Claude Sonnet 5.5
Last verified November 9, 2026 · Anthropic pricing ↗$2.00/1M input · $10.00/1M output · 1.0M context · Anthropic
Claude Sonnet 5.5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens from Anthropic, with a 1.0M-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0070, or $70.00 per 10,000 requests. On that workload it is cheaper than 43 of the 173 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What Claude Sonnet 5.5 Costs Per Request
At $2.00 per 1M input and $10.00 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0070 | $70.00 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.022 | $220.00 |
| Coding-agent step | 30,000 / 2,000 | $0.080 | $800.00 |
Claude Sonnet 5.5 vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Claude Sonnet 5.5 Anthropic | $2.00 | $10.00 | 1.0M | $0.022 |
| Claude Sonnet 5 Anthropic | $2.00 | $10.00 | 1.0M | $0.022 |
| GPT-6.1 Sol OpenAI | $2.00 | $10.00 | 1.1M | $0.022 |
| Gemini 4 Argon Google | $2.00 | $10.00 | 1.0M | $0.022 |
Alternatives to Claude Sonnet 5.5
Pricing Details
AnthropicLaunched September 28, 2026. Same card as Sonnet 5 on every line: $2.00 input, $2.50 5-minute cache write, $4.00 1-hour cache write, $0.10 cache hit (0.05x, same ratio as Opus 5.5; corrected 2026-10-13), $10.00 output. Batch $1.00/$5.00. No Fast mode. Full 1M context at standard pricing. inference_geo 'us' is 1.1x; Vertex AI US/EU multi-region $2.20/$0.22/$11.00. Max output 128K (300K on Batch with the output-300k-2026-03-24 beta header). Same tokenizer as Sonnet 5. Minimum cacheable prompt 512 tokens (Sonnet 5: 1,024); tool-use system prompt 286 tokens (Sonnet 5: 354). Adaptive thinking on by default; effort low/medium/high/xhigh/max, recalibrated vs Sonnet 5. API default effort HIGH (Claude Code and apps default to medium). thinking: disabled, forced tool_choice and non-default temperature/top_p/top_k return 400. Anthropic claims 'up to 30% less per task' than Sonnet 5, no method published. Artificial Analysis Intelligence Index v4.3.2 (read 2026-09-29), score / cost to run index / per task: low 35.8 / $544 / $0.41; medium 40.7 / $701 / $0.59; high 46.7 / $1,176 / $1.08; xhigh 51.9 / $2,738 / $2.74; max 56.0 / $8,977 / $7.60 (~193k output tokens per task, the highest AA has measured). At max it costs more than Opus 5.5 max ($8,708, score 57.6). Anthropic-reported: Terminal-Bench 4.0 70.6 (max), FrontierCode 1.1 52.1 (xhigh), CursorBench 4.0 55.5, GDPval-AA v2.1 1844, OSWorld 2.1 80.1, SWE-Bench Pro 81.3. Falls back to Sonnet 5 on some cyber requests. Retirement not sooner than September 28, 2027. API ID: claude-sonnet-5-5.
Input / 1M tokens
$2
Output / 1M tokens
$10
Context Window
1.0M
Max Output
128K
Price History
No price change recorded since 2026-09-29, when this site started tracking this model; it launched on 2026-09-28.
Frequently Asked Questions
Common questions about Claude Sonnet 5.5 pricing and usage
How much does Claude Sonnet 5.5 cost?
Claude Sonnet 5.5 costs $2 per 1 million input tokens and $10 per 1 million output tokens. This pricing is set by Anthropic.
What tokenizer does Claude Sonnet 5.5 use?
Claude Sonnet 5.5 uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is Claude Sonnet 5.5's context window?
Claude Sonnet 5.5 supports a context window of 1.0M tokens (1,000,000 tokens). The maximum output length is 128K tokens.
How does Claude Sonnet 5.5 compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, Claude Sonnet 5.5 costs $0.022 per request. The nearest-priced alternatives cost: Claude Sonnet 5 (Anthropic) $0.022, GPT-6.1 Sol (OpenAI) $0.022, Gemini 4 Argon (Google) $0.022. The table above lists their full rates and context windows.
How do I count tokens for Claude Sonnet 5.5?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Claude Sonnet 5.5 using the cl100k_base tokenizer.