DeepSeek

Models/deepseek V4 PRO 0813

Name: Models/deepseek V4 PRO 0813
Brand: DeepSeek
Price: 1.32 USD
Availability: InStock

Models/deepseek V4 PRO 0813 is a reasoning model by DeepSeek with function calling — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 1M token context window with up to 131K tokens of output. Priced at $1.32 per million input tokens and $3.96 per million output tokens. Access Models/deepseek V4 PRO 0813 through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

→Function CallingReasoningreasoningCapabilityresponseFormatCapability

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": "inworld/models/deepseek-v4-pro-0813-a",
          "model_id": "inworld/models/deepseek-v4-pro-0813"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "deepinfra/deepseek-ai/DeepSeek-V3.2-b",
          "model_id": "deepinfra/deepseek-ai/DeepSeek-V3.2"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "deepinfra/deepseek-ai/DeepSeek-V4-Flash-c",
          "model_id": "deepinfra/deepseek-ai/DeepSeek-V4-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": "inworld/models/deepseek-v4-pro-0813-a",
                        "model_id": "inworld/models/deepseek-v4-pro-0813"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "deepinfra/deepseek-ai/DeepSeek-V3.2-b",
                        "model_id": "deepinfra/deepseek-ai/DeepSeek-V3.2"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "deepinfra/deepseek-ai/DeepSeek-V4-Flash-c",
                        "model_id": "deepinfra/deepseek-ai/DeepSeek-V4-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: "inworld/models/deepseek-v4-pro-0813-a",
              model_id: "inworld/models/deepseek-v4-pro-0813",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "deepinfra/deepseek-ai/DeepSeek-V3.2-b",
              model_id: "deepinfra/deepseek-ai/DeepSeek-V3.2",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "deepinfra/deepseek-ai/DeepSeek-V4-Flash-c",
              model_id: "deepinfra/deepseek-ai/DeepSeek-V4-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!"}]
}'

Models/deepseek V4 PRO 0813 pricing and providers

Access Models/deepseek V4 PRO 0813 through Inworld 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
Inworld	1M	131.1K	$1.32	$3.96	+1

Other DeepSeek models available through Inworld

Compare Models/deepseek V4 PRO 0813 with other DeepSeek models available through Inworld Router or Realtime API.

					Capabilities
Deepseek Ai/DeepSeek V3.2	163.8K	—	$0.26	$0.38	+2
Deepseek Ai/DeepSeek V4 Flash	1M	131.1K	$0.09	$0.18	+2
Deepseek Ai/DeepSeek V4 PRO	1M	131.1K	$1.30	$2.60	+2
Deepseek V4 Flash	1M	—	$0.149	$0.297	+1
Deepseek V4 PRO	1M	—	$0.462	$0.923	+1
Models/deepseek V3.2	163.8K	—	$0.26	$0.38
Models/deepseek V4 Flash	1M	131.1K	$0.10	$0.20	+2
Models/deepseek V4 PRO	1M	131.1K	$1.15	$2.415	+1

Start building with Models/deepseek V4 PRO 0813

Access Models/deepseek V4 PRO 0813 and every other model through Inworld Router or Realtime API. Create your free account and start routing in minutes.

Get Started Free Contact Sales

Products

Solutions