Gemini 4 Argon

Specs & limits

Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving and autonomous multi-step agents. Thinking has three levels (low, medium, high), with no off setting and no numeric thinking budget. The output price includes thinking tokens. The published rate is introductory: input and output both double on 1 December 2026, and cached input doubles with them.

per Google official docs ↗

Use Gemini 4 Argon in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gemini-4-argon",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://synthorai.io/v1",
  apiKey: "sk-syn-...",
});

const resp = await client.chat.completions.create({
  model: "gemini-4-argon",
  messages: [{ role: "user", content: "Summarize this diff" }],
  reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);

curl https://synthorai.io/v1/chat/completions \
  -H "Authorization: Bearer sk-syn-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-4-argon",
    "messages": [{"role": "user", "content": "Hello"}],
    "reasoning_effort": "medium"
  }'

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://synthorai.io/v1"),
		option.WithAPIKey("sk-syn-..."),
	)
	resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
		Model: "gemini-4-argon",
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("Summarize this diff"),
		},
		ReasoningEffort: openai.ReasoningEffortMedium,
	})
	fmt.Println(resp.Choices[0].Message.Content)
}

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://synthorai.io/v1")
    .apiKey("sk-syn-...")
    .build();

ChatCompletion resp = client.chat().completions().create(
    ChatCompletionCreateParams.builder()
        .model("gemini-4-argon")
        .addUserMessage("Summarize this diff")
        .reasoningEffort(ReasoningEffort.MEDIUM)
        .build());
System.out.println(resp.choices().get(0).message().content().orElse(""));

About Gemini 4 Argon

• Its official model page describes it as built for complex software engineering, deep mathematical and scientific problem solving and autonomous multi-step agents.
• It accepts text, images, audio, video and PDF input and returns text.
• The context window is one limit of 1,048,576 tokens shared by input and output, rather than separate input and output ceilings, and a single synchronous request returns up to 65,536 output tokens (32,768 without streaming).
• Thinking works differently from earlier Gemini models: the model page lists three levels, low, medium and high, with no off setting and no numeric thinking budget, so through Synthorai a request that asks for the least reasoning runs at low.
• Google's documentation also says custom temperature, top_p and top_k values are ignored.
• The pricing detail to plan around is that the published rate is introductory rather than settled: $2 per million input tokens and $10 per million output tokens hold through 30 November 2026, and both double on 1 December 2026, to $4 and $20.
• Cached input moves on the same date, from $0.10 to $0.20 per million tokens.
• Anything sized on today's price is worth re-checking before December rather than after it.
• The output price includes thinking tokens, so a reasoning-heavy answer is billed on the full trace rather than only the visible text; budget max output tokens with that in mind.
• Google's published Standard table lists a single input rate covering text, image, video and audio, with no context-length step, so a long prompt and media input bill at the same rate as text.
• Caching is implicit only: there is no explicit cache to create or manage.
• Synthorai serves it through the OpenAI-compatible chat completions endpoint, so it drops into an existing integration without a Google-specific client.

FAQ

Related models

Compare