Claude Sonnet 4.6

Google Vertex AI chat

Claude Sonnet 4.6 is a Google Vertex AI chat model.It supports a 1,000,000-token context windowwith up to 64,000 output tokens.Input is priced at $3.00/M tokens and output at $15.00/M tokens. Capabilities include function calling, vision, reasoning, prompt caching. Route Claude Sonnet 4.6 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 12, 2026 View source ↗
Cost calculator

Estimate Claude Sonnet 4.6 spend

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

~3K in / ~400 out · 5K req/day
3,000
01,000,000
400
064,000
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 12, 2026.

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

Limits

Context window
1,000,000 tokens
Max input
1,000,000 tokens
Max output
64,000 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 ✓ supported

Where it's strong

  • +pricing — cheaper than 88% of priced chat models on Future AGI
  • +long-context tasks — context window in the top 8% of peers
  • +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

  • No major caveats flagged from public spec.

Benchmark scores

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

Chatbot Arena ELOgeneral· overall↓1% vs peers
Captured May 12, 2026
τ-bench (retail)agent
Captured May 12, 2026
GPQA Diamondreasoning↓3% vs peers
Captured May 12, 2026
MMLUgeneral↓0% vs peers
Captured May 12, 2026
SWE-bench Verifiedagent↓1% vs peers
Captured May 12, 2026
MMMU-Promultimodal· without tools↓7% vs peers
Captured May 12, 2026
ARC-AGI-2reasoning· max effort↓8% vs peers
Captured May 12, 2026
Humanity's Last Examreasoning· without tools↓11% vs peers
Captured May 12, 2026
Try it

Call Claude Sonnet 4.6 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 Sonnet 4.6 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="vertex-ai/claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello, Claude Sonnet 4.6!"}],
)

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="vertex-ai/claude-sonnet-4-6",
    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-sonnet-4-6
    provider: vertex-ai
    weight: 80
fallbacks:
  - model: claude-opus-4-6
    provider: azure-ai-foundry
  - model: claude-opus-4-6-20260205
    provider: anthropic
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true }

Same model on other providers

claude-sonnet-4-6 is also available via 2 other routes. Pricing, regions, and capabilities can differ — compare before routing production traffic.

ProviderInput / 1MOutput / 1MVerified
Azure AI Foundry$3.00/M$15.00/MMay 12, 2026
Anthropic$3.00/M$15.00/MMay 12, 2026

Compare with similar models

Grouped by Chatbot Arena tier (Claude Sonnet 4.6 sits at 1466 ELO).

FAQ

How much does Claude Sonnet 4.6 cost?

Input is priced at $3.00 per 1M tokens and output at $15.00 per 1M tokens (Google Vertex AI, last verified May 12, 2026).

What is the context window of Claude Sonnet 4.6?

Claude Sonnet 4.6 supports a 1,000,000-token context window with up to 64,000 output tokens.

Does Claude Sonnet 4.6 support function calling?

Yes — Claude Sonnet 4.6 supports function (tool) calling.

Is Claude Sonnet 4.6 good for production?

Claude Sonnet 4.6 is well-suited for pricing — cheaper than 88% of priced chat models on Future AGI and long-context tasks — context window in the top 8% of peers.

How can I route to Claude Sonnet 4.6 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 Sonnet 4.6

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