Anthropic
Operational· checked every few minutes

Claude Sonnet 5.5 API

The Claude Sonnet 5.5 API: Anthropic's fastest Sonnet, 61% below list price.

Price per 1M tokens61%off
Input
$0.79$2.00
Output
$3.95$10.00
Cached input
$0.079$0.10
Cache-write pricesAll prices
Get your API keyTry it in the playground
Model IDclaude-sonnet-5-5Updated
chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[
        {"role": "user", "content": "Explain quicksort briefly."},
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK, and the Anthropic SDK and Claude Code. Chat API docs

Context window
1M tokens
Max output
128K tokens
Reasoning
low to max
Input
Text, Image
Released
Sep 28, 2026
Status
Operational

Pricing

Claude Sonnet 5.5 API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

RateZurelayAnthropic list
Input
per 1M tokens
$0.79$2.00
Output
per 1M tokens
$3.95$10.00
Cached input
per 1M tokens
$0.079$0.10
Cache writes (5 min)
per 1M tokens
$0.9875$2.50
Cache writes (1 h)
per 1M tokens
$1.58$4.00

One rate at every prompt length, up to the full 1M context window. Streaming, tool calls and structured outputs cost nothing extra.

Every Claude model and price
Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M
Output tokens per month10M
Zurelay
$79.00
Anthropic list price
$200.00
You save every month$121.00

$1,452 a year

Cost

Claude Sonnet 5.5 API cost, worked out. And compared.

Typical workloads at Zurelay's live prices next to the list price, and what other places charge for the same model.

  • Chatbot

    50,000 requests a month, 1,500 tokens in and 300 out, 30% of the input cached. $0.00205 a request.

    $102.50a month$257.25 at list

  • Documents

    20,000 requests a month, 8,000 tokens in and 500 out, 20% of the input cached. $0.00716 a request.

    $143.15a month$359.20 at list

  • Coding agent

    5,000 requests a month, 40,000 tokens in and 1,500 out, 85% of the input cached. $0.0134 a request.

    $66.76a month$152.00 at list

  • Classification

    1,000,000 requests a month, 400 tokens in and 5 out. $0.000336 a request.

    $335.75a month$850.00 at list

Where to buy Claude Sonnet 5.5

Prices per 1M tokens

SellerInputOutput
Anthropic
List price, direct
$2.00$10.00
OpenRouter
List price, plus 5.5% on card top-ups
$2.00$10.00
Zurelay
No fee to add credit
$0.79$3.95

OpenRouter's fee as its pricing page listed it on October 28, 2026. Zurelay's prices are live. Some labs also discount batch or off-peak requests.

Overview

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is Anthropic's current Sonnet model, which Anthropic calls its best combination of speed and intelligence. The Zurelay Claude Sonnet 5.5 API serves it through an OpenAI-compatible or Anthropic-compatible endpoint at 61% below list price, for teams running coding, agent and document work at volume.

Claude Sonnet 5.5 was released on September 28, 2026, as the second model in Anthropic's 5.5 family. It replaces Claude Sonnet 5 at the same list price. On Zurelay, the Claude Sonnet 5.5 API uses the model ID claude-sonnet-5-5 and costs $0.79 per 1M input tokens and $3.95 per 1M output tokens.

Anthropic says Sonnet 5.5 generates output more than 30% faster than Sonnet 5, which makes it the fastest Sonnet so far. In Anthropic's testing it also costs up to 30% less per task, because it needs fewer tokens to finish. It is strongest at well-scoped everyday tasks, bug fixes, and polished documents, slides and spreadsheets, and Anthropic notes a sharp eye for design. It is the first Sonnet model to beat Pokémon Red working only from screenshots, a test of long-horizon work and image understanding.

The specs: a 1M-token context window, up to 128K output tokens per request, text and image input, and text output. Adaptive thinking is on by default and effort defaults to high. Unlike Opus 5.5, Sonnet 5.5 lets you turn off up-front thinking with the between_tools setting, which suits latency-sensitive routes. Anthropic recalibrated the effort levels, so re-test your settings instead of copying them from Sonnet 5. Sampling parameters (temperature, top_p, top_k) must stay at their defaults.

Sonnet 5.5 or Opus 5.5? Anthropic positions Sonnet 5.5 as a faster, lower-cost complement to Opus 5.5, while Opus stays stronger at complex, open-ended work that needs sustained judgment. On Zurelay both run on the same key, so you can send routine traffic to Sonnet and escalate hard cases to Opus without a second integration.

Strengths

Where Claude Sonnet 5.5 shines. And what teams build with it.

01

Speed

Anthropic measured output more than 30% faster than Sonnet 5. Its comparative latency is rated fast, a step quicker than Opus 5.5.

02

Lower cost per task

Same list price as Sonnet 5, but up to 30% lower cost per task in Anthropic's testing, because the model reaches the answer in fewer tokens.

03

Documents, slides and spreadsheets

Anthropic calls out polished documents, slides and spreadsheets, plus a sharp eye for design.

04

Close to Opus on knowledge work

On the GDPval-AA knowledge-work benchmark that Anthropic reports, Sonnet 5.5 scores almost level with Opus 5.5.

Use cases

  • Coding assistants and bug fixes

    Handle well-scoped tickets, bug fixes and code edits with fast turnaround in IDE tools, CLIs and CI.

  • Agents at volume

    Run multi-step tool-calling agents where cost per task and latency matter, and turn off up-front thinking on the simplest routes.

  • Docs, slides and spreadsheets

    Generate reports, slide content and spreadsheet logic that need little cleanup before they ship.

  • Chat and support

    Serve user-facing chat where response time matters. Anthropic suggests starting chat workloads at low or medium effort.

Get started

Call Claude Sonnet 5.5 in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

  1. 1

    Create a key

    Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.

    Get your API key
  2. 2

    Point your SDK at Zurelay

    Change the base URL. Everything else in your code stays the same.

    https://api.zurelay.com/v1
  3. 3

    Use claude-sonnet-5-5

    Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.

    claude-sonnet-5-5

Works with the tools you already use

Compare

Similar models. All on the same key.

65%off

Claude Opus 5.5

$1.40 / $7.00 per 1M tokens

Pick Claude Opus 5.5 for complex, open-ended work that needs sustained judgment, such as large migrations or long agent runs.

Claude Opus 5.5 API
74%off

Nano Banana Pro

from $0.035 per image

Pick Nano Banana Pro to generate images; Sonnet 5.5 reads images but only returns text.

Nano Banana Pro API
75%off

GPT-6 Luna

$0.025 / $0.125 per 1M tokens

Try GPT-6 Luna, which has a much lower list price, for bulk simple text jobs once your evals show it holds up.

GPT-6 Luna API

FAQ

Claude Sonnet 5.5 API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the Claude Sonnet 5.5 API cost on Zurelay?

Zurelay charges $0.79 per 1M input tokens and $3.95 per 1M output tokens, with cached input at $0.079. Anthropic's list price is $2.00 input and $10.00 output, so you save 61%. The rate is the same across the full context window.

Is there a cheaper Claude Sonnet API than Anthropic's?

Yes. Zurelay serves claude-sonnet-5-5 at 61% below Anthropic's list price. It is the same model, not a smaller substitute. Switch the base URL and key and keep the rest of your code.

How do I call Claude Sonnet 5.5 with the OpenAI SDK?

Create a Zurelay API key, set the base URL to https://api.zurelay.com/v1 and set the model to claude-sonnet-5-5. Chat completions, streaming and tool calls work as they do with OpenAI. Temperature and top_p have no effect: Anthropic's API refuses them on this model, so Zurelay leaves them out of the request. Anthropic's API also refuses a forced tool_choice on it, so Zurelay sends a forced tool as auto and tells the model which tool to call.

Can I use the Anthropic SDK or Claude Code with Claude Sonnet 5.5?

Yes. Zurelay serves the Anthropic Messages API too. Set the base URL, or ANTHROPIC_BASE_URL for Claude Code, to https://api.zurelay.com with no /v1, and authenticate with your Zurelay key. The same key works for every model in the catalog.

Should I use Claude Sonnet 5.5 or Claude Opus 5.5?

Start with Sonnet 5.5 for well-scoped tasks, bug fixes, documents and chat, where its speed and lower price pay off. Move to Opus 5.5 for complex, open-ended work such as large refactors, long agent runs or careful analysis. Both are on one Zurelay key, so you can route per request.

What is the Claude Sonnet 5.5 context window?

Claude Sonnet 5.5 has a 1M-token context window and returns up to 128K output tokens per request. Stream long responses so tokens arrive as they are generated.

Can I turn off thinking on Claude Sonnet 5.5?

Not with thinking type disabled, which returns an error on this model. Send thinking type between_tools instead. It turns off up-front thinking and works at high effort or below. For xhigh or max effort, keep adaptive thinking on.

Does the Zurelay Claude Sonnet 5.5 API support streaming, and what are the rate limits?

Streaming works on both chat completions and the Messages API, using server-sent events. You set your own requests-per-minute cap and spend limit on each key. If a route errors, times out or hits a rate limit, Zurelay retries on another route for the same model, and failed attempts are not billed.

Are Claude Sonnet 5.5 responses on Zurelay identical to Anthropic's API?

Your requests run on Claude Sonnet 5.5 itself. Zurelay doesn't swap in a different or smaller model. Only smart routing, which you turn on yourself, can answer with a close alternative when the model is down, and the x-zurelay-model header names the model that answered. Output is sampled, so the wording varies between calls on any API, but capability and behavior are the model's own. Zurelay is an independent service and is not affiliated with or endorsed by Anthropic.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer