Anthropic Claude API API Status, Latency & Hosted LLM Directory (2026)

What is the latency, uptime SLA, and model lineup of Anthropic Claude API?

Anthropic Claude API maintains an average response latency of 280ms TTFT and an operational uptime SLA of 99.96% across its global infrastructure endpoints (us-east-1, us-west-2, eu-central-1). It currently hosts 6 tracked foundation models including Claude Opus 5.5, Claude 4.5 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Haiku.

Verified daily via automated API latency tests and official documentation.

Zero-Shot RAG Verified

Average TTFT Latency 280ms P90 Benchmark Window

Historical Uptime SLA 99.96% 30-Day Rolling Telemetry

Regional Deployment

us-east-1 us-west-2 eu-central-1

Multi-AZ Availability

Models Hosted on Anthropic Claude API (6)

Claude Opus 5.5

Anthropic · Extended Thinking Hybrid Transformer

57.8 IVR

Anthropic's September 2026 frontier powerhouse achieving 89.9% SWE-bench Verified and 92.5% GPQA Diamond at a 73% lower token price than previous Opus generations.

Input / Out $4.00 / $20.00

Host TTFT 680ms

Throughput 95 t/s

Claude 4.5 Sonnet

Anthropic · Extended Thinking Hybrid Transformer

56.5 IVR

Anthropic's premier software engineering and autonomous computer-use model featuring interleaved thinking and 90% prompt cache read discounts.

Input / Out $3.00 / $15.00

Host TTFT 380ms

Throughput 84 t/s

Claude 3.7 Sonnet

Anthropic · Hybrid Reasoning Dense Transformer

54.3 IVR

Anthropic's hybrid reasoning model combining instant conversational responses with controllable extended thinking budgets up to 64k tokens.

Input / Out $3.00 / $15.00

Host TTFT 540ms

Throughput 72 t/s

Claude 3.5 Haiku

Anthropic · High-Speed Compact Transformer

52.4 IVR

Fast, compact Anthropic model delivering sub-200ms responses with 90% prompt caching discounts for interactive applications.

Input / Out $0.80 / $4.00

Host TTFT 190ms

Throughput 130 t/s

Claude 3.5 Sonnet

Anthropic · Frontier Multimodal Transformer

46.2 IVR

Proven enterprise workhorse for software engineering, visual chart extraction, and nuanced prose generation.

Input / Out $3.00 / $15.00

Host TTFT 310ms

Throughput 80 t/s

Claude 4 Opus

Anthropic · Frontier Deep Reasoning Transformer

43.6 IVR

Anthropic's ultra-dense flagship model built for multi-hour autonomous agent horizons, novel scientific synthesis, and zero-defect systems architecture.

Input / Out $15.00 / $75.00

Host TTFT 920ms

Throughput 46 t/s

Frequently Asked Questions About Anthropic Claude API

What is the average latency and uptime SLA of Anthropic Claude API?

Anthropic Claude API delivers an average Time to First Token (TTFT) latency of 280ms and a verified 30-day rolling uptime SLA of 99.96%.

Which AI models are available on Anthropic Claude API?

Anthropic Claude API hosts 6 tracked LLMs on InferenceRate: Claude Opus 5.5, Claude 4.5 Sonnet, Claude 3.7 Sonnet, Claude 3.5 Haiku, Claude 3.5 Sonnet, Claude 4 Opus.

Which cloud regions does Anthropic Claude API support?

Anthropic Claude API supports API inference deployments across us-east-1, us-west-2, eu-central-1.