Providers/Azure AI

Azure AI

Cloud platform · azure.microsoft.com

Azure AI models via API.

Models
131
Endpoints
13
Regions
8
Avg input
$26.38
Auth
API key
SDKs
1

Endpoints

POST/v1/audio/speechSpeechStream
POST/v1/audio/transcriptionsTranscriptions-
POST/v1/batchBatch-
POST/v1/batchesBatches-
POST/v1/chat/completionsCompletionsStream
POST/v1/embeddingsEmbeddings-
POST/v1/images/editsEdits-
POST/v1/images/generationsGenerations-
POST/v1/messagesMessagesStream
POST/v1/moderationsModerations-
POST/v1/ocrOcr-
POST/v1/rerankRerank-
POST/v1/responsesResponsesStream

Models · 131

ModelContextInputOutputCapabilities
gpt-6-astra922K$10.00$50.00ReasoningVisionToolsclaude-fable-5-11M$10.00$50.00ReasoningVisionToolsgrok-4.6200K$2.00$6.00ReasoningVisionToolsDeepSeek-V4-Flash-0731Open1M$0.44$1.32ReasoningToolsclaude-opus-51M$5.00$25.00ReasoningVisionToolsclaude-sonnet-51M$2.00$10.00ReasoningVisionToolskimi-k2.7-codeOpen262K$0.95$4.00ReasoningVisionToolsclaude-fable-51M$10.00$50.00ReasoningVisionToolsclaude-opus-4-81M$5.00$25.00ReasoningVisionToolsgpt-chat-latest272K$5.00$30.00ReasoningVisionToolsgrok-4.3200K$1.25$2.50ReasoningVisionToolsdeepseek-v4-flashOpen1M$0.19$0.51ReasoningToolsdeepseek-v4-proOpen1M$1.74$3.48ReasoningToolsgpt-5.51.1M$5.00$30.00ReasoningVisionToolsgpt-5.5-2026-04-231.1M$5.00$30.00ReasoningVisionToolsgpt-5.5-2026-04-241.1M$5.00$30.00ReasoningVisionToolskimi-k2.6Open262K$0.95$4.00ReasoningVisionToolsclaude-opus-4-71M$5.00$25.00ReasoningVisionToolsgpt-5.4-mini272K$0.75$4.50ReasoningVisionToolsgpt-5.4-mini-2026-03-17272K$0.75$4.50ReasoningVisionToolsgpt-5.4-nano272K$0.20$1.25ReasoningVisionToolsgpt-5.4-nano-2026-03-17272K$0.20$1.25ReasoningVisionToolsgpt-5.41.1M$2.50$15.00ReasoningVisionToolsgpt-5.4-2026-03-051.1M$2.50$15.00ReasoningVisionToolsgpt-5.4-pro1.1M$30.00$180.00ReasoningVisionToolsgpt-5.4-pro-2026-03-051.1M$30.00$180.00ReasoningVisionToolsclaude-sonnet-4-61M$3.00$15.00ReasoningVisionToolsclaude-opus-4-61M$5.00$25.00ReasoningVisionToolskimi-k2.5Open262K$0.60$3.00VisionToolsdeepseek-v3.2Open164K$0.58$1.68ReasoningToolsclaude-opus-4-5200K$5.00$25.00ReasoningVisionToolsclaude-haiku-4-5200K$1.00$5.00ReasoningVisionToolsclaude-sonnet-4-5200K$3.00$15.00ReasoningVisionToolsclaude-opus-4-1200K$15.00$75.00ReasoningVisionToolsgpt-oss-120bOpen131K$0.15$0.60ToolsJSONLlama-4-Scout-17B-16E-InstructOpen10M$0.20$0.78VisionToolsdeepseek-r1Open128K$1.35$5.40ReasoningToolsPhi-4Open16K$0.13$0.50ToolsLlama-3.3-70B-InstructOpen128K$0.71$0.71Toolsmistral-large-2407128K$2.00$6.00Toolsmistral-nemoOpen131K$0.15$0.15Toolsmistral-large32K$4.00$12.00ToolsCodestral-2501256K$0.30$0.90Cohere-embed-v3-english512$0.10$0.00EmbeddingsCohere-embed-v3-multilingual512$0.10$0.00EmbeddingsCohere-parse-v50$0.00-FLUX-1.1-pro0$0.00-Image genFLUX.1-Kontext-pro0$0.00-Image genFLUX.2-flex32K$0.00-Image genFW-DeepSeek-V3.2Open164K$0.62$1.85ReasoningToolsFW-DeepSeek-V4-ProOpen1M$1.93$3.83ReasoningToolsFW-GLM-5200K$1.10$3.52ReasoningToolsFW-GLM-5.1203K$1.54$4.84ReasoningToolsFW-GLM-5.21.0M$1.54$4.84ReasoningToolsFW-GLM-5.2-Fast1.0M$2.31$7.26ReasoningToolsFW-Inkling1.0M$1.10$4.46ReasoningToolsFW-Kimi-K2.5Open262K$0.66$3.30ReasoningVisionToolsFW-Kimi-K2.6Open262K$1.04$4.40ReasoningVisionToolsFW-Kimi-K2.7-CodeOpen262K$1.05$4.40ReasoningVisionToolsFW-Kimi-K3Open1.0M$3.00$15.00ReasoningVisionToolsFW-MiniMax-M2.5Open1M$0.33$1.32ReasoningToolsFW-MiniMax-M3Open512K$0.33$1.32ReasoningVisionToolsFW-Nemotron-3-Ultra-NVFP4Open262K$0.66$2.64ReasoningToolsFW-Nemotron-Lightning-3.5-30B-A3BOpen262K$0.06$0.22ReasoningToolsLlama-3.2-11B-Vision-InstructOpen128K$0.37$0.37VisionToolsLlama-3.2-90B-Vision-InstructOpen128K$2.04$2.04VisionToolsLlama-4-Maverick-17B-128E-Instruct-FP8Open1M$0.25$1.00VisionToolsMAI-DS-R1128K$1.35$5.40ReasoningToolsMAI-Image-2.50$5.00-Image genMAI-Image-2.5-Flash0$1.75-Image genMAI-Image-2e0$5.00-Image genMAI-Thinking-1256K$2.00$8.00ReasoningToolsMeta-Llama-3-70B-InstructOpen8K$1.10$0.37ToolsMeta-Llama-3.1-405B-InstructOpen128K$5.33$16.00ToolsMeta-Llama-3.1-70B-InstructOpen128K$2.68$3.54ToolsMeta-Llama-3.1-8B-InstructOpen128K$0.30$0.61ToolsPhi-3-medium-128k-instructOpen128K$0.17$0.68ToolsPhi-3-medium-4k-instructOpen4K$0.17$0.68ToolsPhi-3-mini-128k-instructOpen128K$0.13$0.52ToolsPhi-3-mini-4k-instructOpen4K$0.13$0.52ToolsPhi-3-small-128k-instructOpen128K$0.15$0.60ToolsPhi-3-small-8k-instructOpen8K$0.15$0.60ToolsPhi-3.5-MoE-instructOpen128K$0.16$0.64ToolsPhi-3.5-mini-instructOpen128K$0.13$0.52ToolsPhi-3.5-vision-instructOpen128K$0.13$0.52VisionToolsPhi-4-mini-instructOpen131K$0.07$0.30ToolsPhi-4-mini-reasoningOpen131K$0.07$0.30ToolsPhi-4-multimodal-instructOpen131K$0.08$0.32VisionToolsAudioPhi-4-reasoningOpen33K$0.13$0.50ReasoningToolscodex-mini200K$1.50$6.00ReasoningVisionToolscohere-command-a131K$2.50$10.00Toolscohere-rerank-v3-english4K$0.00$0.00cohere-rerank-v3-multilingual4K$0.00$0.00cohere-rerank-v3.54K$0.00$0.00cohere-rerank-v4.0-fast33K$0.00$0.00cohere-rerank-v4.0-pro33K$0.00$0.00deepseek-v3Open128K$1.14$4.56Toolsdeepseek-v3-0324Open128K$1.14$4.56Toolsdeepseek-v3.1Open131K$1.23$4.94ReasoningToolsdeepseek-v3.2-specialeOpen164K$0.58$1.68ReasoningToolsembed-v-4-0128K$0.12$0.00Embeddingsflux.2-pro0$0.00-Image gengrok-3131K$3.00$15.00Toolsgrok-3131K$3.00$15.00Toolsgrok-3-mini131K$0.25$1.27ReasoningToolsgrok-3-mini131K$0.25$1.27ReasoningToolsgrok-4131K$3.00$15.00ToolsJSONgrok-4-1-fast-non-reasoning131K$0.20$0.50ToolsJSONgrok-4-1-fast-reasoning131K$0.20$0.50ReasoningToolsJSONgrok-4-20-non-reasoning262K$1.25$2.50VisionToolsJSONgrok-4-20-reasoning262K$1.25$2.50ReasoningVisionToolsgrok-4-fast-non-reasoning131K$0.20$0.50ToolsJSONgrok-4-fast-reasoning131K$0.20$0.50ToolsJSONgrok-code-fast-1131K$0.20$1.50ToolsJSONjais-30b-chat8K$3200.00$9710.00jamba-instructOpen70K$0.50$0.70Toolsministral-3bOpen128K$0.04$0.04Toolsmistral-document-ai-25050$0.00-mistral-document-ai-25120$0.00-mistral-large-3256K$0.50$1.50VisionToolsmistral-large-latest128K$2.00$6.00Toolsmistral-medium-2505131K$0.40$2.00Toolsmistral-ocr-4-00$0.00-mistral-small32K$1.00$3.00Toolsmistral-small-2503128K$0.10$0.30VisionToolsmodel-router200K$0.14$0.00model_router200K$0.14$0.00prebuilt-document0$0.00-prebuilt-layout0$0.00-prebuilt-read0$0.00-whisper0$0.00-

Release timeline

Jul 2026
claude-opus-5
Jul 2026
DeepSeek-V4-Flash-0731
Aug 2026
grok-4.6
Sep 2026
claude-fable-5-1
Sep 2026
gpt-6-astra

Details

CategoryCloud platform
AuthAPI key
Regions8

Regions

eastuseastus2japaneastnortheuropeswedencentraluksouthwesteuropewestus3

SDKs

Pythondocs ↗
pip install azure-ai-inference