AIHubMix Phi 3.5 Vision Instruct
Microsoft · text, image → text
Input$0.4 /M
Output$1.6 /M
← ModelsAIHubMix Phi 3.5 Vision InstructAihub Phi 4 Multimodal Instruct
AIHubMix Phi 3.5 Vision Instruct vs Aihub Phi 4 Multimodal Instruct
Compare AIHubMix Phi 3.5 Vision Instruct from Microsoft and Aihub Phi 4 Multimodal Instruct from Microsoft on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
AIHubMix Phi 3.5 Vision InstructAihub Phi 4 Multimodal Instruct+ Add model · 2/4
Aihub Phi 4 Multimodal Instruct
Microsoft · text, image, audio → text
Microsoft's latest model
Input$0.12 /M
Output$0.48 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
AIHubMix Phi 3.5 Vision Instruct
Aihub Phi 4 Multimodal Instruct
Input /M
$0.4
$0.12
Output /M
$1.6
$0.48
Cache read /M
-
-
Context length
0
0
Max output
0
0
Time to First Token
-
-
Throughput
-
-
Modalities
textimage
textimageaudio
Supported Parameters
API Formats
Released
-
-
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
ahm-Phi-3-5-vision-instructaihub-Phi-4-multimodal-instruct
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
ahm-Phi-3-5-vision-instructaihub-Phi-4-multimodal-instruct
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
Aihub Phi 4 Multimodal Instruct
$14.40 /mo
AIHubMix Phi 3.5 Vision Instruct
$48.00 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: AIHubMix Phi 3.5 Vision Instruct, Aihub Phi 4 Multimodal Instruct?
Aihub Phi 4 Multimodal Instruct: $0.48/M output tokens; AIHubMix Phi 3.5 Vision Instruct: $1.6/M. Use the cost calculator above to estimate your own workload.
What inputs and capabilities does each model support?
AIHubMix Phi 3.5 Vision Instruct accepts text and image input; Aihub Phi 4 Multimodal Instruct accepts text, image and audio input.
Can I call AIHubMix Phi 3.5 Vision Instruct and Aihub Phi 4 Multimodal Instruct with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
