Phi 3.5 Vision Instruct
Phi 3.5 Vision Instruct is a released long context and vision model with open-source and 128k context; evaluate it while provider pricing coverage matures.
Use it for
- Teams evaluating long context and vision
- Workloads that can use a 128k context window
Do not use it for
- Cost-sensitive launches that need sourced token pricing
- Strict JSON or tool-calling flows
- Teams that need a tracked hosted API route today
Advancing the state-of-the-art in AI and computing.
No tracked provider token pricing is available yet.
About
Phi 3.5 Vision Instruct is Microsoft Research's Phi-3 model with multimodal text and image input. It offers a 128K-token context window with weights openly available for self-hosting and scores 43 on MMMU.
Phi 3.5 Vision Instruct is an open-source model in the Phi-3 family. The structured metadata tracks a 128k-token context window and multimodal input. Headline tracked benchmarks include Massive Multi-discipline Multimodal Understanding 43.0.
Top use-case fit
Long context
Included by capability and metadata signals in the decision map.
Vision
1 relevant benchmark in the decision map.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
Benchmark peer barsfor Vision
Benchmark scores(1)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Massive Multi-discipline Multimodal Understanding | 43.0 | —Observed 2026-04-15 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Compare Phi 3.5 Vision Instruct with other models
Frequently asked questions
What is the context window of Phi 3.5 Vision Instruct?
Phi 3.5 Vision Instruct has a context window of 128k tokens.
When was Phi 3.5 Vision Instruct released?
Phi 3.5 Vision Instruct was released on 2024-08-20.
What benchmarks has Phi 3.5 Vision Instruct been tested on?
Phi 3.5 Vision Instruct has been evaluated on 1 benchmark, including Massive Multi-discipline Multimodal Understanding.
Advancing the state-of-the-art in AI and computing.
No tracked provider token pricing is available yet.