Inworld has acquired Ultravox to accelerate its speech-to-speech research and voice agent capabilities.Read the announcement

Inworld has acquired UltravoxRead announcement →

Get started

Alibaba

Qwen2.5 72B Instruct

Name: Qwen2.5 72B Instruct
Brand: Alibaba
Price: 0.36 USD
Availability: InStock

Qwen2.5 72B Instruct is a large language model by Alibaba with support for function calling and structured output. It supports a 33K token context window with up to 33K tokens of output. Priced at $0.36 per million input tokens and $0.4 per million output tokens, it is one of the most cost-efficient options in its class. Access Qwen2.5 72B Instruct through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

→Function CallingResponse SchemaresponseFormatCapability

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/Qwen/Qwen2.5-72B-Instruct-a",
          "model_id": "deepinfra/Qwen/Qwen2.5-72B-Instruct"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "inworld/models/qwen3.8-27b-b",
          "model_id": "inworld/models/qwen3.8-27b"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "inworld/models/qwen3.8-flash-c",
          "model_id": "inworld/models/qwen3.8-flash"
        },
        "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/Qwen/Qwen2.5-72B-Instruct-a",
                        "model_id": "deepinfra/Qwen/Qwen2.5-72B-Instruct"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "inworld/models/qwen3.8-27b-b",
                        "model_id": "inworld/models/qwen3.8-27b"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "inworld/models/qwen3.8-flash-c",
                        "model_id": "inworld/models/qwen3.8-flash"
                    },
                    "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/Qwen/Qwen2.5-72B-Instruct-a",
              model_id: "deepinfra/Qwen/Qwen2.5-72B-Instruct",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "inworld/models/qwen3.8-27b-b",
              model_id: "inworld/models/qwen3.8-27b",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "inworld/models/qwen3.8-flash-c",
              model_id: "inworld/models/qwen3.8-flash",
            },
            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!"}]
}'

Qwen2.5 72B Instruct pricing and providers

Access Qwen2.5 72B Instruct 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	$0.36	$0.40	—	—	32.8K	32.8K

Prices in USD per 1M tokens.

Other Alibaba models available through Inworld

Compare Qwen2.5 72B Instruct with other Alibaba models available through Inworld Router or Realtime API.

							Capabilities
Qwen3.8 27b	$0.40	$3.00	$0.04	—	262.1K	131.1K	+2
Qwen3.8 Flash	$0.16	$0.47	$0.016	—	1M	131.1K	+2
Qwen3guard Gen 0 6b Int8	$0.003	$0.222	$0.003	—	4.1K	—	—
Qwen3 235B A22B Instruct 2507	$0.09	$0.55	—	—	262.1K	262.1K
Qwen3.8 2.4T A95B	$2.00	$6.00	$0.20	—	262.1K	131.1K	+2
Qwen3 VL 30B A3B Instruct	$0.15	$0.60	—	—	262.1K	—	+1