Claude Sonnet 5.5 API Pricing & Monthly Cost Simulator
Verified 2026 unit economics for Anthropic Claude Sonnet 5.5 (anthropic/claude-sonnet-5.5): $2/1M uncached input, $0.1/1M cached prefix read, and $10/1M output across a 1,000,000-token context window (released 2026-09-28).
Uncached Input (/1M)
$2
Cached Prompt Read (/1M)
$0.1 (-95%)
Output Completion (/1M)
$10
50% Batch API (In / Out)
$1 / $5
Interactive 30-Day Monthly Spend Simulator
Live Unit-Cost & Prompt Cache Slider (Claude Sonnet 5.5)
anthropic/claude-sonnet-5.5
Estimated 30-day spend
$366.00/mo
Cost per 1,000 calls
$12.2000
Monthly savings vs 0% cache
$114.00/mo
Technical Limits & API Capabilities
Context window
1,000,000
Max output tokens
128,000
Workload tier
Frontier Reasoning
Input modalities
text, image, file
Tool Calling: Yes
JSON Schema Strict: Yes
Reasoning Tokens: Supported
50% Batch API: Available
Same-Category 2026 Model Alternatives (Frontier Reasoning)
| Model | Provider | Input / Cached ($/1M) | Output ($/1M) | Context / Max Out |
|---|---|---|---|---|
| Claude Sonnet 5.5 | Anthropic | $2 / $0.1 | $10 | 1,000,000 / 128,000 |
| Claude Fable 5.2 | Anthropic | $8 / $0.2 | $40 | 1,000,000 / 128,000 |
| GLM 5.3 FlashX Legal | Z.ai / GLM | $0.37 / $0.075 | $1.25 | 1,048,576 / 131,072 |
| GPT-6.1 Terra Pro | OpenAI | $1 / $0.05 | $5 | 1,050,000 / 128,000 |
| Kimi K3.1 Pro | Moonshot | $2 / $0.2 | $10 | 1,048,576 / 943,718 |
| GPT-6.1 Sol Pro | OpenAI | $2 / $0.1 | $10 | 1,050,000 / 128,000 |
| GPT-6 Luna Pro | OpenAI | $0.1 / $0.01 | $0.5 | 1,050,000 / 128,000 |
Head-to-Head Matchups Featuring Claude Sonnet 5.5
- Claude Opus 5.5 vs Claude Sonnet 5.5 — $4 vs $2 / 1M
- Claude Sonnet 5.5 vs Claude Haiku 5.5 — $2 vs $0.1 / 1M
- GPT-6.1 Sol Pro vs Claude Sonnet 5.5 — $2 vs $2 / 1M
- Claude Sonnet 5.5 vs Gemini 4 Argon — $2 vs $2 / 1M
- Grok 4.7 vs Claude Sonnet 5.5 — $2 vs $2 / 1M
Frequently Asked Questions
How much does Claude Sonnet 5.5 cost per 1 million tokens in 2026?
Claude Sonnet 5.5 by Anthropic is billed at $2 per 1M uncached input tokens, $0.1 per 1M cached input read tokens (95% cache discount), and $10 per 1M output tokens.
What are the context window and max output token limits for Claude Sonnet 5.5?
Claude Sonnet 5.5 supports a 1,000,000-token input context window and up to 128,000 completion output tokens per request, accepting text, image, file inputs.
Does Claude Sonnet 5.5 support strict JSON Schema outputs, tool calling, and Batch API?
Claude Sonnet 5.5 capability profile: tool calling = Supported, strict JSON Schema structured outputs = Supported, reasoning mode = Supported, and 50% asynchronous Batch API = Supported.