 37 | 19.25 | 32.60 | -- | |||
 Kimi K2.6 | 262k | Open | 31* | -- | 206 | 1.44 | 25.47 | 21.60 | |||
 DeepSeek V4 Pro (max) | 1M | Open | 31 | $9.65 | 86 | 1.69 | 58.57 | 51.05 | |||
Claude Sonnet 4.6 (max) | 200k | Proprietary | 30 | $2.70 | 56 | 92.05 | 100.99 | -- | |||
GPT-5.2 (xhigh) | 400k | Proprietary | 30* | -- | 83 | 98.75 | 104.80 | -- | |||
DeepSeek V4 Pro (high) | 1M | Open | 30* | -- | 72 | 1.72 | 36.11 | 27.49 | |||
Claude Opus 4.5 | 200k | Proprietary | 29* | -- | 46 | 17.17 | 27.93 | -- | |||
GPT-5.2 Codex (xhigh) | 400k | Proprietary | 29* | -- | 79 | 107.93 | 114.26 | -- | |||
GPT-5.2 (medium) | 400k | Proprietary | 27* | -- | 73 | 6.22 | 13.09 | -- | |||
Claude Opus 4.6 (Non-reasoning, high) | 1M | Proprietary | 26* | -- | 37 | 2.42 | 16.06 | -- | |||
 Grok 4.20 0309 v2 | 262k | Proprietary | 26* | -- | 216 | 11.68 | 14.00 | -- | |||
Grok 4.3 (high) | 200k | Proprietary | 25 | $0.53 | 171 | 22.92 | 25.84 | -- | |||
GPT-5 Codex (high) | 400k | Proprietary | 25* | -- | 152 | 11.58 | 14.87 | -- | |||
Grok 4.3 (medium) | 200k | Proprietary | 25* | -- | 150 | 10.25 | 13.57 | -- | |||
GPT-5.1 (high) | 272k | Proprietary | 25* | -- | 92 | 40.94 | 46.36 | -- | |||
Claude Sonnet 4.6 (Non-reasoning, high) | 200k | Proprietary | 25* | -- | 43 | 1.98 | 13.64 | -- | |||
GPT-5.4 mini (xhigh) | 400k | Proprietary | 25 | $0.48 | 220 | 124.36 | 126.63 | -- | |||
Grok 4.3 (low) | 200k | Proprietary | 24* | -- | 148 | 4.85 | 8.23 | -- | |||
GPT-5.1 Codex (high) | 400k | Proprietary | 24* | -- | 123 | 7.74 | 11.81 | -- | |||
Claude Opus 4.5 (Non-reasoning) | 200k | Proprietary | 24* | -- | 47 | 1.64 | 12.25 | -- | |||
Kimi K2.6 (Non-reasoning) | 262k | Open | 24* | -- | 184 | 1.57 | 4.29 | -- | |||
Kimi K2.5 | 262k | Open | 23* | -- | 135 | 2.16 | 27.82 | 21.96 | |||
GPT-5 (high) | 400k | Proprietary | 23* | -- | 100 | 62.15 | 67.16 | -- | |||
GPT-5 (medium) | 400k | Proprietary | 23* | -- | 90 | 28.65 | 34.24 | -- | |||
Claude 4.1 Opus | 200k | Proprietary | 23* | -- | -- | -- | -- | -- | |||
Grok 4 | 256k | Proprietary | 22* | -- | 76 | 7.44 | 14.03 | -- | |||
Kimi K2 Thinking | 256k | Open | 22* | -- | 127 | 1.58 | 21.19 | 15.69 | |||
o3-pro | 200k | Proprietary | 22* | -- | -- | -- | -- | -- | |||
Claude 4.5 Sonnet | 200k | Proprietary | 21 | $1.78 | 41 | 11.14 | 23.41 | -- | |||
DeepSeek V4 Pro (Non-reasoning) | 1M | Open | 21* | -- | 88 | 1.72 | 7.40 | -- | |||
GPT-5 (low) | 400k | Proprietary | 21* | -- | 89 | 5.60 | 11.20 | -- | |||
GPT-5 mini (medium) | 400k | Proprietary | 21* | -- | 126 | 10.65 | 14.61 | -- | |||
GPT-5.1 Codex mini (high) | 400k | Proprietary | 20* | -- | 147 | 16.91 | 20.31 | -- | |||
o3 | 200k | Proprietary | 20* | -- | 98 | 26.92 | 32.05 | -- | |||
GPT-5.4 mini (medium) | 400k | Proprietary | 20* | -- | 175 | 6.36 | 9.21 | -- | |||
Kimi K2.5 (Non-reasoning) | 262k | Open | 19* | -- | 140 | 1.38 | 4.96 | -- | |||
Claude 4.5 Sonnet (Non-reasoning) | 200k | Proprietary | 19* | -- | 41 | 1.80 | 13.91 | -- | |||
Claude 4.1 Opus (Non-reasoning) | 200k | Proprietary | 19* | -- | -- | -- | -- | -- | |||
Grok 4 Fast | 2M | Proprietary | 18* | -- | -- | -- | -- | -- | |||
Claude 4.5 Haiku | 200k | Proprietary | 18 | $0.57 | 86 | 22.52 | 28.36 | -- | |||
GPT-5 mini (high) | 400k | Proprietary | 17 | $0.05 | 127 | 57.28 | 61.21 | -- | |||
GPT-5.2 (Non-reasoning) | 400k | Proprietary | 17* | -- | 70 | 1.97 | 9.16 | -- | |||
o4-mini (high) | 200k | Proprietary | 17* | -- | 143 | 22.13 | 25.63 | -- | |||
DeepSeek V3.2 (Non-reasoning) | 128k | Open | 16* | -- | 161 | 1.79 | 4.90 | -- | |||
Claude 4.5 Haiku (Non-reasoning) | 200k | Proprietary | 15* | -- | 80 | 1.11 | 7.33 | -- | |||
o1 | 200k | Proprietary | 15* | -- | -- | -- | -- | -- | |||
Grok 3 mini Reasoning (high) | 32k | Proprietary | 15* | -- | -- | -- | -- | -- | |||
GPT-5.1 (Non-reasoning) | 400k | Proprietary | 13* | -- | 85 | 1.69 | 7.56 | -- | |||
GPT-5 nano (high) | 400k | Proprietary | 13* | -- | 141 | 87.84 | 91.39 | -- | |||
GPT-4.1 | 1M | Proprietary | 13* | -- | 102 | 2.15 | 7.04 | -- | |||
GPT-5 nano (medium) | 400k | Proprietary | 12* | -- | 115 | 41.86 | 46.20 | -- | |||
o3-mini | 200k | Proprietary | 12* | -- | 253 | 6.99 | 8.97 | -- | |||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 302 | 0.79 | 9.05 | 6.61 | |||
Grok 3 | 16k | Proprietary | 12* | -- | -- | -- | -- | -- | |||
GPT-5 (minimal) | 400k | Proprietary | 11* | -- | 90 | 1.56 | 7.11 | -- | |||
o1-preview | 128k | Proprietary | 11* | -- | -- | -- | -- | -- | |||
GPT-5.4 mini (Non-reasoning) | 400k | Proprietary | 11* | -- | 165 | 1.02 | 4.05 | -- | |||
Grok 4 Fast (Non-reasoning) | 2M | Proprietary | 11* | -- | -- | -- | -- | -- | |||
o3-mini (high) | 200k | Proprietary | 11 | -- | 224 | 19.84 | 22.07 | -- | |||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 341 | 0.79 | 8.13 | 5.87 | |||
GPT-4.1 mini | 1M | Proprietary | 10* | -- | 110 | 1.54 | 6.07 | -- | |||
GPT-5 mini (minimal) East US 2 - Global Standard | 400k | Proprietary | 10* | -- | -- | -- | -- | -- | |||
 Mistral Large 3 | 256k | Open | 10 | $0.10 | 64 | 1.41 | 9.16 | -- | |||
Llama 4 Maverick (FP8) | 128k | Open | 9 | $0.04 | 404 | 1.36 | 2.59 | -- | |||
Mistral Medium 3 | 128k | Proprietary | 9* | -- | 46 | 2.45 | 13.42 | -- | |||
GPT-4o (Nov) | 128k | Proprietary | 8* | -- | 122 | 2.40 | 6.51 | -- | |||
GPT-4.1 nano | 1M | Proprietary | 8* | -- | 215 | 1.84 | 4.17 | -- | |||
GPT-4o (Aug) | 128k | Proprietary | 8* | -- | 143 | 1.61 | 5.12 | -- | |||
Llama 3.3 70B | 128k | Open | 8* | -- | 121 | 2.22 | 6.34 | -- | |||
GPT-4o (May) | 128k | Proprietary | 7* | -- | 140 | 1.96 | 5.52 | -- | |||
GPT-5 nano (minimal) East US 2 - Global Standard | 400k | Proprietary | 7* | -- | -- | -- | -- | -- | |||
GPT-4 Turbo | 128k | Proprietary | 7* | -- | 133 | 1.90 | 5.66 | -- | |||
 Command A | 256k | Open | 7* | -- | 42 | 3.00 | 14.84 | -- | |||
GPT-4o mini | 128k | Proprietary | 7* | -- | 79 | 2.17 | 8.49 | -- | |||
Llama 4 Scout | 128k | Open | 6 | $0.12 | 113 | 0.91 | 5.34 | -- | |||
Phi-4 Mini | 128k | Open | 6* | -- | 44 | 0.87 | 12.12 | -- | |||
Phi-4 | 16.4k | Open | 6* | -- | 41 | 2.54 | 14.82 | -- | |||
Phi-4 Multimodal | 128k | Open | 6* | -- | 17 | 0.87 | 30.56 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Microsoft Azure
Microsoft Azure offers 79 models that we track: Claude Fable 5 (with fallback), GPT-5.6 Sol (max), GPT-5.6 Sol (xhigh), GPT-5.6 Sol (high), Claude Opus 4.7 (max), GPT-5.4 (xhigh), Claude Sonnet 5 (max), GPT-5.6 Terra (xhigh), GPT-5.5 (high), GPT-5.6 Luna (xhigh), GPT-5.6 Terra (high), GPT-5.6 Luna (high), Claude Opus 4.6 (max), Kimi K2.6, DeepSeek V4 Pro (max), Claude Sonnet 4.6 (max), GPT-5.2 (xhigh), DeepSeek V4 Pro (high), Claude Opus 4.5, GPT-5.2 Codex (xhigh), GPT-5.2 (medium), Claude Opus 4.6 (Non-reasoning, high), Grok 4.20 0309 v2, Grok 4.3 (high), GPT-5 Codex (high), Grok 4.3 (medium), GPT-5.1 (high), Claude Sonnet 4.6 (Non-reasoning, high), GPT-5.4 mini (xhigh), Grok 4.3 (low), GPT-5.1 Codex (high), Claude Opus 4.5 (Non-reasoning), Kimi K2.6 (Non-reasoning), Kimi K2.5, GPT-5 (high), GPT-5 (medium), Grok 4, Kimi K2 Thinking, Claude 4.5 Sonnet, DeepSeek V4 Pro (Non-reasoning), GPT-5 (low), GPT-5 mini (medium), GPT-5.1 Codex mini (high), o3, GPT-5.4 mini (medium), Kimi K2.5 (Non-reasoning), Claude 4.5 Sonnet (Non-reasoning), Claude 4.5 Haiku, GPT-5 mini (high), GPT-5.2 (Non-reasoning), o4-mini (high), DeepSeek V3.2 (Non-reasoning), Claude 4.5 Haiku (Non-reasoning), GPT-5.1 (Non-reasoning), GPT-5 nano (high), GPT-4.1, GPT-5 nano (medium), o3-mini, gpt-oss-120b (high), GPT-5 (minimal), GPT-5.4 mini (Non-reasoning), o3-mini (high), gpt-oss-120b (low), GPT-4.1 mini, Mistral Large 3, Llama 4 Maverick (FP8), Mistral Medium 3, GPT-4o (Nov), GPT-4.1 nano, GPT-4o (Aug), Llama 3.3 70B, GPT-4o (May), GPT-4 Turbo, Command A, GPT-4o mini, Llama 4 Scout, Phi-4 Mini, Phi-4, and Phi-4 Multimodal.
The most intelligent model available on Microsoft Azure is Claude Fable 5 (with fallback) with an Intelligence Index score of 50.
The fastest model on Microsoft Azure by output speed is Llama 4 Maverick (FP8) at 385.3 tokens per second.
The model with the lowest time to first answer token on Microsoft Azure is Phi-4 Mini at 0.85s. Lower latency means faster initial response time.
The most affordable model on Microsoft Azure by blended price is GPT-5 nano (high) at $0.05 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Microsoft Azure vary up to 262x across models, from $0.05 per 1M tokens for GPT-5 nano (high) to $14.00 per 1M tokens for Claude Fable 5 (with fallback).
Yes, Microsoft Azure offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
66 of 79 models on Microsoft Azure support JSON mode for structured output.
76 of 79 models on Microsoft Azure support function calling (tool use).
Yes, Microsoft Azure offers 49 reasoning models: Claude Fable 5 (with fallback), GPT-5.6 Sol (max), GPT-5.6 Sol (xhigh), GPT-5.6 Sol (high), Claude Opus 4.7 (max), GPT-5.4 (xhigh), Claude Sonnet 5 (max), GPT-5.6 Terra (xhigh), GPT-5.5 (high), GPT-5.6 Luna (xhigh), GPT-5.6 Terra (high), GPT-5.6 Luna (high), Claude Opus 4.6 (max), Kimi K2.6, DeepSeek V4 Pro (max), Claude Sonnet 4.6 (max), GPT-5.2 (xhigh), DeepSeek V4 Pro (high), Claude Opus 4.5, GPT-5.2 Codex (xhigh), GPT-5.2 (medium), Grok 4.20 0309 v2, Grok 4.3 (high), GPT-5 Codex (high), Grok 4.3 (medium), GPT-5.1 (high), GPT-5.4 mini (xhigh), Grok 4.3 (low), GPT-5.1 Codex (high), Kimi K2.5, GPT-5 (high), GPT-5 (medium), Grok 4, Kimi K2 Thinking, Claude 4.5 Sonnet, GPT-5 (low), GPT-5 mini (medium), GPT-5.1 Codex mini (high), o3, GPT-5.4 mini (medium), Claude 4.5 Haiku, GPT-5 mini (high), o4-mini (high), GPT-5 nano (high), GPT-5 nano (medium), o3-mini, gpt-oss-120b (high), o3-mini (high), and gpt-oss-120b (low). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, 19 of 79 models on Microsoft Azure are open weight models: Kimi K2.6, DeepSeek V4 Pro (max), DeepSeek V4 Pro (high), Kimi K2.6 (Non-reasoning), Kimi K2.5, Kimi K2 Thinking, DeepSeek V4 Pro (Non-reasoning), Kimi K2.5 (Non-reasoning), DeepSeek V3.2 (Non-reasoning), gpt-oss-120b (high), gpt-oss-120b (low), Mistral Large 3, Llama 4 Maverick (FP8), Llama 3.3 70B, Command A, Llama 4 Scout, Phi-4 Mini, Phi-4, and Phi-4 Multimodal.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Microsoft Azure, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.