Grok 4.20 Multi-Agent API: toman pricing and code
x-ai/grok-4.20-multi-agent
visionreasoningjsonfilesYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 58,025 toman / 1M. Web search: 1,450.63 toman / request.Pricing and top-ups
Grok 4.20 Multi-Agent example: reading an image into JSON
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "x-ai/grok-4.20-multi-agent",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "Return only the invoice number and the total, as JSON."},
{"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
]
}]
}'import base64, json
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
img = base64.b64encode(open("factor.jpg", "rb").read()).decode()
resp = client.chat.completions.create(
model="x-ai/grok-4.20-multi-agent",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
],
}],
response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))import OpenAI from "openai";
import { readFileSync } from "node:fs";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");
const resp = await client.chat.completions.create({
model: "x-ai/grok-4.20-multi-agent",
messages: [{
role: "user",
content: [
{ type: "text", text: "Return the invoice number, the date and the total as JSON." },
{ type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
],
}],
response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));What is Grok 4.20 Multi-Agent good for?
Grok 4.20 Multi-Agent is one of xAI's models. Put "x-ai/grok-4.20-multi-agent" in the model field and the rest of your code stays as it is. Grok 4.20 Multi-Agent keeps 2,000,000 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 1,800,000 tokens. On price it sits in the "mid-range" band — cheaper than 228 and dearer than 178 of the other paid models in the catalogue.
What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; it takes files such as PDFs as input; it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.
Input runs at 362,656 toman per 1M tokens and output at 725,313 — output costs 2× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 58,025 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.
The closest alternative with the same capabilities from a different provider is Nano Banana (Gemini 2.5 Flash Image): Grok 4.20 Multi-Agent works out roughly 1.3× more expensive, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.
To make the figure concrete: 100,000 toman of credit buys roughly 71 thousand-word requests on Grok 4.20 Multi-Agent, and every 1,000 toman is about 707 words of round trip. A job with one million input tokens and one million output tokens comes to 1,087,969 toman in total. Filling this model's 2,000,000-token window costs 725,313 toman on the input side alone, which is the real reason to keep conversation history short.
xAI has 8 models in our catalogue; the cheapest is Grok 4.3 (batch) at 1,131 toman per thousand words and the dearest Grok Latest at 3,017. Among the less common parameters it accepts logprobs, reasoning_effort, top_logprobs — all through the standard request body. It does not support tool_choice, tools, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Auto Router at 2,000,000 tokens.
Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, pulling text and fields out of images, extracting data against a fixed schema, analysing a long document or codebase in one request.
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 834 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 1,886 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 58,025 toman |
Frequently asked
- How do I call Grok 4.20 Multi-Agent from Iran?
- Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "x-ai/grok-4.20-multi-agent". Nothing else in your code changes.
- What does Grok 4.20 Multi-Agent cost in toman?
- 362,656 toman per 1M input tokens and 725,313 toman per 1M output tokens; a 1,000-word request is around 1,414 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Grok 4.20 Multi-Agent take?
- Up to 2,000,000 tokens per request, roughly 1,500k words. A single answer can reach 1,800,000 tokens.
- Does Grok 4.20 Multi-Agent support streaming and image input?
- Streaming (stream=true) works on every model here. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.