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
Claude Opus 5.5 (max with fallback)Claude Sonnet 5.5 (max with fallback)
GPT-6 Astra (max)GPT-6.1 Sol (max)Claude Fable 5 (with fallback)Intelligence Index
Total 77 models
Fastest
gpt-oss-120b (low)gpt-oss-120b (high)GPT-4.1 nano
Llama 4 Maverick (FP8)
Kimi K2.6Output speed
Total 77 models
Lowest Price
GPT-5 nano (high)GPT-6 Luna (max)GPT-6 Luna (non-reasoning)GPT-4.1 nanoPhi-4 MiniBlended price (per 1M tokens)
Total 77 models
Azure offers 77 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 Opus 5.5 (max with fallback) (58), Claude Sonnet 5.5 (max with fallback) (56), and GPT-6 Astra (max) (53).
- For output speed, the fastest models are gpt-oss-120b (low) (418 t/s), gpt-oss-120b (high) (372 t/s), and GPT-4.1 nano (294 t/s). Speed varies significantly across models, with a 74% difference between the fastest and slowest.
- For latency, Phi-4 Mini (0.81s), Llama 4 Scout (0.83s), and Claude 4.5 Haiku (non-reasoning) (0.86s) offer the lowest time to first answer token.
- For pricing, GPT-5 nano (high) ($0.05), GPT-6 Luna (max) ($0.08), and GPT-6 Luna (non-reasoning) ($0.08) offer the lowest blended prices per 1M tokens.
- For context window size, GPT-6 Sol (max) (1M), GPT-5.4 (xhigh) (1M), and GPT-6.1 Sol (max) (1M) support the largest context windows on Azure.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, Elo
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Agentic interactive 3D experiences, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
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
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
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 Opus 5.5 (max with fallback) | 1M | Proprietary | 58 | $6.70 | 97 | 633.94 | 639.11 | -- | |||
Claude Sonnet 5.5 (max with fallback) | 1M | Proprietary | 56 | $4.96 | 129 | 402.88 | 406.76 | -- | |||
GPT-6 Astra (max) | 524k | Proprietary | 53 | $3.35 | 60 | 288.31 | 296.61 | -- | |||
GPT-6.1 Sol (max) | 1.05M | Proprietary | 52 | $0.73 | 45 | 321.18 | 332.18 | -- | |||
Claude Fable 5 (with fallback) | 1M | Proprietary | 50 | $8.50 | 65 | 80.55 | 88.29 | -- | |||
GPT-6 Sol (max) | 1.05M | Proprietary | 48 | $1.06 | 125 | 79.93 | 83.91 | -- | |||
GPT-5.6 Sol (max) | 524k | Proprietary | 47 | $2.02 | 107 | 83.74 | 88.40 | -- | |||
GPT-6 Astra (low) | 524k | Proprietary | 46 | $0.84 | 56 | 2.52 | 11.49 | -- | |||
GPT-5.6 Sol (xhigh) | 524k | Proprietary | 44 | $1.34 | -- | -- | -- | -- | |||
GPT-5.6 Sol (high) | 524k | Proprietary | 42 | $0.90 | -- | -- | -- | -- | |||
Claude Opus 5.5 (low with fallback) | 1M | Proprietary | 42 | $0.59 | 72 | 6.55 | 13.48 | -- | |||
Claude Opus 4.7 (max) | 1M | Proprietary | 41* | -- | 53 | 21.04 | 30.50 | -- | |||
GPT-5.4 (xhigh) | 1.05M | Proprietary | 39* | -- | 118 | 148.40 | 152.63 | -- | |||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $4.75 | 78 | 208.80 | 215.18 | -- | |||
GPT-6 Luna (max) | 524k | Proprietary | 38 | $0.07 | 136 | 95.07 | 98.76 | -- | |||
GPT-5.6 Terra (xhigh) | 524k | Proprietary | 38 | $0.71 | 130 | 10.96 | 14.81 | -- | |||
GPT-5.5 (high) | 524k | Proprietary | 37 | $1.13 | 98 | 18.63 | 23.73 | -- | |||
Claude Sonnet 5.5 (low with fallback) | 1M | Proprietary | 36 | $0.33 | 97 | 0.85 | 6.03 | -- | |||
GPT-5.6 Luna (xhigh) | 524k | Proprietary | 35 | $0.10 | 181 | 30.80 | 33.57 | -- | |||
GPT-5.6 Terra (high) | 524k | Proprietary | 34 | $0.37 | 121 | 2.22 | 6.37 | -- | |||
GPT-6 Luna (high) | 524k | Proprietary | 33 | $0.03 | -- | -- | -- | -- | |||
GPT-5.6 Luna (high) | 524k | Proprietary | 32 | $0.05 | 184 | 8.65 | 11.37 | -- | |||
Claude Opus 4.6 (max) | 1M | Proprietary | 32* | -- | 41 | 12.65 | 24.95 | -- | |||
 DeepSeek V4 Pro (max) | 1M | Open | 30 | $9.65 | 153 | 1.70 | 33.53 | 28.57 | |||
GPT-5.2 (xhigh) | 400k | Proprietary | 30* | -- | 100 | 74.83 | 79.85 | -- | |||
DeepSeek V4 Pro (high) | 1M | Open | 30* | -- | -- | -- | -- | -- | |||
Claude Sonnet 4.6 (max) | 200k | Proprietary | 30 | $2.70 | 57 | 133.04 | 141.82 | -- | |||
Claude Opus 4.5 | 200k | Proprietary | 29* | -- | 52 | 16.48 | 26.05 | -- | |||
GPT-5.2 Codex (xhigh) | 400k | Proprietary | 29* | -- | 97 | 85.48 | 90.62 | -- | |||
Kimi K2.6 | 262k | Open | 27 | $1.91 | 226 | 1.48 | 23.39 | 19.70 | |||
GPT-5.2 (medium) | 400k | Proprietary | 27* | -- | -- | -- | -- | -- | |||
Claude Opus 4.6 (non-reasoning, high) | 1M | Proprietary | 26* | -- | 39 | 1.99 | 14.84 | -- | |||
 Grok 4.20 0309 v2 | 262k | Proprietary | 26* | -- | 146 | 13.66 | 17.09 | -- | |||
GPT-5 Codex (high) | 400k | Proprietary | 25* | -- | 160 | 8.47 | 11.59 | -- | |||
Grok 4.3 (high) | 200k | Proprietary | 25 | $0.53 | 168 | 18.66 | 21.63 | -- | |||
Grok 4.3 (medium) | 200k | Proprietary | 25* | -- | -- | -- | -- | -- | |||
GPT-5.1 (high) | 400k | Proprietary | 25* | -- | 96 | 44.78 | 49.97 | -- | |||
Claude Sonnet 4.6 (non-reasoning, high) | 200k | Proprietary | 25* | -- | 43 | 1.55 | 13.21 | -- | |||
Grok 4.3 (low) | 200k | Proprietary | 24* | -- | -- | -- | -- | -- | |||
GPT-5.4 mini (xhigh) | 400k | Proprietary | 24 | $0.43 | 230 | 147.83 | 150.01 | -- | |||
GPT-5.1 Codex (high) | 400k | Proprietary | 24* | -- | 126 | 6.56 | 10.52 | -- | |||
Claude Opus 4.5 (non-reasoning) | 200k | Proprietary | 24* | -- | 49 | 1.40 | 11.70 | -- | |||
Kimi K2.6 (non-reasoning) | 262k | Open | 24* | -- | 231 | 1.75 | 3.91 | -- | |||
Kimi K2.5 | 262k | Open | 23* | -- | 200 | 2.29 | 19.61 | 14.82 | |||
GPT-5 (high) | 400k | Proprietary | 23* | -- | 90 | 54.92 | 60.48 | -- | |||
GPT-5 (medium) | 400k | Proprietary | 23* | -- | -- | -- | -- | -- | |||
Claude 4.1 Opus | 200k | Proprietary | 23* | -- | -- | -- | -- | -- | |||
Grok 4 | 256k | Proprietary | 22* | -- | 71 | 7.76 | 14.79 | -- | |||
Kimi K2 Thinking | 256k | Open | 22* | -- | 166 | 2.16 | 17.24 | 12.06 | |||
o3-pro | 200k | Proprietary | 22* | -- | -- | -- | -- | -- | |||
DeepSeek V4 Pro (non-reasoning) | 1M | Open | 21* | -- | 175 | 1.84 | 4.69 | -- | |||
GPT-5 (low) | 400k | Proprietary | 21* | -- | -- | -- | -- | -- | |||
Claude 4.5 Sonnet | 200k | Proprietary | 21 | $0.54 | 51 | 12.49 | 22.37 | -- | |||
GPT-5 mini (medium) | 400k | Proprietary | 21* | -- | -- | -- | -- | -- | |||
GPT-5.1 Codex mini (high) | 400k | Proprietary | 20* | -- | 174 | 10.83 | 13.70 | -- | |||
o3 | 200k | Proprietary | 20* | -- | 96 | 28.29 | 33.51 | -- | |||
GPT-5.4 mini (medium) | 400k | Proprietary | 20* | -- | -- | -- | -- | -- | |||
Kimi K2.5 (non-reasoning) | 262k | Open | 19* | -- | 178 | 1.58 | 4.38 | -- | |||
Claude 4.5 Sonnet (non-reasoning) | 200k | Proprietary | 19* | -- | 44 | 1.45 | 12.71 | -- | |||
Claude 4.1 Opus (non-reasoning) | 200k | Proprietary | 19* | -- | -- | -- | -- | -- | |||
GPT-6 Luna (non-reasoning) | 524k | Proprietary | 18 | $0.01 | 122 | 1.31 | 5.41 | -- | |||
Grok 4 Fast | 2M | Proprietary | 18* | -- | -- | -- | -- | -- | |||
GPT-5.2 (non-reasoning) | 400k | Proprietary | 17* | -- | 89 | 2.07 | 7.72 | -- | |||
Claude 4.5 Haiku | 200k | Proprietary | 17 | $0.22 | 92 | 23.42 | 28.87 | -- | |||
GPT-5 mini (high) | 400k | Proprietary | 17 | $0.05 | 143 | 50.07 | 53.58 | -- | |||
o4-mini (high) | 200k | Proprietary | 17* | -- | 148 | 19.31 | 22.69 | -- | |||
DeepSeek V3.2 (non-reasoning) | 128k | Open | 16* | -- | 178 | 1.82 | 4.64 | -- | |||
Claude 4.5 Haiku (non-reasoning) | 200k | Proprietary | 15* | -- | 84 | 0.91 | 6.85 | -- | |||
o1 | 200k | Proprietary | 15* | -- | -- | -- | -- | -- | |||
Grok 3 mini Reasoning (high) | 32k | Proprietary | 15* | -- | -- | -- | -- | -- | |||
GPT-5.1 (non-reasoning) | 400k | Proprietary | 13* | -- | 91 | 1.25 | 6.77 | -- | |||
GPT-5 nano (high) | 400k | Proprietary | 13* | -- | 206 | 58.68 | 61.11 | -- | |||
GPT-4.1 | 1M | Proprietary | 13* | -- | 119 | 1.46 | 5.68 | -- | |||
GPT-5 nano (medium) | 400k | Proprietary | 12* | -- | -- | -- | -- | -- | |||
o3-mini | 200k | Proprietary | 12* | -- | 219 | 6.52 | 8.81 | -- | |||
Grok 3 | 16k | Proprietary | 12* | -- | -- | -- | -- | -- | |||
gpt-oss-120b (high) | 131k | Open | 12 | $0.11 | 371 | 0.77 | 7.51 | 5.39 | |||
GPT-5 (minimal) | 400k | Proprietary | 11* | -- | 95 | 1.52 | 6.77 | -- | |||
o1-preview | 128k | Proprietary | 11* | -- | -- | -- | -- | -- | |||
GPT-5.4 mini (non-reasoning) | 400k | Proprietary | 11* | -- | 183 | 1.20 | 3.94 | -- | |||
Grok 4 Fast (non-reasoning) | 2M | Proprietary | 11* | -- | -- | -- | -- | -- | |||
o3-mini (high) | 200k | Proprietary | 11 | -- | 224 | 17.70 | 19.94 | -- | |||
gpt-oss-120b (low) | 131k | Open | 10* | -- | 395 | 0.91 | 7.24 | 5.07 | |||
GPT-4.1 mini | 1M | Proprietary | 10* | -- | 107 | 1.35 | 6.03 | -- | |||
GPT-5 mini (minimal) East US 2 - Global Standard | 400k | Proprietary | 10* | -- | -- | -- | -- | -- | |||
Llama 4 Maverick (FP8) | 128k | Open | 9 | $0.04 | 322 | 1.27 | 2.82 | -- | |||
 Mistral Large 3 | 256k | Open | 9 | $0.10 | 73 | 1.70 | 8.56 | -- | |||
Mistral Medium 3 | 128k | Proprietary | 9* | -- | 47 | 2.24 | 12.89 | -- | |||
GPT-4o (Nov) | 128k | Proprietary | 8* | -- | 147 | 1.89 | 5.29 | -- | |||
GPT-4.1 nano | 1M | Proprietary | 8* | -- | 291 | 1.11 | 2.83 | -- | |||
GPT-4o (Aug) | 128k | Proprietary | 8* | -- | 141 | 1.46 | 5.01 | -- | |||
Llama 3.3 70B | 128k | Open | 8* | -- | 128 | 2.09 | 5.98 | -- | |||
GPT-4o (May) | 128k | Proprietary | 7* | -- | 163 | 1.56 | 4.63 | -- | |||
GPT-5 nano (minimal) East US 2 - Global Standard | 400k | Proprietary | 7* | -- | -- | -- | -- | -- | |||
GPT-4 Turbo | 128k | Proprietary | 7* | -- | 111 | 1.65 | 6.16 | -- | |||
 Command A | 256k | Open | 7* | -- | 41 | 3.08 | 15.20 | -- | |||
GPT-4o mini | 128k | Proprietary | 7* | -- | 85 | 1.76 | 7.64 | -- | |||
Llama 4 Scout | 128k | Open | 6 | $0.12 | 133 | 0.84 | 4.60 | -- | |||
Phi-4 Mini | 128k | Open | 6* | -- | 46 | 0.81 | 11.74 | -- | |||
Phi-4 | 16.4k | Open | 6* | -- | 40 | 2.67 | 15.12 | -- | |||
Phi-4 Multimodal | 4.1k | Open | 6* | -- | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Microsoft Azure
Microsoft Azure offers 77 models that we track: Claude Opus 5.5 (max with fallback), Claude Sonnet 5.5 (max with fallback), GPT-6 Astra (max), GPT-6.1 Sol (max), Claude Fable 5 (with fallback), GPT-6 Sol (max), GPT-5.6 Sol (max), GPT-6 Astra (low), Claude Opus 5.5 (low with fallback), Claude Opus 4.7 (max), GPT-5.4 (xhigh), Claude Sonnet 5 (max), GPT-6 Luna (max), GPT-5.6 Terra (xhigh), GPT-5.5 (high), Claude Sonnet 5.5 (low with fallback), GPT-5.6 Luna (xhigh), GPT-5.6 Terra (high), GPT-5.6 Luna (high), Claude Opus 4.6 (max), DeepSeek V4 Pro (max), GPT-5.2 (xhigh), Claude Sonnet 4.6 (max), Claude Opus 4.5, GPT-5.2 Codex (xhigh), Kimi K2.6, Claude Opus 4.6 (non-reasoning, high), Grok 4.20 0309 v2, GPT-5 Codex (high), Grok 4.3 (high), GPT-5.1 (high), Claude Sonnet 4.6 (non-reasoning, high), GPT-5.4 mini (xhigh), GPT-5.1 Codex (high), Claude Opus 4.5 (non-reasoning), Kimi K2.6 (non-reasoning), Kimi K2.5, GPT-5 (high), Grok 4, Kimi K2 Thinking, DeepSeek V4 Pro (non-reasoning), Claude 4.5 Sonnet, GPT-5.1 Codex mini (high), o3, Kimi K2.5 (non-reasoning), Claude 4.5 Sonnet (non-reasoning), GPT-6 Luna (non-reasoning), GPT-5.2 (non-reasoning), Claude 4.5 Haiku, GPT-5 mini (high), 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, 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, Llama 4 Maverick (FP8), Mistral Large 3, 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, and Phi-4.
The most intelligent model available on Microsoft Azure is Claude Opus 5.5 (max with fallback) with an Intelligence Index score of 58.
The fastest model on Microsoft Azure by output speed is gpt-oss-120b (low) at 418.3 tokens per second.
The model with the lowest time to first answer token on Microsoft Azure is Phi-4 Mini at 0.81s. 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 224x across models, from $0.05 per 1M tokens for GPT-5 nano (high) to $12.00 per 1M tokens for GPT-4 Turbo.
Yes, Microsoft Azure offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
60 of 77 models on Microsoft Azure support JSON mode for structured output.
75 of 77 models on Microsoft Azure support function calling (tool use).
Yes, Microsoft Azure offers 47 reasoning models: Claude Opus 5.5 (max with fallback), Claude Sonnet 5.5 (max with fallback), GPT-6 Astra (max), GPT-6.1 Sol (max), Claude Fable 5 (with fallback), GPT-6 Sol (max), GPT-5.6 Sol (max), GPT-6 Astra (low), Claude Opus 5.5 (low with fallback), Claude Opus 4.7 (max), GPT-5.4 (xhigh), Claude Sonnet 5 (max), GPT-6 Luna (max), GPT-5.6 Terra (xhigh), GPT-5.5 (high), Claude Sonnet 5.5 (low with fallback), GPT-5.6 Luna (xhigh), GPT-5.6 Terra (high), GPT-5.6 Luna (high), Claude Opus 4.6 (max), DeepSeek V4 Pro (max), GPT-5.2 (xhigh), Claude Sonnet 4.6 (max), Claude Opus 4.5, GPT-5.2 Codex (xhigh), Kimi K2.6, Grok 4.20 0309 v2, GPT-5 Codex (high), Grok 4.3 (high), GPT-5.1 (high), GPT-5.4 mini (xhigh), GPT-5.1 Codex (high), Kimi K2.5, GPT-5 (high), Grok 4, Kimi K2 Thinking, Claude 4.5 Sonnet, GPT-5.1 Codex mini (high), o3, Claude 4.5 Haiku, GPT-5 mini (high), o4-mini (high), GPT-5 nano (high), 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, 17 of 77 models on Microsoft Azure are open weight models: DeepSeek V4 Pro (max), Kimi K2.6, 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), Llama 4 Maverick (FP8), Mistral Large 3, Llama 3.3 70B, Command A, Llama 4 Scout, Phi-4 Mini, and Phi-4.
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.