impulse

Phi 3.5 MOE Instruct

Open weights
API id phi-3.5-moe-instruct
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve Phi 3.5 MOE Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
NVIDIA NIMInference
phi-3.5-moe-instruct
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: MIT
Runtimes: Ollama, llama.cpp, vLLM

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Microsoft models

  • Mai Thinking 1
    Microsoft · on Azure AI Foundry
    $2.00 / $8.00
    Has every key capability

Other frontier labs

  • GPT-5.5 Pro
    OpenAI · on OpenAI
    $30.00 / $180.00
    Has every key capability
  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability

Open-weight picks

  • Command A Plus
    Cohere · on AIHubMix
    $2.50 / $10.00
    Has every key capability
  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability

Call it

Using NVIDIA NIM's API.

Python
from litellm import completion

response = completion(
    model="nvidia_nim/phi-3.5-moe-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Phi 3.5 MOE Instruct?

Phi 3.5 MOE Instruct runs on 1 API: NVIDIA NIM.

Is Phi 3.5 MOE Instruct being retired?

No retirement date is scheduled for it on any API we track.

What is Phi 3.5 MOE Instruct's API model id?

Use phi-3.5-moe-instruct with NVIDIA NIM.

Sources

Raw catalog entry for phi-3.5-moe-instruct on NVIDIA NIM
{
  "litellm_provider": "nvidia_nim",
  "source": "https://integrate.api.nvidia.com/v1/models"
}