Phi 4 mini Instruct

W&B Inference chat

Phi 4 mini Instruct is a W&B Inference chat model.It supports a 128,000-token context windowwith up to 128,000 output tokens. Route Phi 4 mini Instruct via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: unknown Last verified: Oct 22, 2026
Pricing not yet public

We don't have verified per-token pricing for Phi 4 mini Instruct yet. If you have a source from W&B Inference's documentation, help us add it — your submission gets reviewed within 48 hours.

Pricing

Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.

Input —
Output —

Context & limits

Context window
128,000 tokens
Max input
128,000 tokens
Max output
128,000 tokens
Modalities
text

Capabilities

  • Function calling — not advertised
  • Parallel tool calls — not advertised
  • Vision input — not advertised
  • Audio input — not advertised
  • Audio output — not advertised
  • PDF input — not advertised
  • Streaming ✓ supported
  • Structured output — not advertised
  • Prompt caching — not advertised
  • Reasoning — not advertised

Strengths & caveats — when to pick Phi 4 mini Instruct

Data-driven from Phi 4 mini Instruct's percentile within chat peers.

Where it's strong

Watch out for

  • !agentic workflows — no advertised function-calling; use a tool-capable model and route via Agent Command Center for fallback
  • !strict structured output — no JSON-schema enforcement, expect retry loops

Benchmarks pending

We haven't logged public benchmark scores for Phi 4 mini Instruct yet. Have one to contribute? Submit a source — citations help us prioritise.

Try it

Call Phi 4 mini Instruct via Agent Command Center

One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.

SDK
Native Future AGI client (agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.
# Phi 4 mini Instruct via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC

client = AgentCC(
    api_key=os.environ["AGENTCC_API_KEY"],   # from app.futureagi.com → Settings → API Keys
    base_url="https://gateway.futureagi.com/v1",
)

resp = client.chat.completions.create(
    model="wandb-inference/microsoft-phi-4-mini-instruct",
    messages=[{"role": "user", "content": "Hello, Phi 4 mini Instruct!"}],
)

print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")

# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
    model="wandb-inference/microsoft-phi-4-mini-instruct",
    messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost:   ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache:  ", raw.headers.get("x-agentcc-cache"))
Set AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗

Explore similar models

Phi 4 mini Instruct doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark. Side-by-side links appear where a comparison page exists; otherwise, open the model profile.

FAQ

How much does Phi 4 mini Instruct cost?

Public per-token pricing for Phi 4 mini Instruct is not yet published. Submit a source on this page to help us add it.

What is the context window of Phi 4 mini Instruct?

Phi 4 mini Instruct supports a 128,000-token context window with up to 128,000 output tokens.

Does Phi 4 mini Instruct support function calling?

Phi 4 mini Instruct does not currently advertise function-calling support. For agentic workloads, prefer a tool-calling-capable model and route via Agent Command Center for fallback.

Is Phi 4 mini Instruct good for production?

Phi 4 mini Instruct is best evaluated against your own production traces. Pipe traffic through Agent Command Center to compare it head-to-head against alternatives in shadow mode.

How can I route to Phi 4 mini Instruct with fallback?

Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.

Useful links for Phi 4 mini Instruct

Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.