Choose an existing Claude model to work with a written task, technical document or code excerpt. Provide the relevant evidence, describe the operation and define the answer you want to review. The current family includes Sonnet, Opus, Fable and Haiku entries, with Messages and Chat Completions options. Output controls and online response handling depend on the selected model, so use its current settings and inspect the complete reply and token usage.
Claude is developed by Anthropic. Vidgo provides access to the models. Model names and trademarks belong to their respective owners.Open a card to review the available protocol, context information, output controls and token rates. Prepare the document, code or task brief you intend to use, then evaluate the response against its source and completion criteria.
Claude Sonnet 5.5 handles coding, long-context analysis, and image understanding with adaptive thinking and a 1M-token context window.
Claude Opus 5.5 combines adaptive reasoning and a 1M-token context for long-running coding, document analysis, and visual understanding.
Anthropic Claude models for long-running agentic coding, multi-step reasoning, daily coding, tools, and analysis.
Anthropic Claude models for long-running agentic coding, multi-step reasoning, daily coding, tools, and analysis.
Anthropic Claude models for long-running agentic coding, multi-step reasoning, daily coding, tools, and analysis.
Claude Opus 4.8 handles agentic coding, long-context analysis, and image understanding with a 1M-token context window.
Claude Opus 4.7 supports coding, reasoning, and analysis with a 1M-token context window and up to 128K output tokens.
Claude Sonnet 4.6 and Opus 4.6 for coding, agents, and long-context analysis.
Claude Sonnet 4.6 and Opus 4.6 for coding, agents, and long-context analysis.
Claude Opus, Sonnet, and Haiku 4.5 for coding, analysis, and fast text generation.
Claude Opus, Sonnet, and Haiku 4.5 for coding, analysis, and fast text generation.
Claude Opus, Sonnet, and Haiku 4.5 for coding, analysis, and fast text generation.
Messages requests use model, messages and max_tokens, with a separate system field when supported. Chat Completions uses messages and the settings provided by the selected task. The Sonnet 5.5 online request exposes system instructions and the output-token limit; Opus 4.7’s Messages settings also offer output_config.effort. Choose the protocol first, then use its matching fields and response handling.
| Model / task | Input and workflow |
|---|---|
| Claude Sonnet 5.5 | Claude Sonnet 5.5 handles coding, long-context analysis, and image understanding with adaptive thinking and a 1M-token context window. |
| Claude Opus 5.5 | Claude Opus 5.5 combines adaptive reasoning and a 1M-token context for long-running coding, document analysis, and visual understanding. |
| Claude Fable 5.1 | Anthropic Claude models for long-running agentic coding, multi-step reasoning, daily coding, tools, and analysis. |
| Claude Opus 5 | Anthropic Claude models for long-running agentic coding, multi-step reasoning, daily coding, tools, and analysis. |
| Claude Sonnet 5 | Anthropic Claude models for long-running agentic coding, multi-step reasoning, daily coding, tools, and analysis. |
| Claude Opus 4.8 | Claude Opus 4.8 handles agentic coding, long-context analysis, and image understanding with a 1M-token context window. |
| Claude Opus 4.7 | Claude Opus 4.7 supports coding, reasoning, and analysis with a 1M-token context window and up to 128K output tokens. |
| Claude Sonnet 4.6 | Claude Sonnet 4.6 and Opus 4.6 for coding, agents, and long-context analysis. |
| Claude Opus 4.6 | Claude Sonnet 4.6 and Opus 4.6 for coding, agents, and long-context analysis. |
| Claude Opus 4.5 | Claude Opus, Sonnet, and Haiku 4.5 for coding, analysis, and fast text generation. |
| Claude Sonnet 4.5 | Claude Opus, Sonnet, and Haiku 4.5 for coding, analysis, and fast text generation. |
| Claude Haiku 4.5 | Claude Opus, Sonnet, and Haiku 4.5 for coding, analysis, and fast text generation. |
Sonnet 5.5 and Opus 5.5 support different levels of software development and professional analysis. The charts show their published evaluations across coding, reasoning and knowledge work, including the settings noted in each image. Choose the Claude model that fits your task, then provide the relevant code or documents and the criteria for a useful result.
Sonnet 5.5 combines coding, reasoning and knowledge-work capabilities in a model suited to well-scoped daily tasks. Its evaluation covers terminal programming, code changes and professional work. Supply the relevant code or source documents with clear requirements to prepare a bug fix, organize information or produce a complete draft.
Opus 5.5 is designed for work that requires careful judgment across multiple steps. Its published results cover coding, scientific reasoning and professional workflows. Describe the project context, constraints and expected deliverables so the model can help analyze a difficult problem, plan an implementation or develop a detailed explanation.
Prepare the source material and explain its role in the task. Request an analysis, review, structured extraction or complete draft with clear constraints, then check the answer against the facts and intended use. Continue with specific corrections or test feedback when refining the work.
Provide the relevant passages and state the question and required structure. Review the returned analysis against the document before using it in a working note or technical decision.
Supply the code, expected behavior and checks that matter. Ask for a review tied to those requirements, then verify proposed changes with tests and add the results to the next conversation turn.
Define the fields, units and output shape and provide the complete source text. Validate the generated data before adding it to a product-content workflow or application prototype.
Prepare the facts, target audience and required sections. Generate an explanation and review its meaning and necessary details before using it as an article, product explanation or project document.
Describe the reader’s issue, permitted actions and information to request. Review the reply for an accurate resolution, appropriate tone and clear next steps before using it in your communication workflow.
Prepare the text task in Messages or Chat Completions, following the selected Claude entry’s available settings and response handling. Review the answer, token usage and integration requirements before adopting the workflow.
The table reads the current starting input-token rate for each Claude entry per one million tokens. A complete request also includes output-token usage and applicable cache-read or cache-write categories listed on the selected task page, including a one-hour cache-write rate where shown. The rates vary across entries. Review the full price table and actual usage, with the conversation history sent in each turn, when planning your workflow.
| Model | Provider | Workflow | Input | API formats | Starting input rate |
|---|---|---|---|---|---|
| Claude Sonnet 5.5 | Anthropic | Chat | Text instructions and conversation context | Claude Messages / Chat Completions | $1.6 / 1M tokens |
| Claude Opus 5.5 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $3.2 / 1M tokens |
| Claude Fable 5.1 | Anthropic | Chat | Text instructions and conversation context | Claude Messages / Chat Completions | $8 / 1M tokens |
| Claude Opus 5 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $2 / 1M tokens |
| Claude Sonnet 5 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $0.85 / 1M tokens |
| Claude Opus 4.8 | Anthropic | Chat | Text instructions and conversation context | Claude Messages / Chat Completions | $4 / 1M tokens |
| Claude Opus 4.7 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $4 / 1M tokens |
| Claude Sonnet 4.6 | Anthropic | Chat | Text instructions and conversation context | Claude Messages / Chat Completions | $1.44 / 1M tokens |
| Claude Opus 4.6 | Anthropic | Chat | Text instructions and conversation context | Claude Messages / Chat Completions | $2.7 / 1M tokens |
| Claude Opus 4.5 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $4 / 1M tokens |
| Claude Sonnet 4.5 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $2.4 / 1M tokens |
| Claude Haiku 4.5 | Anthropic | Chat | Text instructions and conversation context | Chat Completions / Claude Messages | $0.8 / 1M tokens |
Test a complete text task online, then integrate the selected model and API format.
Open the selected model, provide the task and source text, and choose its available output settings. Submit the conversation, read the complete answer and inspect available token usage. Add clarifications or test feedback when preparing a follow-up.
Use the existing model conversation, current token prices and task documentation to connect a reviewed answer with your application workflow.
Choose a Claude entry by the protocol, context information, output controls and token prices shown in its current task page. Prepare a complete text or coding task and the supporting material, then inspect how the chosen model responds before adopting the workflow.
Open the selected model, provide the task and source text, and choose its available output settings. Submit the conversation, read the complete answer and inspect available token usage. Add clarifications or test feedback when preparing a follow-up.
The table reads the current starting input-token rate for each Claude entry per one million tokens. A complete request also includes output-token usage and applicable cache-read or cache-write categories listed on the selected task page, including a one-hour cache-write rate where shown. The rates vary across entries. Review the full price table and actual usage, with the conversation history sent in each turn, when planning your workflow.
Use /v1/messages with model, messages and the selected task’s accepted settings, or /v1/chat/completions with the compatible conversation fields. Follow the protocol documentation for authentication and response fields. In the current Messages online workflow, Sonnet 5.5 and Opus 4.7 stream text; other listed Messages workflows read a complete reply. The 4.5 Chat Completions workflows also read a complete reply, while the other listed Chat Completions workflows stream.
Use your Vidgo API credentials to authenticate the request to the selected endpoint. Send the exact model identifier, the conversation fields required by that protocol and the supported output settings. Consume the returned response using the same format you selected.
Accumulate streaming text when the selected workflow streams, or read the complete response body when it returns a full reply. Inspect the final answer and returned usage fields, then keep the relevant messages for the next turn. Return to the model conversation when continuing the online task.
Choose an existing Claude model to work with a written task, technical document or code excerpt. Provide the relevant evidence, describe the operation and define the answer you want to review. The current family includes Sonnet, Opus, Fable and Haiku entries, with Messages and Chat Completions options. Output controls and online response handling depend on the selected model, so use its current settings and inspect the complete reply and token usage.
Read language-model introductions, API guides and platform comparisons to understand model selection, conversation inputs, response formats and token costs.
