Tchavi
Why TchaviModelsPricingDocumentationBlog
TchaviTchavi

Frontier AI, paid with mobile money. No card, no KYC.

Product

  • Why Tchavi
  • Pricing
  • Models

Resources

  • Documentation
  • API Reference
  • Blog
  • Support

Legal

  • Privacy
  • Terms of Service

© 2026 Tchavi. All rights reserved.

We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.

Back to models

Claude Sonnet 5.5

anthropic/claude-sonnet-5-5

Sonnet 5.5 — Opus-class answers at the Sonnet price

Claude Sonnet 5.5 costs exactly what Sonnet 5 costs — 5 credits per 1K input — and answers far closer to Opus. Same 1M context, same 128K output, same speed tier. Unless your code forces a specific tool call, there is no reason to send new work to Sonnet 5 instead.

Modalities
Input / Output
5 / 24cr / 1K
Context window
1M
Max output
128K
Capabilities
  • Tools
  • Vision
  • PDF
  • Streaming
  • Prompt caching· read 0.5 cr / 1K

What this model does well

  • 🎯

    Near-frontier quality

    Within a point and a half of Opus 5.5 on published evaluations, at a fifth of the price

  • 📚

    1M token context

    A whole contract, codebase or quarter of tickets in one call

  • 🧠

    Adaptive thinking

    Decides how long to think on its own, and stays quick on easy turns

  • 👁️

    Vision + documents

    Reads images and PDFs in the same request as your text

  • 📤

    128K output

    Long enough for a full report or migration diff in one pass

Example prompts

  • Read this 200-page supplier contract and list every clause that lets them raise prices mid-term.

  • Here is a failing test and the three files it touches. Find the bug and give me the patch.

Good to know

  • Forced tool use is rejected. Anthropic removed `tool_choice: any` and `tool_choice: tool` on this model — a request that forces a specific tool returns a 400. Use Sonnet 5 if your integration depends on forcing a call.
  • Sampling parameters are ignored. Anthropic removed temperature, top_p and top_k on this model, so Tchavi drops them rather than letting the request fail.
  • Text between tool calls arrives in thinking blocks rather than as plain content, so a UI that streams only text can look idle mid-run.

Technical specifications

Author
anthropic
API identifier
claude-sonnet-5-5
Category
Chat & Text
Context window
1,000,000 tokens
Max output
128,000 tokens
Rate limit
400 RPM
Billing unit
token
Streaming
Yes

Ideal for

  • Everything Sonnet 5 does, for the same credits
  • Long contracts and document review
  • Code review and multi-file debugging
  • Customer-facing assistants that need real reasoning
  • Agents with tools, where the model picks the tool

Ready to try it?

Test this model in the playground, no setup needed.

Frequently asked questions

Can I pay with mobile money, without a bank card?

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.

Is the API compatible with OpenAI's?

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.

API

import Tchavi from '@tchavi/sdk';

const client = new Tchavi({ apiKey: 'API_KEY' });

const response = await client.chat.completions.create({
  model: 'claude-sonnet-5-5',
  messages: [
  {
    "role": "user",
    "content": "Hello!"
  }
],
});

console.log(response.choices[0].message.content);
console.log('Credits used:', response.tchavi.credits_used);

API parameters

Every parameter this model accepts on the API. Check the SDK for full typings.

modelRequired
string

ID of the chat model (e.g. `claude-sonnet-5-5`).

messagesRequired
Array<{ role, content }>

Conversation 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`).

temperature
number
Default: 1

Sampling temperature between 0 and 2. Higher values = more random.

max_tokens
integer

Maximum number of tokens to generate in the response.

stream
boolean
Default: false

If true, partial message deltas are streamed as Server-Sent Events.

tools
Array<{ type, function }>

Function-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_choice
"auto" | "none" | { type, function }

How 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`.

Show all parameters (14)
top_p
number
Default: 1

Nucleus sampling: only tokens in the top `top_p` probability mass are considered.

stop
string | string[]

Up to 4 sequences where the API will stop generating further tokens.

frequency_penalty
number
Default: 0

Between -2.0 and 2.0. Positive values penalize tokens that have appeared frequently.

presence_penalty
number
Default: 0

Between -2.0 and 2.0. Positive values encourage the model to talk about new topics.

messages[].content[].image_url
string

Attach 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_url
string

Attach 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
"low" | "medium" | "high"
Default: "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.

Pricing

per 1,000 tokens
5 credits
Input 5 · Output 24 cr/1K

How billing works

  • Billed per token used, down to a thousandth of a credit.
  • A typical message (500 in, 150 out) costs about —, or 6.1 credits.
  • Prompt cache reads: — per 1K tokens (0.5 credits).
Real-world scenarios
Per day
Per week
Per month

Estimated over 30 days, for a typical message: ~500 input + ~150 output tokens, billed to the thousandth of a credit.

A 10 000 F CFA top-up gives you about ~4 918 questions. Pay with Orange Money, MTN MoMo or M-Pesa — no Visa card needed.

Ready to use Claude Sonnet 5.5?

Create your accountAPI Documentation

Bonus credits on your first top-up · No card to sign up