NewGPT Image 2.6, Kling V4 and Kimi K3.1 Pro are now available.

Tchavi
ModelsPricingDocumentationBlog
Tchavi
  • Why Tchavi
  • Models
  • Pricing

Tchavi is an OpenAI-compatible AI API: 130+ models, from text to video, topped up with mobile money in FCFA or your local currency, no bank card needed.

  • support@tchavi.com
  • Support

Popular models

  • GPT-6 Sol API
  • Claude Sonnet 5.5 API
  • Claude Opus 5.5 API
  • Gemini 4 Argon API
  • DeepSeek V4.1 Flash API
  • Nano Banana 2.1 (images)
  • GPT Image 2 (images)
  • Wan 3.0 (video)
  • All 130+ models

Developers

  • Quickstart
  • API Reference
  • Claude Code
  • Cursor
  • SDKs

Resources

  • Documentation
  • Blog
  • Image models
  • Video models
  • Music models
  • Audio models
  • Mobile money payments
  • Pay for AI APIs with M-Pesa
  • Claude Code with mobile money

Legal

  • Privacy
  • Terms of Service

APIs by creator

  • OpenAI API
  • Gemini API
  • Claude API
  • Qwen API
  • DeepSeek API
  • Seedance API
  • MiniMax API
  • Mistral API

Mobile money payments · Available in 12 countries: Benin, Cameroon, Congo, Côte d'Ivoire, DR Congo, Gabon, Kenya, Rwanda, Senegal, Sierra Leone, Uganda, and Zambia. Operators: Moov Money, MTN MoMo, Airtel Money, Orange Money, M-Pesa, Free Money, and Zamtel Kwacha.

© 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 Opus 4.8

anthropic/claude-opus-4-8

Opus 4.8 — the last of the 4.x Opus line

Claude Opus 4.8 is the final 4-series Opus: the most reliable of the three on long agentic work, at the same 11 credits per 1K input. Choose it over Opus 5 when you want the 4.x behaviour your prompts were written against.

Modalities
-25%
Input / Output
8.25 / 41.25cr / 1K11 / 55Offer ends January 1, 2028
Context window
1M
Max output
128K
Capabilities
  • Tools
  • Vision
  • PDF
  • Streaming
  • Prompt caching· read 1.1 cr / 1K

What this model does well

  • 📚

    1M token context

    Swallow whole codebases or quarterly reports in one prompt

  • 🧠

    Deep reasoning

    Multi-step problems, ambiguous specs, contested trade-offs

  • 🤖

    Agentic by design

    Plans, calls tools, recovers from errors across long horizons

  • 💻

    Elite coding

    Refactors, debugs and reviews at senior-engineer quality

  • 👁️

    Vision + documents

    Reads images and PDFs natively in the same call

  • 🗓️

    Fresh knowledge

    Knowledge current to January 2026

Example prompts

  • Review this 800-line service file and propose three refactors that would simplify it without changing behavior

  • I'm pasting our entire codebase below. Find every place we mutate user state outside a transaction and rank by severity.

Good to know

  • Superseded. Opus 5.5 is newer and costs less per token (10/48 credits against 12/60), so there is no reason to choose 4.8 for new work.
  • Sampling parameters are ignored. Anthropic removed temperature and top_p on this model, so Tchavi drops them rather than letting the request fail.
  • JSON output takes response_format json_schema with your schema. Plain JSON mode (json_object) is refused with a 400 unsupported_parameter.

Technical specifications

Provider
anthropic
API identifier
claude-opus-4-8
Category
Chat & Text
Context window
1,000,000 tokens
Max output
128,000 tokens
Rate limit
150 RPM
Billing unit
token
Streaming
Yes

Ideal for

  • Long refactors with many constraints
  • Compliance and policy review
  • Technical research with citations
  • Planning agents that must not lose state
  • Audits of another model's output

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-opus-4-8',
  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-opus-4-8`).

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

-25%Limited offer: the discount applies to every price for this model until January 1, 2028.
per 1,000 tokens
8.25 credits
Input 11 · Output 55 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 10.313 credits.
  • Prompt cache reads: — per 1K tokens (0.825 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 ~2 909 questions. Pay with Orange Money, MTN MoMo or M-Pesa — no Visa card needed.

Ready to use Claude Opus 4.8?

Create your accountAPI Documentation

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