Home/Anthropic/Claude Sonnet 5.5
Anthropic pricing

Claude Sonnet 5.5 API Pricing & Cost Calculator

Claude Sonnet 5.5 is priced at $2.00 input / $10.00 output per 1M tokens, with a 1M context window and 128K max output. Cached input $0.20/1M. Same per-call cost as Claude Sonnet 5. A 1,000-in / 500-out call costs $0.00700.

Listed automatically on 2026-09-29

Prices and limits come straight from the LiteLLM registry and are verified daily. The description is generated from those numbers and has not yet been reviewed by a person, so it may miss context about how this model relates to others in its family.

Input
$2.00
per 1M tokens
Output
$10.00
per 1M tokens
Context window
1000K
tokens
Released
—
Cutoff —
≈ Estimated tokenizer·$2.00 in·$10.00 out (per 1M)
Quick start with a use case
Total cost per call$0.007000
Input$0.002000
Output$0.005000
Cost comparison
Standard
$0.007000
With Caching
$0.006100
Save 13% ↓
With Batch
$0.003500
Save 50% ↓
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Detailed pricing

Claude Sonnet 5.5 pricing breakdown

All pricing dimensions including caching and batch discounts.

TypePrice (per 1M tokens)
Input$2.0000
Output$10.0000
Cached input$0.2000
Cache write$2.5000
Batch input$1.0000
Batch output$5.0000
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Last verified 2026-09-29 · Anthropic official pricing · ⚠️ Spotted a wrong price? Report in 30s →

How it compares

Claude Sonnet 5.5 vs alternatives

Single-call cost (1000 input + 500 output tokens) ranked from cheapest.

ModelPer call
Claude Sonnet 5.5
Anthropic · this page
$0.007000
GPT-6 Luna
OpenAI
$0.000350
DeepSeek V3.2
DeepSeek
$0.000480
GPT-5.6 Luna
OpenAI
$0.000800
DeepSeek V4-Flash
DeepSeek
$0.000900
Gemini 3.1 Flash Lite
Google
$0.001000
Recommended use

When to choose Claude Sonnet 5.5

Claude Sonnet 5.5 shines for general-purpose tasks, complex multi-step reasoning, image and document understanding, and long documents and large codebases. Token counts are estimated within ~10-20% margin.

✓Context window of 1000K tokens handles entire codebases or book-length documents.
✓Prompt caching available — significant savings for repeated system prompts.
✓Batch API support for non-realtime workloads at ~50% discount.
✓Tool / function calling supported.
FAQ

Frequently asked questions

Claude Sonnet 5.5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0070. Use the calculator above to estimate your specific use case.
Claude Sonnet 5.5 supports a 1000K token context window with a max output of 128,000 tokens.
Yes. Cached input is priced at $0.20 per 1M tokens — 90% cheaper than uncached input. This is especially valuable for repeated system prompts, long-context retrieval, and chat threads with shared history.
Yes. Claude Sonnet 5.5 supports the Batch API at $1.00 input / $5.00 output per 1M tokens — typically 50% off standard pricing. Batch jobs complete within ~24 hours, ideal for non-realtime workloads like overnight data processing or content generation pipelines.
Yes, Claude Sonnet 5.5 accepts image input. Vision token pricing is generally calculated based on image dimensions and folded into the input token count. Specific image-specific pricing varies — refer to Anthropic's official documentation.
Token counts for Claude Sonnet 5.5 are estimated from character ratios (~10-20% margin). Cost calculations use prices verified on 2026-09-29. For final billing accuracy, always verify with Anthropic's usage dashboard.
Claude Sonnet 5.5 does not currently support fine-tuning. Consider another model in the Anthropic family if fine-tuning is required.
Related

Other models you might consider

OpenAI
GPT-6 Luna
The cheapest model on this site — with a 922K context window
$0.10 in$0.50 out
DeepSeek
DeepSeek V3.2
DeepSeek's open-weight MoE — top cost/quality ratio
$0.28 in$0.40 out
OpenAI
GPT-5.6 Luna
The cheapest long-context model OpenAI ships — 20x under the flagship
$0.20 in$1.20 out
DeepSeek
DeepSeek V4-Flash
1M context at budget pricing — $0.30/$1.20
$0.30 in$1.20 out
Google
Gemini 3.1 Flash Lite
Google's cheapest listed model — 250¢/1M input
$0.25 in$1.50 out