o3 (EU)

Azure OpenAI chat Deprecates in 15d (Nov 19, 2026)
Heads-up: Azure OpenAI has scheduled o3 (EU) for deprecation on Nov 19, 2026. Plan a migration. Use Agent Command Center's model fallback routing to swap models without code changes.

o3 (EU) is an Azure OpenAI chat model.It supports a 200,000-token context windowwith up to 100,000 output tokens.Input is priced at $2.20/M tokens and output at $8.80/M tokens. Route o3 (EU) via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: litellm Last verified: Oct 22, 2026 View source ↗
Cost calculator

Estimate o3 (EU) spend

Pick a workload, fine-tune the sliders, and see the monthly bill.

~3K in / ~400 out · 5K req/day
3,000
0200,000
400
0100,000
5,000
01,000,000
cached @ $0.5500/M
Per request
$0.0101
in $0.006600 · out $0.003520
Per day
$50.60
5,000 requests
Per month
$1,540
152,188 requests

Estimate uses $2.20/M input · $8.80/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.

Pricing

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

Input $2.20/M
Output $8.80/M
Blended (3:1 in:out) $3.85/M
Cross-model comparable price
Cached input $0.550/M
Batch input $1.10/M
Batch output $4.40/M

Context & limits

Context window
200,000 tokens
Max input
200,000 tokens
Max output
100,000 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 o3 (EU)

Data-driven from o3 (EU)'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
  • !scheduled deprecation on Nov 19, 2026 (15 days)

Benchmarks pending

We haven't logged public benchmark scores for o3 (EU) yet. Have one to contribute? Submit a source — citations help us prioritise.

Try it

Call o3 (EU) 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.
# o3 (EU) 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="azure-openai/eu-o3",
    messages=[{"role": "user", "content": "Hello, o3 (EU)!"}],
)

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="azure-openai/eu-o3",
    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

o3 (EU) 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 o3 (EU) cost?

Input is priced at $2.20 per 1M tokens and output at $8.80 per 1M tokens (Azure OpenAI, last verified Oct 22, 2026).

What is the context window of o3 (EU)?

o3 (EU) supports a 200,000-token context window with up to 100,000 output tokens.

Does o3 (EU) support function calling?

o3 (EU) 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 o3 (EU) good for production?

o3 (EU) 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 o3 (EU) 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 o3 (EU)

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