Claude Opus 4.7 API
anthropic/claude-opus-4.7Claude Opus 4.7 works across code, documents, and image context to produce detailed reasoning and reviewable answers. Its 1M-token context window and 128K-token maximum output support connected coding tasks through Chat Completions and Claude Messages.
Claude Opus 4.7
Anthropic · chat-completions
Quick start
Send a POST request to /v1/chat/completions with anthropic/claude-opus-4.7. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- anthropic/claude-opus-4.7
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | anthropic/claude-opus-4.7 |
| messages | Required | A non-empty array of conversation messages. |
| max_tokens | Optional | A positive integer; the model API maximum is 128,000 output tokens, and this playground offers 1–65,536. |
| temperature | Optional | Sampling temperature; the playground allows 0–2. |
| top_p | Optional | Nucleus sampling probability; the playground allows 0–1. |
| stream | Optional | Returns an SSE event stream when true. |
Response and usage
Successful responses include generated content and usage. Billing settles from actual input, output, and cache tokens.
Streaming
Set stream: true to read SSE. Finalize usage accounting from the terminal usage event.
curl --request POST \
--url https://api.vidgo.ai/v1/chat/completions \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "anthropic/claude-opus-4.7",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Explain why deterministic retries matter in distributed systems."
}
],
"max_tokens": 4096,
"temperature": 1,
"top_p": 1,
"stream": false
}'Keep API keys on the server. Never expose them in browser code or public repositories.
Continue with
Related Models
Claude Opus 4.7 API frequently asked questions
What is the Claude Opus 4.7 API?
Claude Opus 4.7 is an Anthropic model for coding, reasoning, and long-context analysis. On Vidgo AI it accepts Chat Completions at /v1/chat/completions and Claude Messages at /v1/messages. Its 1M-token context window supports connected work across extensive source material.
How can Claude Opus 4.7 help with coding tasks?
Supply the target behavior, relevant files, constraints, and test results. The model can use that context to draft code, examine edge cases, and review the result against your criteria.
What is the Claude Opus 4.7 context window?
The context window is 1,000,000 tokens. Include the files, documents, and conversation turns needed to compare evidence across the task.
How do I set reasoning effort?
Set output_config.effort to low, medium, high, xhigh, or max in a Claude Messages request. The default is high.
What output limit applies to Claude Opus 4.7?
The model API supports up to 128,000 output tokens. Set max_tokens for each Claude Messages request. The on-page Playground offers a separate 1–65,536-token control.
How can Claude Opus 4.7 analyze images?
Place an image block alongside text in messages.content and ask a focused question about the visual details. The model returns a text response that uses the supplied image context.
How can I use tools with Claude Opus 4.7?
Define available tools in the request. When the model returns a tool call, your application executes it and sends the result in the next conversation turn.
What does Claude Opus 4.7 cost on Vidgo AI?
Input costs 800 credits ($4.00) per 1M tokens; output costs 4000 credits ($20.00) per 1M tokens. Use the reported token counts to calculate a request’s charge.