Llama 3.3 Instruct 70b Turbo

Name: Llama 3.3 Instruct 70b Turbo
Brand: Meta
Price: 0.1 USD
Availability: InStock

Llama 3.3 Instruct 70b Turbo is a large language model by Meta with support for function calling. It supports a 131K token context window with up to 131K tokens of output. Priced at $0.1 per million input tokens and $0.32 per million output tokens, it is one of the most cost-efficient options in its class. Access Llama 3.3 Instruct 70b Turbo 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/llama-3-3-instruct-70b-turbo-a",
          "model_id": "deepinfra/llama-3-3-instruct-70b-turbo"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "deepinfra/llama-3-instruct-8b-b",
          "model_id": "deepinfra/llama-3-instruct-8b"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "deepinfra/llama-3-1-instruct-70b-c",
          "model_id": "deepinfra/llama-3-1-instruct-70b"
        },
        "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/llama-3-3-instruct-70b-turbo-a",
                        "model_id": "deepinfra/llama-3-3-instruct-70b-turbo"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "deepinfra/llama-3-instruct-8b-b",
                        "model_id": "deepinfra/llama-3-instruct-8b"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "deepinfra/llama-3-1-instruct-70b-c",
                        "model_id": "deepinfra/llama-3-1-instruct-70b"
                    },
                    "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/llama-3-3-instruct-70b-turbo-a",
              model_id: "deepinfra/llama-3-3-instruct-70b-turbo",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "deepinfra/llama-3-instruct-8b-b",
              model_id: "deepinfra/llama-3-instruct-8b",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "deepinfra/llama-3-1-instruct-70b-c",
              model_id: "deepinfra/llama-3-1-instruct-70b",
            },
            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!"}]
}'

Llama 3.3 Instruct 70b Turbo pricing and providers

Access Llama 3.3 Instruct 70b Turbo through DeepInfra via Inworld Router or Realtime API.

					Capabilities	Input modalities	Output modalities
DeepInfra	131.1K	131.1K	$0.10	$0.32

Other Meta models available through Inworld

Compare Llama 3.3 Instruct 70b Turbo with other Meta models available through Inworld Router or Realtime API.

					Capabilities
Llama 3 Instruct 8b	8.2K	8.2K	$0.03	$0.04
Llama 3.1 Instruct 70b	131.1K	131.1K	$0.40	$0.40
Llama 3.1 Instruct 70b Turbo	131.1K	131.1K	$0.40	$0.40
Llama 3.1 Instruct 8b	128K	8.2K	$0.02	$0.05
Llama 3.1 Instruct 8b Turbo	131.1K	131.1K	$0.02	$0.03
Llama 3.2 Instruct 11b Vision	131.1K	131.1K	$0.049	$0.049	—
Llama 3.3 Instruct 70b	128K	32.8K	$0.59	$0.79
Llama 4 Maverick	1M	1M	$0.15	$0.60
Llama 4 Scout	131.1K	8.2K	$0.08	$0.30
Meta Llama/Llama Guard 4 12B	163.8K	163.8K	$0.18	$0.18	—

Start building with Llama 3.3 Instruct 70b Turbo

Access Llama 3.3 Instruct 70b Turbo and every other model through Inworld Router or Realtime API. Create your free account and start routing in minutes.

Get Started Free Contact Sales