o1 (2024-12-17)

OpenAI chat Deprecated 12d ago
Heads-up: OpenAI has scheduled o1 (2024-12-17) for deprecation on Oct 23, 2026. Plan a migration. Use Agent Command Center's model fallback routing to swap models without code changes.

o1 (2024-12-17) is an OpenAI chat model.It supports a 200,000-token context windowwith up to 100,000 output tokens.Input is priced at $15.00/M tokens and output at $60.00/M tokens. Capabilities include function calling, vision, reasoning, prompt caching. Route o1 (2024-12-17) 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 o1 (2024-12-17) 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 @ $7.50/M
Per request
$0.0690
in $0.0450 · out $0.0240
Per day
$345
5,000 requests
Per month
$10,501
152,188 requests

Estimate uses $15.00/M input · $60.00/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 $15.00/M
Output $60.00/M
Blended (3:1 in:out) $26.25/M
Cross-model comparable price
Cached input $7.50/M
Batch input $7.50/M
Batch output $30.00/M

Context & limits

Context window
200,000 tokens
Max input
200,000 tokens
Max output
100,000 tokens
Modalities
vision, pdf, text

Capabilities

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

Strengths & caveats — when to pick o1 (2024-12-17)

Data-driven from o1 (2024-12-17)'s percentile within chat peers.

Where it's strong

  • +pricing — cheaper than 98% of priced chat models on Future AGI
  • +parallel tool calls — only 18% of chat models on Future AGI advertise this
  • +PDF input — only 18% of chat models on Future AGI advertise this

Watch out for

  • !already deprecated — provider stopped accepting new traffic 12 days ago

Benchmark scores

Reported public benchmark numbers. Each row links to the source.

Captured Oct 20, 2026
Captured Oct 20, 2026
Captured Oct 19, 2026
Try it

Call o1 (2024-12-17) 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.
# o1 (2024-12-17) 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="openai/o1-2024-12-17",
    messages=[{"role": "user", "content": "Hello, o1 (2024-12-17)!"}],
)

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="openai/o1-2024-12-17",
    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 ↗
Advanced: fallback + cache config (YAML) ▸
strategy: cost-optimized
targets:
  - model: o1-2024-12-17
    provider: openai
    weight: 80
fallbacks:
  - model: claude-sonnet-5
    provider: azure-ai-foundry
  - model: kimi-k2-6
    provider: azure-ai-foundry
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true }

Same model on other providers

o1-2024-12-17 is also available via 1 other route. Pricing, regions, and capabilities can differ — compare before routing production traffic.

ProviderInput / 1MOutput / 1MVerified
Azure OpenAI$15.00/M$60.00/MOct 22, 2026

Explore similar models

Grouped by Chatbot Arena tier (o1 (2024-12-17) sits at 1402 ELO). Side-by-side links appear where a comparison page exists; otherwise, open the model profile.

FAQ

How much does o1 (2024-12-17) cost?

Input is priced at $15.00 per 1M tokens and output at $60.00 per 1M tokens (OpenAI, last verified Oct 22, 2026).

What is the context window of o1 (2024-12-17)?

o1 (2024-12-17) supports a 200,000-token context window with up to 100,000 output tokens.

Does o1 (2024-12-17) support function calling?

Yes — o1 (2024-12-17) supports function (tool) calling, including parallel tool calls.

Is o1 (2024-12-17) good for production?

o1 (2024-12-17) is well-suited for pricing — cheaper than 98% of priced chat models on Future AGI and parallel tool calls — only 18% of chat models on Future AGI advertise this. Consider alternatives if you need already deprecated — provider stopped accepting new traffic 12 days ago.

How can I route to o1 (2024-12-17) 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 o1 (2024-12-17)

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