BroadRouter

Claude Sonnet 5.5 vs Claude Haiku 5.5 API pricing

Updated

Claude Sonnet 5.5: USD 2 input, USD 10 output per 1M tokens (Anthropic and 4 others). Claude Haiku 5.5: USD 0.10 input, USD 0.50 output per 1M tokens (Anthropic and 3 others). At 3 input tokens per output token, Claude Sonnet 5.5 costs 20× as much as Claude Haiku 5.5 (USD 4 vs USD 0.20 per 1M).

Claude Sonnet 5.5 and Claude Haiku 5.5 are neighbouring tiers of one Anthropic generation (Sonnet and Haiku, by name), so this page shows what the step up costs. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do Claude Sonnet 5.5 and Claude Haiku 5.5 differ on price?

Claude Sonnet 5.5 and Claude Haiku 5.5 prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Claude Sonnet 5.5 and Claude Haiku 5.5 API prices compared
PriceClaude Sonnet 5.5Claude Haiku 5.5
Model pageClaude Sonnet 5.5
Anthropic · 6 providers
Claude Haiku 5.5
Anthropic · 4 providers
Cheapest standard price, blended 3:1USD 4
USD 2 in / USD 10 out at Anthropic and 4 others
Anthropic page checked 2026-11-14
USD 0.20 lower
USD 0.10 in / USD 0.50 out at Anthropic and 3 others
Anthropic page checked 2026-11-14
Cheapest inputUSD 2
Anthropic source
USD 0.10 lower
Anthropic source
Cheapest cached inputUSD 0.10
Anthropic source
USD 0.01 lower
Anthropic source
Cheapest outputUSD 10
Anthropic source
USD 0.50 lower
Anthropic source
Maker's own APIUSD 2 / USD 10
Anthropic source
USD 0.10 / USD 0.50
Anthropic source
Median standard priceUSD 2 / USD 10
input / output, 6 prices
USD 0.10 / USD 0.50
input / output, 4 prices
Context window1,000,000 tokens, largest statedNo provider states one on its pricing page.
Providers with a standard price64

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Claude Sonnet 5.5 and Claude Haiku 5.5 cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Claude Sonnet 5.5 and Claude Haiku 5.5
WorkloadClaude Sonnet 5.5Claude Haiku 5.5Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 257.40
Anthropic
USD 13.14
Anthropic
USD 244.26
Claude Haiku 5.5 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 493.20
Anthropic
USD 25.02
Anthropic
USD 468.18
Claude Haiku 5.5 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 1,593
Anthropic
USD 87.30
Anthropic
USD 1,506
Claude Haiku 5.5 lower

Claude Haiku 5.5 is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 20× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

Claude Haiku 5.5 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Sonnet 5.5's, so the input:output ratio never changes the answer.

Price per 1M tokens of Claude Sonnet 5.5 and Claude Haiku 5.5 at different input:output mixes
Input : output tokensClaude Sonnet 5.5Claude Haiku 5.5
1 : 3 (long answers)USD 8
Anthropic
USD 0.40 lower
Anthropic
1 : 1USD 6
Anthropic
USD 0.30 lower
Anthropic
3 : 1 (the site’s blend)USD 4
Anthropic
USD 0.20 lower
Anthropic
10 : 1 (retrieval, long prompts)USD 2.727
Anthropic
USD 0.1364 lower
Anthropic
30 : 1 (agents, big contexts)USD 2.258
Anthropic
USD 0.1129 lower
Anthropic

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Claude Sonnet 5.5 and Claude Haiku 5.5 cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Claude Sonnet 5.5 and Claude Haiku 5.5 are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: Claude Sonnet 5.5 vs Claude Sonnet 5 · GPT-6 Sol vs Claude Sonnet 5.5 · Claude Sonnet 5.5 vs Kimi K3 · Claude Sonnet 5.5 vs Gemini 4 Hydrogen · Claude Sonnet 5.5 vs Grok 4.7 · Claude Opus 5.5 vs Claude Sonnet 5.5 · Claude Sonnet 5.5 vs GLM 5.3 · Claude Haiku 5.5 vs Claude Haiku 4.5 · GPT-6 Luna vs Claude Haiku 5.5 · Claude Haiku 5.5 vs DeepSeek V4.1 Flash · Claude Haiku 5.5 vs Gemini 3.8 Flash · every Claude Sonnet 5.5 comparison · every Claude Haiku 5.5 comparison · all 662 price comparisons

Questions

Is Claude Sonnet 5.5 cheaper than Claude Haiku 5.5?

No. On a blend of 3 input tokens to 1 output token, Claude Haiku 5.5 costs USD 0.20 per 1M tokens and Claude Sonnet 5.5 USD 4, at each model's cheapest standard price. For input alone, Claude Haiku 5.5 is cheaper (USD 0.10 against USD 2 per 1M); for output alone, Claude Haiku 5.5 is (USD 0.50 against USD 10). This compares price only, not quality.

What do Claude Sonnet 5.5 and Claude Haiku 5.5 cost per 1M tokens?

Claude Sonnet 5.5: from USD 2 input and USD 10 output at Anthropic and 4 others; Anthropic's own API charges USD 2 / USD 10; median of 6 standard prices USD 2 / USD 10. Claude Haiku 5.5: from USD 0.10 input and USD 0.50 output at Anthropic and 3 others; Anthropic's own API charges USD 0.10 / USD 0.50; median of 4 standard prices USD 0.10 / USD 0.50. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Claude Sonnet 5.5 and Claude Haiku 5.5?

4 providers have a standard price for both: Anthropic (USD 4 and USD 0.20 at 3:1), DigitalOcean (USD 4 and USD 0.20 at 3:1), Google Vertex AI (USD 4 and USD 0.20 at 3:1), Perplexity (USD 4 and USD 0.20 at 3:1). The first 4 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 4 and USD 0.20.

Which is cheaper for a coding agent or a chatbot, Claude Sonnet 5.5 or Claude Haiku 5.5?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,593 a month on Claude Sonnet 5.5 (Anthropic) against USD 87.30 on Claude Haiku 5.5 (Anthropic), a difference of USD 1,506. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 257.40 a month on Claude Sonnet 5.5 (Anthropic) against USD 13.14 on Claude Haiku 5.5 (Anthropic), a difference of USD 244.26. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Claude Sonnet 5.5 and Claude Haiku 5.5 change?

Claude Haiku 5.5 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Sonnet 5.5's, so the input:output ratio never changes the answer.

Do Claude Sonnet 5.5 and Claude Haiku 5.5 have cached input pricing?

Claude Sonnet 5.5 from USD 0.10 per 1M cached input tokens (Anthropic; 5 of 6 standard prices list a discount). Claude Haiku 5.5 from USD 0.01 per 1M cached input tokens (Anthropic; 4 of 4 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity