Phi-4-multimodal-instruct
azure_ai · chat model
Phi-4-multimodal-instruct is listed here as a chat model from azure_ai. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.0800 / 1M tokens
Output
$0.3200 / 1M tokens
Cached input
N/A
Context
4.1K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.0800 / 1M tokens |
| Output | $0.3200 / 1M tokens |
| Audio input | $4.0000 / 1M tokens |
| Embedding | $0.0800 / 1M tokens |
Token limits
Context window
4.1K
Max input tokens
131.1K
Max output tokens
4.1K
Max tokens
4.1K
Capabilities
| Capability | Supported |
|---|---|
| Vision | ✅ |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | — |
| Prompt caching | — |
| Reasoning | — |
| Response schema | — |
| System messages | — |
| Audio input | ✅ |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| MMLU | 84.8 | Popular Aggregated Benchmark | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| GPQA | 56.1 | Science | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| HumanEval | 82.6 | Code Generation | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| DROP | 75.5 | Reasoning | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| MMLU | 84.8 | Popular Aggregated Benchmark | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| GPQA | 56.1 | Science | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| HumanEval | 82.6 | Code Generation | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| SimpleQA | 3.0 | Factual Knowledge | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
| DROP | 75.5 | Reasoning | Base model: Phi-4 (phi-4 (14B)) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| Phi-4-multimodal-instruct azure_ai | In $0.0800 / 1M tokens Out $0.3200 / 1M tokens | audioimagetext
Output: text | VisionFunction callingAudio input | 4.1K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| meta.llama3-2-11b-instruct-v1:0 Bedrock | In $0.3500 / 1M tokens Out $0.3500 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 4.1K | Text + image covered Overall 76% |
| us.meta.llama3-2-11b-instruct-v1:0 Bedrock | In $0.3500 / 1M tokens Out $0.3500 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 4.1K | Text + image covered Overall 76% |
| gemini-2.0-flash-lite vercel_ai_gateway | In $0.0750 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext video
Output: text | VisionFunction calling | 8.2K | Text + image covered Overall 70% |
| llama-4-scout vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 8.2K | Text + image covered Overall 70% |
| mistral-small vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext
Output: text | Function calling | 4.0K | Text + image covered Overall 69% |
| Phi-4-mini-reasoning azure_ai | In $0.0800 / 1M tokens Out $0.3200 / 1M tokens | audioimagetext
Output: text | Function calling | 4.1K | Same provider Overall 67% Missing image |
| Phi-4-mini-instruct azure_ai | In $0.0750 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext
Output: text | Function calling | 4.1K | Same provider Overall 66% Missing image |
| meta.llama3-2-90b-instruct-v1:0 Bedrock | In $2.0000 / 1M tokens Out $2.0000 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 4.1K | Text + image covered Overall 66% |
| us.meta.llama3-2-90b-instruct-v1:0 Bedrock | In $2.0000 / 1M tokens Out $2.0000 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 4.1K | Text + image covered Overall 66% |
| Phi-3.5-vision-instruct azure_ai | In $0.1300 / 1M tokens Out $0.5200 / 1M tokens | audioimagetext
Output: text | Vision | 4.1K | Same provider Overall 66% |
| gemini-2.0-flash Google | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | audioimagetext urlvideo
Output: text | VisionFunction callingAudio input | 8.2K | Text + image covered Overall 65% |
| gemini-2.0-flash vertex_ai-language-models | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | audioimagetext urlvideo
Output: text | VisionFunction callingAudio input | 8.2K | Text + image covered Overall 64% |
| Llama-3.2-11B-Vision-Instruct azure_ai | In $0.3700 / 1M tokens Out $0.3700 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 2.0K | Same provider Overall 63% |
| mistral-small-2503 azure_ai | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 128.0K | Same provider Overall 62% |
| eu.amazon.nova-lite-v1:0 bedrock_converse | In $0.0780 / 1M tokens Out $0.3120 / 1M tokens | audioimagetext pdfvideo
Output: text | VisionFunction calling | 10.0K | Text + image covered Overall 62% |
| Llama-4-Maverick-17B-128E-Instruct-FP8 azure_ai | In $1.4100 / 1M tokens Out $0.3500 / 1M tokens | audioimagetext
Output: text | VisionFunction calling | 16.4K | Same provider Overall 59% |
| Llama-4-Scout-17B-16E-Instruct deepinfra | In $0.0800 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext
Output: text | Function calling | 327.7K | Text + image covered Overall 58% |
| gemini-2.0-flash-lite vertex_ai-language-models | In $0.0750 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext video
Output: text | VisionFunction calling | N/A | Text + image covered Overall 58% |
| gemini-2.0-flash-lite-001 vertex_ai-language-models | In $0.0750 / 1M tokens Out $0.3000 / 1M tokens | audioimagetext video
Output: text | VisionFunction calling | N/A | Text + image covered Overall 58% |
| gemini-2.5-flash vercel_ai_gateway | In $0.3000 / 1M tokens Out $2.5000 / 1M tokens | audioimagetext video
Output: text | VisionFunction calling | 65.5K | Text + image covered Overall 49% |
| mimo-v2.5 OpenRouter | In $0.4000 / 1M tokens Out $2.0000 / 1M tokens | audioimagetext video
Output: text | VisionFunction callingAudio input | 131.1K | Text + image covered Overall 47% |
| gemini-3.1-flash-live-preview Google | In $0.7500 / 1M tokens Out $4.5000 / 1M tokens | audioimagetext video
Output: audio, text | VisionFunction callingAudio input | 65.5K | Text + image covered Overall 44% |
| gemini-3.1-flash-live-preview Google | In $0.7500 / 1M tokens Out $4.5000 / 1M tokens | audioimagetext video
Output: audio, text | VisionFunction callingAudio input | 65.5K | Text + image covered Overall 44% |
| gemini-2.5-flash replicate | In $2.5000 / 1M tokens Out $2.5000 / 1M tokens | audioimagetext video
Output: text | VisionFunction calling | N/A | Text + image covered Overall 43% |
No models match this filter.