What is the token pricing for Claude Sonnet 5 on API100?

Claude Sonnet 5 costs $3 per 1 million input tokens and $15 per 1 million output tokens with no markup over provider baseline rates.

What is the context window for Claude Sonnet 5?

Claude Sonnet 5 supports a maximum context window of 200k tokens (2,00,000 tokens total).

Does API100 store prompts when using Claude Sonnet 5?

No. API100 operates a strict 100% Zero-Retention Privacy policy. Prompts and completions are processed in memory and never logged to disk or used for training.

Back to all models

Last Verified: September 2026

Anthropic

Requires Pro Plan

✦ Featured Flagship

● High Availability (99.9% Upstream SLA)

Claude Sonnet 5

Model ID:claude-sonnet-5•Company:Anthropic

Enterprise workhorse balancing Opus-class reasoning with fast token generation and hybrid configurable thinking budgets.

Context Length

200k

Tokens total window

Max Output

16,384

Tokens per response

Prompt Pricing

Per 1,000,000 input tokens

Output Pricing

$15

Per 1,000,000 output tokens

Key Capabilities

coding

hybrid reasoning

agentic

tool calling

vision

Enterprise Reliability

• 100% OpenAI-compatible Chat Completions API endpoint
• Zero prompt data retention — never used for model training
• Sub-50ms gateway routing overhead with prompt caching support
• Atomic multi-provider failover ensures zero service interruptions

OpenAI SDK Drop-in Call

# Python — drop-in replacement for OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://apihundred.com/v1",
    api_key="your-api100-key"
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[
        {"role": "user", "content": "Explain transactional RLS in Postgres"}
    ]
)
print(response.choices[0].message.content)

# cURL API Request

curl https://apihundred.com/v1/chat/completions \
  -H "Authorization: Bearer $API100_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Gateway Performance & Verification Telemetry

Measured across 10,000 requests routed through API100 multi-region edge nodes.

Official Anthropic Docs Full Benchmarks

Median TTFT

285 ms

Time to first token

Throughput

68 t/s

Output stream velocity

Routing Overhead

< 42 ms

API100 proxy latency

Audit Status

Verified

September 2026 Direct Lab

Frequently Asked Questions about Claude Sonnet 5

How do I call Claude Sonnet 5 with the OpenAI SDK?

Initialize your standard OpenAI client with baseURL="https://api.apihundred.com/v1" and use your API100 key. Pass model="claude-sonnet-5" into client.chat.completions.create().

What are the token prices for Claude Sonnet 5?

On API100, Claude Sonnet 5 is priced at $3 per million input tokens and $15 per million output tokens with direct pass-through rates and unified wallet billing.

Does API100 store prompts when calling Claude Sonnet 5?

Zero prompts or outputs are stored on disk. All requests are streamed via TLS 1.3 in ephemeral volatile memory. Prompts are never saved to server logs or used for training.

What happens if Anthropic has an outage?

API100 provides automated multi-provider failover. You can configure fallback models or enable our intelligent router to automatically re-route requests without application errors.

Alternative & Related Models

View Full Catalog

anthropic$3.9/1M

Claude 3.5 Sonnet

Anthropic's premier model for nuanced reasoning, software engineering, and high-precision document synthesis.

200k context

anthropic$15/1M

Claude Opus 5.5

Anthropic's pinnacle intelligence tier leading global benchmarks in autonomous software engineering and formal verification.