Claude 3.5 Sonnet (2024-10-22)

Anthropic chat Deprecated 224d ago
Heads-up: Anthropic has scheduled Claude 3.5 Sonnet (2024-10-22) for deprecation on Oct 1, 2025. Plan a migration. Use Agent Command Center's model fallback routing to swap models without code changes.

Claude 3.5 Sonnet (2024-10-22) is an Anthropic chat model.It supports a 200,000-token context windowwith up to 8,192 output tokens.Input is priced at $3.00/M tokens and output at $15.00/M tokens. Capabilities include function calling, vision, prompt caching. Route Claude 3.5 Sonnet (2024-10-22) via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: litellm Last verified: May 7, 2026 View source ↗
Cost calculator

Estimate Claude 3.5 Sonnet (2024-10-22) 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
08,192
5,000
01,000,000
cached @ $0.3000/M
Per request
$0.0150
in $0.009000 · out $0.006000
Per day
$75.00
5,000 requests
Per month
$2,283
152,188 requests

Estimate uses $3.00/M input · $15.00/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 May 7, 2026.

Input $3.00/M
Output $15.00/M
Cached input $0.300/M

Limits

Context window
200,000 tokens
Max input
200,000 tokens
Max output
8,192 tokens
Modalities
vision, pdf, text

Capabilities

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

Where it's strong

  • +pricing — cheaper than 88% of priced chat models on Future AGI
  • +PDF input — only 16% of chat models on Future AGI advertise this
  • +prompt caching — only 23% of chat models on Future AGI advertise this

Watch out for

  • !already deprecated — provider stopped accepting new traffic 224 days ago

Benchmark scores

Reported public benchmark numbers. Each row links to the source. Faded bar shows 6-peer average for context.

HumanEvalcode· 0-shot
Captured May 12, 2026
MMLUgeneral· 5-shot↓1% vs peers
Captured May 12, 2026
Chatbot Arena ELOgeneral· overall↓13% vs peers
Captured May 12, 2026
MMMUmultimodal· 0-shot
Captured May 12, 2026
GPQA Diamondreasoning· 0-shot CoT↓30% vs peers
Captured May 12, 2026
SWE-bench Verifiedagent· agentic↓39% vs peers
Captured May 12, 2026
Try it

Call Claude 3.5 Sonnet (2024-10-22) 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.
# Claude 3.5 Sonnet (2024-10-22) 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="anthropic/claude-3-5-sonnet-20241022",
    messages=[{"role": "user", "content": "Hello, Claude 3.5 Sonnet (2024-10-22)!"}],
)

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="anthropic/claude-3-5-sonnet-20241022",
    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: claude-3-5-sonnet-20241022
    provider: anthropic
    weight: 80
fallbacks:
  - model: gemini-2-5-flash
    provider: vertex-ai
  - model: gpt-5-nano
    provider: azure-openai
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true }

Compare with similar models

Grouped by Chatbot Arena tier (Claude 3.5 Sonnet (2024-10-22) sits at 1283 ELO).

FAQ

How much does Claude 3.5 Sonnet (2024-10-22) cost?

Input is priced at $3.00 per 1M tokens and output at $15.00 per 1M tokens (Anthropic, last verified May 7, 2026).

What is the context window of Claude 3.5 Sonnet (2024-10-22)?

Claude 3.5 Sonnet (2024-10-22) supports a 200,000-token context window with up to 8,192 output tokens.

Does Claude 3.5 Sonnet (2024-10-22) support function calling?

Yes — Claude 3.5 Sonnet (2024-10-22) supports function (tool) calling.

Is Claude 3.5 Sonnet (2024-10-22) good for production?

Claude 3.5 Sonnet (2024-10-22) is well-suited for pricing — cheaper than 88% of priced chat models on Future AGI and PDF input — only 16% of chat models on Future AGI advertise this. Consider alternatives if you need already deprecated — provider stopped accepting new traffic 224 days ago.

How can I route to Claude 3.5 Sonnet (2024-10-22) 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 Claude 3.5 Sonnet (2024-10-22)

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