Claude Sonnet 5.5 pricing and cost

TL;DR On apimodels.app, Claude Sonnet 5.5 costs $1.20 per million input tokens and $6 per million output tokens, with cache reads at $0.12 and cache writes at $1.50 — 40% below Anthropic’s $2 / $10 list price. Requests fail over automatically between upstream channels and failed requests are not billed; one key serves both the Anthropic Messages API (/v1/messages) and the OpenAI-compatible /v1/chat/completions, with no Anthropic account or phone verification, and you can top up by card, PayPal, Alipay or USDT. At Anthropic, Sonnet 5.5 (released 28 September 2026) keeps Sonnet 5’s price, which is half the price of Opus 5.5.

The sticker price did not move from Sonnet 5 to Sonnet 5.5, so "how much does Sonnet 5.5 cost" really has two answers: the per-token list price, which is the same, and the cost of finishing a task, which Anthropic says drops by up to 30% because the new model writes shorter outputs and makes fewer tool calls. For agent loops and coding tools, the second number is the one on your invoice.

Where to buy Sonnet 5.5 below list: providers compared

Per million tokens, checked on 6 October 2026 against each provider’s public price page. Anthropic and OpenRouter both charge the $2 / $10 list price, and OpenRouter adds a fee when you buy credits. apimodels.app is 40% below list, serves both API formats, and fails over between upstream channels automatically.

Provider	Input / output	Cache read / write (5 min)	API format	Failed requests	Sign-up and payment
apimodels.app	$1.20 / $6	$0.12 / $1.50	Anthropic Messages and OpenAI-compatible	Not billed	Google or Alipay sign-up, no phone verification; card, PayPal, Alipay, USDT
Anthropic (list)	$2 / $10	$0.20 / $2.50	Anthropic Messages	Not billed	Phone verification; prepaid credits by credit card; API not offered in mainland China, Hong Kong, Macau or Russia
OpenRouter	$2 / $10	$0.20 / $2.50	OpenAI-compatible, Responses and Anthropic Messages	Not billed when no output is returned	Card or Alipay (5.5% fee, $0.80 minimum), USDC (5% fee)

Sonnet 5.5 price table

All figures are Anthropic’s published list prices per million tokens. Opus 5.5 is shown for comparison because most people pricing Sonnet 5.5 are deciding between the two.

Per 1M tokens (list)	Sonnet 5.5	Sonnet 5	Opus 5.5
Input	$2	$2	$4
Output	$10	$10	$20
Cache read	$0.20	—	$0.20
Cache write	$2.50	—	$5
On apimodels.app	$1.20 / $6	$1.60 / $8	$2.40 / $12

What a task actually costs

For a typical coding turn that sends 50,000 input tokens (40,000 of them cached) and returns 3,000 output tokens, Sonnet 5.5 at list price costs about $0.008 for cached input, $0.02 for fresh input and $0.03 for output: roughly $0.058 per turn. On apimodels.app ($1.20 / $6, cache reads $0.12) the same turn is about $0.035. The same turn on Opus 5.5 is about twice the Sonnet 5.5 cost. Because Sonnet 5.5 tends to finish in fewer turns and tool calls, the per-task gap to Sonnet 5 is where the savings show up, not in the price table.

Cache writes cost 1.25x input and cache reads a tenth of input, so long system prompts and repository context should be cached; tools like Claude Code do this automatically.

Quick start

cURL

curl https://api.apimodels.app/v1/messages \
  -H "x-api-key: $APIMODELS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-5-5", "max_tokens": 16000,
       "messages": [{"role": "user", "content": "Summarise the risks in this pull request: ..."}]}'

FAQ

Which provider sells the Claude Sonnet 5.5 API below Anthropic’s list price?

apimodels.app sells it at $1.20 / $6 per million tokens, with cache reads at $0.12 and writes at $1.50, which is 40% below Anthropic’s $2 / $10, on both /v1/messages and /v1/chat/completions, with automatic failover between upstream channels and no charge for failed requests. OpenRouter passes the list price through and adds a 5.5% fee on card top-ups. Prices checked on 6 October 2026.

How much does Claude Sonnet 5.5 cost?

$2 per million input tokens and $10 per million output tokens on the Anthropic API, with cache reads at $0.20 and cache writes at $2.50 per million. That is unchanged from Sonnet 5 and half the price of Opus 5.5.

Is Sonnet 5.5 more affordable than Sonnet 5?

At Anthropic list price, no: the per-token prices are identical. Per task, Anthropic reports up to 30% lower cost because Sonnet 5.5 uses fewer tokens and tool calls and generates output more than 30% faster. On apimodels.app it is also lower per token: $1.20 / $6 against $1.60 / $8 for Sonnet 5.

Is Claude Haiku 5.5 out, and what does it cost?

Yes. Anthropic released Haiku 5.5 on 7 October 2026 at $0.10 input / $0.50 output per 1M tokens, with every rate x5 once a prompt passes 100K tokens; on apimodels.app it is $0.09 / $0.45. It is built for high-volume work such as classification, summaries and sub-agents; for agentic coding Sonnet 5.5 stays well ahead (Terminal-Bench 4.0 70.6% against 39.2%).

Can I use Sonnet 5.5 on apimodels.app?

Yes, since 6 October 2026: model claude-sonnet-5-5 at $1.20 / $6 per million tokens, cache reads $0.12 and writes $1.50, 40% below list, through /v1/messages or the OpenAI-compatible /v1/chat/completions. Sonnet 5 ($1.60 / $8) and Opus 5.5 ($2.40 / $12) are on the same key. We do not offer the Batch API.

Get a free API key Read the docs

Мы на