Phi 3 Vision 128K
Phi 3 Vision 128K is a language model with 4.2B parameters from Microsoft. It is currently free at 1 provider with up to 131K tokens of context. The model understands images. Its weights are open, so it can also run locally.
- Developer
- Microsoft
- Parameters
- 4.2B
- Context
- 131K tokens
- Type
- Text
- License
- Open weights
Where to use Phi 3 Vision 128K for free
Each row is a separate free endpoint with its own limits.
| Provider | Context | Limit | Card | |
|---|---|---|---|---|
 NVIDIA Build microsoft/phi-3-vision-128k-instruct |
131K | Free serverless inference for development; limits and model availability may change. | No | Open |
Quick start
curl https://integrate.api.nvidia.com/v1/chat/completions \
-H "Authorization: Bearer $NVIDIA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/phi-3-vision-128k-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://integrate.api.nvidia.com/v1",
api_key="YOUR_NVIDIA_API_KEY",
)
reply = client.chat.completions.create(
model="microsoft/phi-3-vision-128k-instruct",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://integrate.api.nvidia.com/v1",
apiKey: process.env.NVIDIA_API_KEY,
});
const reply = await client.chat.completions.create({
model: "microsoft/phi-3-vision-128k-instruct",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for NVIDIA Build. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
This model is not on the Artificial Analysis leaderboard yet. We do not publish our own estimates.
Similar free models
FAQ
Is Phi 3 Vision 128K free?
Yes. As of September 26, 2026, Phi 3 Vision 128K is free at NVIDIA Build. Each provider has its own limits — see the table above.
What is the context window of Phi 3 Vision 128K?
The largest context among free routes is 131,072 tokens. Some providers cap it lower.
How do I call Phi 3 Vision 128K via API?
Use any OpenAI-compatible client with base URL https://integrate.api.nvidia.com/v1, model ID microsoft/phi-3-vision-128k-instruct, and a NVIDIA Build key.
Is Phi 3 Vision 128K open-weight?
Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.