claude-3-5-sonnet-20240620 is the date-pinned version of Anthropic Claude 3.5 Sonnet, suitable for question answering, information organization, and iterative revisions using text and images together. On this platform, you can choose Chat Completions to organize messages yourself, or use AI Chat v2 for managed conversations. It is especially suitable for applications that need to retain existing version configurations and should not be mixed with later Sonnet versions.
Point the Base URL to api.acedata.cloud, configure your platform API key and the model ID below, and use your compatible SDK or client.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ACEDATACLOUD_API_KEY"],
base_url="https://api.acedata.cloud/v1",
)
response = client.chat.completions.create(
model="claude-3-5-sonnet-20240620",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Choose an available protocol for this model. OpenAI SDK uses a Base URL ending in /v1; Anthropic SDK uses the root URL. See each guide for protocol-specific parameters, tools and response formats.
Clarify capacity, inputs and outputs, and invocation methods before selecting a model.
The date identifier corresponds to a specific model version; conversation storage and response formats are platform invocation features.
Learn what claude-3-5-sonnet-20240620 can bring to your work.
You can submit screenshots, charts, and text questions together, so responses can focus on visible content. Compared with pasting text alone, multimodal messages preserve page layout and visual relationships, making them suitable for explaining interfaces and organizing information from screenshots. Specifying the area of focus and the conclusions you need helps reduce irrelevant descriptions.
It is suitable for breaking information organization into steps such as extracting key points, drafting an initial version, adding conditions, and revising wording. After saving a conversation with AI Chat v2, you can continue the discussion by providing the same id; applications that need strict control over conversation history can also manage messages themselves in Chat Completions.
The full date ID makes it easier for existing applications to continue using the same version configuration and to record test targets. It differs from series names without dates: when upgrading, explicitly switch models, then compare responses using the same set of inputs. A fixed version does not mean every generation is identical word for word, nor does it guarantee permanent service availability.
Start with specific tasks to identify where the model can be useful.
Provide screenshots of product pages, interfaces, or documents, and specify the fields, areas, or workflows to identify. You can request a page summary, a draft operating guide, or a list of items requiring confirmation. For dense text and key figures, crop the target area first, then verify it against the original image to avoid treating blurry content as conclusive.
Submit existing explanatory text, business rules, or article drafts, and request that they be organized into Q&A, summaries, or revised drafts for specified readers. Refine wording and structure through follow-up questions, making this suitable for content applications with existing Claude 3.5 Sonnet workflows. Delivery requirements should clearly specify facts to retain, parts that may be rewritten, and the output format.
Prepare representative questions, text-and-image samples, and historical responses for applications already using this dated version, and use the same materials to check performance after prompt changes. Deliverables may include records of response differences, omissions, and formatting deviations. When comparing new models, keep inputs consistent rather than judging migration results solely by model names.
Choose based on task complexity, input materials, and expected results.
If an application originally used 20240620 and its prompts and evaluations were built around it, it can be retained for maintenance and regression testing. 20241022 is another dated version and cannot be substituted as an alternative spelling of the same ID. Before switching, compare image-and-text understanding, response structure, and adherence to business rules; do not assume that a newer version will produce the same output as the older one.
New projects should not remain tied to this version long term merely because the Claude 3.5 name is familiar. Anthropic has retired this dated version on the platforms it operates and recommends Claude Sonnet 4.6 as a replacement; this lifecycle arrangement is not equivalent to the service status on this platform. This platform still lists the model at two entry points, but that does not constitute a commitment to continued availability. Compare candidate models using real tasks; if retaining the older version, the focus should be compatibility with existing behavior rather than treating it as a Sonnet with the latest features.
From a small-scale task to formal integration.
Define the goal, required inputs, and output requirements, using real business samples as a starting point.
Open the trial page, confirm the parameters supported by this entry point, then submit a small-scale task to review the results.
Retain the complete model ID, use the request format specified in the documentation, and confirm billing rules on the Pricing page.
Before formal use, understand the output quality and scope of capabilities.
Answers to common questions when using claude-3-5-sonnet-20240620.
No. They are different date versions of Claude 3.5 Sonnet, and you should use their respective full IDs when calling them. Keep the original version configuration when maintaining legacy applications; when preparing to switch, compare answers and formats using the same materials, and do not treat the two dates as interchangeable aliases.
In Chat Completions, structure the user message content as text blocks and image_url blocks; in AI Chat v2, use a structured message. Clearly specify the area of interest and delivery requirements in the text, such as extracting only specified fields, rather than broadly requesting a description of the entire image.
If you already have message management logic, you can choose /v1/chat/completions and read the response from choices. If you want the service to save multi-turn conversations, you can choose /aichat2/conversations, read answer and id, and then use the same id to continue the discussion.
You cannot infer this from the series name. This date version and subsequent Sonnet models must be evaluated separately, and reasoning_effort in a general request does not mean it has the corresponding reasoning level. If a task depends on specific reasoning controls, choose a specific model that explicitly supports that feature.
It is better suited for maintaining existing version configurations and comparative testing. This model has been retired on platforms operated by Anthropic, with Claude Sonnet 4.6 officially recommended as its replacement. The two calling endpoints on this platform still list this ID, but that does not mean it will remain available permanently. New projects should also evaluate newer candidate models and decide on a migration plan based on real image-and-text tasks and business acceptance results.
Model information · Updated: 2026-10-01. For calling parameters and billing rules, see the API and pricing sections.
Choose a development approach or application suited to this model and follow its setup guide.
↗OpenAI Chat Completions API
SDK installation, authentication and examples
↗
↗Claude Code CLI Setup Guide
Coding tool setup · requires a Coding Plan application key
↗Using Ace Data Cloud with Cherry Studio
Chat client setup · Base URL, API key and model
↗Using Ace Data Cloud with ChatBox
Chat client setup · Base URL, API key and model↗Input
$0.60per 1M tokens
Official $3.00
Output
$3.00per 1M tokens
Official $15.00
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs