Skip to content
OfferSign up and get $10 of credit for any model in Chat and the API. Top up from $1, with no processing fees. See free models →·Some free models are at the daily cap — refills 05:30 IST; requests auto-route to a live backup. Status →
One AI API Key

Anthropic · Claude · Balanced

Claude Sonnet 5.5 (free lane)

New

Claude Sonnet 5.5 on the free lane: strong coding quality for everyday work.

Model id

claude-sonnet-5-5:free

Price per 1M tokens

Input
$1.40
Output
$7.00
Cached input
Not offered

Added here 11 Nov 2026 — read the changelog for what changed and why.

Output is 5× the input rate. $1 covers about 204 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates

Start using Claude Sonnet 5.5 (free lane)

Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.

curl https://api.oneaiapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5:free",
    "stream": true,
    "messages": [{"role": "user", "content": "Fix the off-by-one error in paginate() and add a test for the last page."}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oneaiapikey.com/v1",
    api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)

stream = client.chat.completions.create(
    model="claude-sonnet-5-5:free",
    messages=[{"role": "user", "content": "Fix the off-by-one error in paginate() and add a test for the last page."}],
    stream=True,  # recommended for long outputs
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.oneaiapikey.com/v1",
  apiKey: process.env.ONEAIAPIKEY_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "claude-sonnet-5-5:free",
  messages: [{ role: "user", content: "Fix the off-by-one error in paginate() and add a test for the last page." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

More: quickstart · API reference · try it in Chat first

Tokens per day, by model

Last 7 days, UTC days

Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.

Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.

Full ranking insights

Claude line-up

Claude Sonnet 5.5 (free lane) or Claude Sonnet 5 or Claude Sonnet 5.5?

Of the 9 Claude models on this site, Claude Sonnet 5 is the step up from Claude Sonnet 5.5 (free lane) and Claude Sonnet 5.5 the step down. Each comparison lists the published rates and limits, then what favours each side.

Claude Sonnet 5.5 (free lane)vsClaude Sonnet 5

Per 1M tokensClaude Sonnet 5.5 (free lane)Claude Sonnet 5
Input$1.4030% less$2
Output$730% less$10
Context1Mthe same1M
Max output128kthe same128k

Pick Claude Sonnet 5.5 (free lane) when

  • cost per request decides it: Claude Sonnet 5.5 (free lane) charges input 30% less and output 30% less than Claude Sonnet 5.

Pick Claude Sonnet 5 instead when

  • Claude Sonnet 5.5 (free lane) does not list Prompt caching and your code depends on it.
  • the client speaks the Anthropic Messages format, as Claude Code does.

Claude Sonnet 5.5 (free lane)vsClaude Sonnet 5.5

Per 1M tokensClaude Sonnet 5.5 (free lane)Claude Sonnet 5.5
Input$1.40the same$1.40
Output$7the same$7
Context1Mthe same1M
Max output128kthe same128k

Pick Claude Sonnet 5.5 (free lane) when

  • the work is writing, which this catalogue lists for Claude Sonnet 5.5 (free lane) and not for Claude Sonnet 5.5.

Pick Claude Sonnet 5.5 instead when

  • Claude Sonnet 5.5 (free lane) does not list Prompt caching and your code depends on it.
  • the client speaks the Anthropic Messages format, as Claude Code does.
  • your workload looks like coding agents, a label the catalogue gives Claude Sonnet 5.5 only.

Use cases

What Claude Sonnet 5.5 (free lane) is listed for, and what it costs

The catalogue lists Claude Sonnet 5.5 (free lane) for daily coding, code review and writing. Each row prices one typical request at the published rates, with the arithmetic shown. Token counts are examples; your prompts will differ.

Model your own traffic

  1. Daily coding

    A bug fix or small feature: 12,000 tokens of the relevant files in, a patch of about 1,500 tokens out.

    A good default for feature work, bug fixes and explaining unfamiliar code.

    “Fix the off-by-one error in paginate() and add a test for the last page.”

    Same request on Claude Sonnet 5 $0.039 and Claude Sonnet 5.5 $0.0273. No other balanced-tier Claude model on this site does this job for less.

    $0.0273

    per change, about 366 per $10

    0.012 × $1.40 + 0.0015 × $7

  2. Code review

    A pull request diff with the code around it: 20,000 tokens in, 1,200 tokens of review comments out.

    Paste a diff and ask for risks, missing tests and edge cases.

    “Review this diff for bugs, missing tests and unclear names. List each issue with its line.”

    Same request on Claude Sonnet 5 $0.052 and Claude Sonnet 5.5 $0.0364. No other balanced-tier Claude model on this site does this job for less.

    $0.0364

    per review, about 274 per $10

    0.02 × $1.40 + 0.0012 × $7

  3. Writing

    A brief plus source notes: 3,000 tokens in, a draft of roughly 1,200 words (1,600 tokens) out.

    Provide tone, audience and length; it follows style instructions closely.

    “Turn these release notes into a 300-word changelog post for developers.”

    Same request on Claude Sonnet 5 $0.022 and Claude Sonnet 5.5 $0.0154. No other balanced-tier Claude model on this site does this job for less.

    $0.0154

    per draft, about 649 per $10

    0.003 × $1.40 + 0.0016 × $7

Overview

When Claude Sonnet 5.5 (free lane) fits

Claude Sonnet 5.5 (free lane) is a balanced model from Anthropic, available here under the exact model id “claude-sonnet-5-5:free”. In the Claude line-up here it sits between Claude Sonnet 5 and Claude Sonnet 5.5. Anthropic has not published a release date we can cite; it has been available here since 11 Nov 2026.

Anthropic documents tools, vision, reasoning and structured output for it, and it reads images as well as text.

It costs $1.40 per million input tokens and $7 per million output tokens, so output is 5× the input rate. On the use cases below, output makes up 38% of the bill for daily coding, 23% for code review and 73% for writing, so trimming the context you send saves more than capping the answer. With a 3:1 input-to-output mix it ranks 21st lowest-cost of the 27 models on this site.

There is no discounted cached-input rate for this model, so every input token bills at $1.40 per million.

It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.

Use Claude Sonnet 5.5 (free lane) with any balance.

Claude Sonnet 5.5 (free lane) is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.

Claude Sonnet 5.5 (free lane) is developed by Anthropic. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by Anthropic.