Morph V3 Fast
Neural Network
Morph V3 Fast is a code model that applies prepared edits to a file at a speed of about 10,500 tokens per second.
Specifications
- Input
- text, images, documents
- Output
- text
- Context size
- 262 144 tokens
- Max answer length
- 131 072 tokens
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
// Sync - Text generation
async function main() {
const chatCompletion = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'morph-v3-fast',
});
}
// Async - Text generation
async function main() {
const stream = await openai.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'morph-v3-fast',
stream: true
});
for await (const chunk of stream) {
const part: string | null = chunk.choices[0].delta?.content ?? null;
}
}
main();
How it works Morph V3 Fast?
Morph V3 Fast is a model by Morph designed for a single narrow task: accurately applying ready-made edits to existing code. It does not write solutions from scratch but quickly rewrites files based on instructions—about 10,500 tokens per second with a claimed 96% accuracy. The request follows a strict three-part template: instructions, source code, and the edit fragment, making it easy to call programmatically within an editor or pipeline. In BotHub, access to Morph V3 Fast is available without a VPN or foreign card: pay in rubles with Russian cards, pay-as-you-go, no subscription, and unused tokens do not expire. A unified OpenAI-compatible API allows you to connect the model once and switch to others in one window; traffic is encrypted via AES-GCM, and teams have access to contracts, invoices, EDI, and an admin panel with limits. You can assign it mass refactoring across a repository, applying diffs from an architect model, auto-fixes after reviews and linters, library version migrations, and quick edits in agent tools where latency is critical.Frequently asked questions about Morph V3 Fast
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
morph-v3-fast is a text model from Morph focused on fast code operations: editing files, refactoring, and analyzing fragments. It accepts not only text but also documents with images, making it suitable for tasks where you need to read the context and quickly return a ready result.
Up to 38,000 output tokens per response with a 32,000 token context window. This is enough for a large file with edits or a detailed task analysis. If there is more material, split the work into parts and pass the intermediate result to the next request.
A separate reasoning mode for morph-v3-fast is not noted in our data—the model is designed primarily for response speed. If you need step-by-step reasoning, ask for it directly in the prompt or switch to a reasoning model in the same BotHub window.
Our data does not indicate support for function calling or strict structured JSON, so do not rely on it without verification. You can describe the required format in the prompt, and for strict schemas, choose another model—you won't need to rewrite the unified BotHub API.
You can upload images and documents: the model parses them and responds with text. Audio and video are not supported as inputs—for transcribing recordings or working with videos, switch to a specialized model available in the same BotHub interface.
We do not provide specific data on Russian language quality for morph-v3-fast, so we make no promises—it is more reliable to test it on your actual task. In BotHub, this is available from Russia without a VPN or foreign card, and the model can be changed with one click if needed.