Google

Gemma 3 4b

Name: Gemma 3 4b
Brand: Google
Price: 0.04 USD
Availability: InStock

Gemma 3 4b is a large language model by Google with support for function calling. It supports a 131K token context window with up to 131K tokens of output. Priced at $0.04 per million input tokens and $0.08 per million output tokens, it is one of the most cost-efficient options in its class. Access Gemma 3 4b through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

→Function Calling

Use This Model

Step 1 — Create Router

curl --location 'https://api.inworld.ai/router/v1/routers' \
--header 'Authorization: Basic <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
  "name": "compare-frontier-models",
  "defaultRoute": {
    "route_id": "default",
    "variants": [
      {
        "variant": {
          "variant_id": "deepinfra/gemma-3-4b-a",
          "model_id": "deepinfra/gemma-3-4b"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "google-ai-studio/gemini-2.0-flash-b",
          "model_id": "google-ai-studio/gemini-2.0-flash"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "google-ai-studio/gemini-2.0-flash-001-c",
          "model_id": "google-ai-studio/gemini-2.0-flash-001"
        },
        "weight": 34
      }
    ]
  }
}'

import requests

response = requests.post(
    "https://api.inworld.ai/router/v1/routers",
    headers={
        "Authorization": "Basic <your-api-key>",
        "Content-Type": "application/json",
    },
    json={
        "name": "compare-frontier-models",
        "defaultRoute": {
            "route_id": "default",
            "variants": [
                {
                    "variant": {
                        "variant_id": "deepinfra/gemma-3-4b-a",
                        "model_id": "deepinfra/gemma-3-4b"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "google-ai-studio/gemini-2.0-flash-b",
                        "model_id": "google-ai-studio/gemini-2.0-flash"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "google-ai-studio/gemini-2.0-flash-001-c",
                        "model_id": "google-ai-studio/gemini-2.0-flash-001"
                    },
                    "weight": 34
                }
            ]
        }
    },
)
print(response.json())

const response = await fetch(
  "https://api.inworld.ai/router/v1/routers",
  {
    method: "POST",
    headers: {
      Authorization: "Basic <your-api-key>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      name: "compare-frontier-models",
      defaultRoute: {
        route_id: "default",
        variants: [
          {
            variant: {
              variant_id: "deepinfra/gemma-3-4b-a",
              model_id: "deepinfra/gemma-3-4b",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "google-ai-studio/gemini-2.0-flash-b",
              model_id: "google-ai-studio/gemini-2.0-flash",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "google-ai-studio/gemini-2.0-flash-001-c",
              model_id: "google-ai-studio/gemini-2.0-flash-001",
            },
            weight: 34,
          },
        ],
      },
    }),
  }
);
const data = await response.json();
console.log(data);

Step 2 — Chat Completion

curl --location 'https://api.inworld.ai/v1/chat/completions' \
--header 'Authorization: Basic <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
  "model": "inworld/compare-frontier-models",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

Gemma 3 4b pricing and providers

Access Gemma 3 4b through DeepInfra via Inworld Router or Realtime API. By using the AI provider(s) below you acknowledge you reviewed and agree to their terms listed in the Legal section under the AI provider's name.

					Capabilities	Input modalities	Output modalities
DeepInfra	131.1K	131.1K	$0.04	$0.08

Other Google models available through Inworld

Compare Gemma 3 4b with other Google models available through Inworld Router or Realtime API.

					Capabilities
Gemini 2.0 Flash	1M	8.2K	$0.10	$0.40	+2
Gemini 2.0 Flash 001	1M	8.2K	$0.15	$0.60	+2
Gemini 2.0 Flash Lite	1M	8.2K	$0.075	$0.30	+2
Gemini 2.0 Flash Lite 001	1M	8.2K	$0.075	$0.30	+2
Gemini 2.5 Flash	1M	65.5K	$0.30	$2.50	+4
Gemini 2.5 Flash Image	32.8K	32.8K	$0.30	$2.50	+1
Gemini 2.5 Flash Lite	1M	65.5K	$0.10	$0.40	+4
Gemini 2.5 Flash Lite Preview 09 2025	1M	65.5K	$0.10	$0.40	+4
Gemini 2.5 PRO	1M	65.5K	$1.25	$10.00	+4
Gemini 3 Flash Preview	1M	65.5K	$0.50	$3.00	+4
Gemini 3 PRO Image Preview	65.5K	32.8K	$2.00	$12.00	+1
Gemini 3.1 Flash Image Preview	65.5K	32.8K	$0.50	$3.00	+1
Gemini 3.1 Flash Lite Preview	1M	65.5K	$0.25	$1.50	+4
Gemini 3.1 PRO Preview	1M	65.5K	$2.00	$12.00	+4
Gemini 3.1 PRO Preview Customtools	1M	65.5K	$2.00	$12.00	+4
Gemini Flash Latest	1M	65.5K	$0.30	$2.50	+4
Gemini Flash Lite Latest	1M	65.5K	$0.10	$0.40	+4
Gemini PRO Latest	1M	65.5K	$1.25	$10.00	+4
Gemma 3 12b	131.1K	131.1K	$0.04	$0.13
Gemma 3 27b	131.1K	131.1K	$0.08	$0.16
Gemma 4 26b A4b	—	—	$0.12	$0.39	—
Gemma 4 31b	—	—	$0.13	$0.38	—