DeepSeek

Deepseek V4 Flash

Name: Deepseek V4 Flash
Brand: DeepSeek
Price: 0.149 USD
Availability: InStock

Deepseek V4 Flash is a reasoning model by DeepSeek with function calling — designed for complex, multi-step problem solving where accuracy matters more than speed. It features an extended 1M token context window, suitable for processing long documents and complex conversations. Priced at $0.149 per million input tokens and $0.297 per million output tokens, it is one of the most cost-efficient options in its class. Access Deepseek V4 Flash 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": "deepseek/deepseek-v4-flash-a",
          "model_id": "deepseek/deepseek-v4-flash"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528-b",
          "model_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "deepinfra/deepseek-ai/DeepSeek-V3-c",
          "model_id": "deepinfra/deepseek-ai/DeepSeek-V3"
        },
        "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": "deepseek/deepseek-v4-flash-a",
                        "model_id": "deepseek/deepseek-v4-flash"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528-b",
                        "model_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "deepinfra/deepseek-ai/DeepSeek-V3-c",
                        "model_id": "deepinfra/deepseek-ai/DeepSeek-V3"
                    },
                    "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: "deepseek/deepseek-v4-flash-a",
              model_id: "deepseek/deepseek-v4-flash",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "deepinfra/deepseek-ai/DeepSeek-R1-0528-b",
              model_id: "deepinfra/deepseek-ai/DeepSeek-R1-0528",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "deepinfra/deepseek-ai/DeepSeek-V3-c",
              model_id: "deepinfra/deepseek-ai/DeepSeek-V3",
            },
            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!"}]
}'

Deepseek V4 Flash pricing and providers

Access Deepseek V4 Flash through deepseek 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
deepseek	1M	—	$0.149	$0.297	+1

Other DeepSeek models available through Inworld

Compare Deepseek V4 Flash with other DeepSeek models available through Inworld Router or Realtime API.

					Capabilities
Deepseek Ai/DeepSeek R1 0528	163.8K	163.8K	$0.50	$2.15	+2
Deepseek Ai/DeepSeek V3	163.8K	163.8K	$0.32	$0.89
Deepseek Ai/DeepSeek V3 0324	163.8K	163.8K	$0.20	$0.77
Deepseek Ai/DeepSeek V3.1 Terminus	163.8K	163.8K	$0.27	$0.95	+2
Deepseek Ai/DeepSeek V3.2	163.8K	—	$0.26	$0.38	+2
Deepseek Ai/DeepSeek V4 Flash	1M	—	$0.10	$0.20	+2
Deepseek Ai/DeepSeek V4 PRO	1M	—	$1.30	$2.60	+2
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	—
Models/deepseek V4 PRO	1M	131.1K	$1.15	$2.415	+1

Start building with Deepseek V4 Flash

Access Deepseek V4 Flash and every other model through Inworld Router or Realtime API. Create your free account and start routing in minutes.

Get Started Free Contact Sales