GigaChat 3 Lightning API — price in US dollars

What GigaChat 3 Lightning is

GigaChat 3 Lightning is the small model of Sber’s GigaChat family: ten billion parameters, fewer than two billion of them active per token. It has a 262,144-token context window, takes text in and gives text out, and belongs to the chat and text generation category. Through kosareva.cloud it is available via one OpenAI-compatible API: the same code as for OpenAI — just change base_url and the key.

GigaChat is not on OpenRouter as of October 2026, and a direct contract for the GigaChat API needs a Russian company or sole proprietor. Here a company outside Russia gets GigaChat 3 Lightning with an English invoice in US dollars from Kosareva Cloud LLC (Armenia) and pays by bank transfer. Requests to GigaChat 3 Lightning are processed in Russia.

One key opens more than GigaChat 3 Lightning: the catalog has over a hundred models, including the other GigaChat and Yandex models. That matters more than it seems: models age within months, and moving to the next version is one line of code, not a new contract and a new integration.

GigaChat 3 Lightning strengths and weaknesses

Who it suits. A pipeline on texts of a few hundred tokens and up: labelling and classifying requests, extracting fields from documents, a first filter before a more expensive model. On one-line requests there is no saving — the overhead outweighs it.

What to compare it with. Against GigaChat 3.5 Ultra ($1.58 / $4.73) it wins from about 70 tokens of your text: on shorter requests Ultra is cheaper despite a price list eight times higher. Against Alice AI Flash ($1.64 / $3.27) the break-even is about 126 tokens: Alice’s service overhead is about ten tokens, so on very short requests it is cheaper. Against GigaChat 3 Pro it is cheaper at any request size.

GigaChat 3 Lightning among the GigaChat models

GigaChat 3 Lightning is the entry model of the family: the same 262K context as GigaChat 3.5 Ultra and GigaChat 3 Pro, eight times cheaper than Ultra on input and over twenty times on output. It is the model for volume, not for hard tasks: for long reasoning take Ultra. GigaChat 2 Max is the previous generation, for existing integrations only.

GigaChat 3 Lightning price in US dollars

Approximate: the catalog price (17.08 ₽ per 1M tokens for both input and output) divided by 85.5 ₽ per $1, ID Bank’s non-cash rate on 3 October 2026. Your balance is kept in rubles; a USD invoice is converted at ID Bank’s non-cash rate on the invoice date. The vendor’s service prompt, about 990 tokens per request, is billed as input. You pay only for actual usage.

What a typical task costs on GigaChat 3 Lightning

A price per million tokens says little on its own, so here are four common tasks at GigaChat 3 Lightning rates: $0.20 per million input tokens and $0.20 per million output tokens, plus the vendor’s service prompt of about 990 input tokens on every request.

Calculated from the current kosareva.cloud price list, in US dollars at 85.5 ₽ per $1, with the service prompt included.

GigaChat 3 Lightning cost calculator

Move the sliders to your volume — the monthly cost in US dollars updates at once, with no sign-up.

At $0.20 per million input tokens and $0.20 per million output tokens; approximate, at 85.5 ₽ per $1. Each request also carries the vendor’s service prompt of about 990 input tokens — it is already in the numbers. Billed for actual usage.

How to connect GigaChat 3 Lightning

Use the standard OpenAI SDK with the kosareva.cloud base_url and the model gigachat-3-lightning. In existing code you change exactly two lines: the address and the key.

Python, OpenAI SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_KOSAREVA_KEY",
    base_url="https://api.kosareva.cloud/v1",
)

response = client.chat.completions.create(
    model="gigachat-3-lightning",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Python without the SDK: requests

import requests

response = requests.post(
    "https://api.kosareva.cloud/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_KOSAREVA_KEY"},
    json={
        "model": "gigachat-3-lightning",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
    timeout=600,
)
print(response.json()["choices"][0]["message"]["content"])

cURL

curl https://api.kosareva.cloud/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KOSAREVA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gigachat-3-lightning","messages":[{"role":"user","content":"Hello!"}]}'

The same key works with any client that supports an OpenAI-compatible endpoint: LangChain, LlamaIndex, Cursor, Continue, n8n. You don’t need a separate key per model — one key opens the whole catalog.

GigaChat 3 Lightning endpoints and parameters

The gateway follows the OpenAI schema, so parameter names and the response format are the ones you know. One base address for every model in the catalog.

Request long answers with stream: true: with a large max_tokens, a regular request stays silent until generation ends and can hit your HTTP client’s timeout. In streaming mode the first tokens arrive within seconds, and the timeout problem goes away.

Specifications

What GigaChat 3 Lightning is good for

• Labelling and classification of requests and texts in Russian
• Extracting fields from documents
• A first-pass filter before a larger model

What to keep in mind with GigaChat 3 Lightning

Count by your average request, not by the price list: take its length in tokens plus 990, multiply by $0.20 and divide by a million — that is the price of one request. The classic saving works: Lightning sorts out the simple cases on the first pass, the unclear ones go to a more expensive model. But if your requests are shorter than a hundred tokens, check Alice AI Flash first — at that length it comes out cheaper.

First, context runs out faster than it seems. In a dialogue the whole conversation goes into the input, not just the last message, so a long chat gets more expensive with every turn. If the history isn’t needed for the answer, trim it: savings on input tokens usually matter more than picking a cheaper model.

Second, the 262K-token window is shared between the request and the answer: the more you send, the less room the model has to generate. Set max_tokens on purpose, not “with a margin”.

Third, the balance is shared by all models in the catalog. You don’t have to decide in advance how much money to “put on GigaChat 3 Lightning”: the same funds go to any other model if you switch tomorrow. Usage per model is shown in the dashboard on a separate line, with the number of requests and tokens.

GigaChat 3 Lightning for companies outside Russia

GigaChat 3 Lightning, the smallest and cheapest GigaChat: $0.20 per million tokens for input and output, a 262K context, requests processed in Russia. Access through kosareva.cloud with an OpenAI-compatible API and a USD invoice for companies.

• Register as “Company or sole proprietor” → “In another country”: country of registration, company registration number, tax ID if you have one.
• In “Top up balance”, “Issue invoice (companies)” gives an English invoice in US dollars from Kosareva Cloud LLC (Armenia): minimum $50, due in 10 days.
• Pay by bank transfer to our USD account at ID Bank. The balance is credited after the bank confirms the payment, usually in 1–3 business days.
• Cards issued outside Russia are not accepted. Invoices are in USD; for EUR, write to us.
• Pay only for actual usage, no subscription. One OpenAI-compatible API for GigaChat 3 Lightning and over a hundred other models with one key.

Contract and payment. Your contract and payment are with Kosareva Cloud LLC (Armenia), not with the model vendor. You are responsible for compliance with the rules of your jurisdiction; if in doubt, check with your counsel.

Requests to GigaChat 3 Lightning are processed in Russia. If data protection rules apply to you, assess the transfer before you send personal data.

Other GigaChat models

Price per 1M input tokens. Output prices and a monthly estimate for each — on the GigaChat page.

GigaChat 3 Lightning questions