We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
anthropic/claude-opus-5-5Frontier Claude for long-running agents and deep work
Claude Opus 5.5 is the model Anthropic says to try first for most workloads, sitting just below Fable 5.1 in its lineup. It holds a 1M-token context and always thinks before it answers.
It is built for long-running agentic coding and knowledge work: repository-wide refactors, many-tool agents, analysis of long case files. According to Anthropic, it reaches Fable 5.1 level on most tasks and generates over 30% faster than Opus 5.
Through Tchavi you pay with mobile money, no card and no KYC, and one API key opens 100+ models. Change your OpenAI SDK's base URL and your credits never expire.
Built for agentic coding and knowledge work over long sessions
A whole repository or case file in a single request
Always on: the model sets its own reasoning effort
Reads screenshots, charts and PDFs in the same request as your text
Long enough for a full migration diff or a detailed report
Chains function calls across many steps
Here is our whole API surface. List every endpoint reachable without authentication, explain the blast radius of each, rank them by severity and propose a one-line fix.
Compare these two architectures against our constraints (a team of four, Friday load spikes, mobile money payments) and recommend one, naming explicitly what we give up.
Here is a repository of 200 JavaScript files. Plan the migration to TypeScript as ordered steps, name the risk of each step and write the diff for the first one.
Opus 5.5 for any new project: it is Anthropic's current version. Keep Opus 5 only if your code turns thinking off or forces a specific tool, two things Opus 5.5 rejects.
Start with Opus 5.5, as Anthropic recommends. Move to Fable 5.1 for the most demanding reasoning and very long agentic runs, or when your tests on Opus 5.5 at high effort still fall short. Fable is slower.
1M tokens in and up to 128K out, per Anthropic's specifications.
Yes, images and documents in the same request as the text. The reply is text.
With the OpenAI SDK, change the base URL, use your sk-tch-… key and model: "claude-opus-5-5" on /v1/chat/completions. The Anthropic-format /v1/messages endpoint works too.
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const response = await client.chat.completions.create({
model: 'claude-opus-5-5',
messages: [
{
"role": "user",
"content": "Hello!"
}
],
});
console.log(response.choices[0].message.content);
console.log('Credits used:', response.tchavi.credits_used);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredID of the chat model (e.g. `claude-opus-5-5`).
messagesRequiredConversation messages. Each item has a `role` (system/user/assistant) and a `content` that's either a plain string or an array of content blocks (`text`, `image_url`, `document_url`).
temperature1Sampling temperature between 0 and 2. Higher values = more random.
max_tokensMaximum number of tokens to generate in the response.
streamfalseIf true, partial message deltas are streamed as Server-Sent Events.
toolsFunction-calling toolbox. Pass an array of `{ type: "function", function: { name, description, parameters } }`. Returned tool calls land in `choices[].message.tool_calls`. Only models with `supportsTools: true` accept this.
tool_choiceHow the model picks among tools: `"auto"` (default), `"none"` to force a plain text reply, or `{ type: "function", function: { name } }` to force a specific tool. Only with `supportsTools: true`.
top_p1Nucleus sampling: only tokens in the top `top_p` probability mass are considered.
stopUp to 4 sequences where the API will stop generating further tokens.
frequency_penalty0Between -2.0 and 2.0. Positive values penalize tokens that have appeared frequently.
presence_penalty0Between -2.0 and 2.0. Positive values encourage the model to talk about new topics.
messages[].content[].image_urlAttach an image on a user message. Pass a content block `{ "type": "image_url", "image_url": { "url": ... } }`. PNG / JPEG / WebP, up to 4 per request. Only models with `supportsImageInput: true` accept this block (e.g. `gpt-4o`, `claude-opus-4-7`).
messages[].content[].document_urlAttach a PDF on a user message. Pass a content block `{ "type": "document_url", "document_url": { "url": ... } }`. Up to 5 PDFs per request. Only models with `supportsDocuments: true` accept this block (e.g. `claude-sonnet-4-6`, `gpt-4.1`).
effort"high"Reasoning depth on Anthropic adaptive-thinking models (Opus 4.7+ / Sonnet 4.6+). Values `"low"`, `"medium"`, `"high"`. Higher = more deliberate, slower. Defaults to `"high"` on Opus 4.8.
Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.