DeepSeek V4 Flash

by deepseek · family deepseek-v4

Facts

Release date	2026-07-31
Retired date	—
Knowledge cutoff	—
Context (max)	1,310,720
Max output	384,000
Modalities	text → text
Aliases	`deepseek-v4-flash-0731`
Open weights	no
Description	Hybrid thinking on by default (V4-Flash-0731); 1M context, 384K max output shared with CoT.

Unknown values are shown as —.

Intelligence Index v4.1.1: 52 · V4 Flash 0731, max · Source: Artificial Analysis (accessed 2026-08-20)

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
Baseten	`deepseek-ai/DeepSeek-V4-Flash-0731`	flash	chat-completions	openai-chat	ga	0.13 / 0.26	effort · default on · returns reasoning_content
DeepSeek	`deepseek-v4-flash`	flash	anthropic	anthropic-messages	ga	0.44 / 1.32	toggle · default on · returns reasoning_content · round-trips reasoning_content
DeepSeek	`deepseek-v4-flash`	flash	chat-completions	openai-chat	ga	0.44 / 1.32	effort · default on · returns reasoning_content · round-trips reasoning_content
IO Intelligence (io.net)	`deepseek-ai/DeepSeek-V4-Flash`	flash	chat	openai-chat	ga	0.20 / 0.52	effort · default on · returns reasoning_content
NEAR AI Cloud	`deepseek-ai/DeepSeek-V4-Flash`	flash	chat	openai-chat	ga	0.17 / 0.35	toggle · default on · returns reasoning_content
Ollama Cloud	`deepseek-v4-flash:0731`	flash	v1-chat-completions	openai-chat	ga	—	effort · default on · returns hidden
OpenCode Go	`deepseek-v4-flash`	flash	go-chat-completions	openai-chat	ga	—	effort · default on · returns reasoning_content · round-trips reasoning_content
OpenCode Zen	`deepseek-v4-flash`	flash	chat-completions	openai-chat	ga	0.44 / 1.32	effort · default on · returns reasoning_content · round-trips reasoning_content
OpenRouter	`deepseek/deepseek-v4-flash-0731`	flash	chat-completions	openai-chat	ga	0.05 / 0.10	effort · default on · returns reasoning_content · round-trips reasoning_content
OpenRouter	`deepseek/deepseek-v4-flash`	flash	chat-completions	openai-chat	ga	0.08 / 0.16	effort · default on · returns reasoning_content · round-trips reasoning_content

Reasoning controls

Baseten· deepseek-ai/DeepSeek-V4-Flash-0731· chat-completions effort

reasoning_effort noneminimallowmediumhigh●xhighmax Default not documented — verify.

effort · default on · returns reasoning_content

DeepSeek· deepseek-v4-flash· anthropic toggle

thinking.type on enabled · off disabled

toggle · default on · returns reasoning_content · round-trips reasoning_content

DeepSeek· deepseek-v4-flash· chat-completions effort

reasoning_effort lowhigh●max

thinking.type on enabled · off disabled

effort · default on · returns reasoning_content · round-trips reasoning_content

IO Intelligence (io.net)· deepseek-ai/DeepSeek-V4-Flash· chat effort

reasoning.effort nonelowmediumhigh● Default not documented — verify.

effort · default on · returns reasoning_content

NEAR AI Cloud· deepseek-ai/DeepSeek-V4-Flash· chat toggle

thinking.type on enabled · off disabled

toggle · default on · returns reasoning_content

Ollama Cloud· deepseek-v4-flash:0731· v1-chat-completions effort

reasoning_effort nonelowmediumhigh●max Default level not documented; verify.

effort · default on · returns hidden

OpenCode Go· deepseek-v4-flash· go-chat-completions effort

reasoning_effort lowhigh●max

thinking.type on enabled · off disabled

effort · default on · returns reasoning_content · round-trips reasoning_content

OpenCode Zen· deepseek-v4-flash· chat-completions effort

reasoning_effort lowhigh●max

thinking.type on enabled · off disabled

effort · default on · returns reasoning_content · round-trips reasoning_content

OpenRouter· deepseek/deepseek-v4-flash-0731· chat-completions effort

reasoning.effort nonelowmedium●highxhighmax

effort · default on · returns reasoning_content · round-trips reasoning_content

OpenRouter· deepseek/deepseek-v4-flash· chat-completions effort

reasoning.effort nonelowmedium●highxhighmax

effort · default on · returns reasoning_content · round-trips reasoning_content

Example requests

Baseten · openai-chat · deepseek-ai/DeepSeek-V4-Flash-0731

curl 'https://inference.baseten.co/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://inference.baseten.co/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://inference.baseten.co/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

DeepSeek · anthropic-messages · deepseek-v4-flash

curl 'https://api.deepseek.com/anthropic' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-v4-flash",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "thinking": {
    "type": "enabled"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.deepseek.com/anthropic",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-v4-flash",
      "max_tokens": 1024,
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "thinking": {
        "type": "enabled"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.deepseek.com/anthropic", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-v4-flash",
    "max_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "thinking": {
      "type": "enabled"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

DeepSeek · openai-chat · deepseek-v4-flash

curl 'https://api.deepseek.com/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.deepseek.com/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-v4-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.deepseek.com/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

IO Intelligence (io.net) · openai-chat · deepseek-ai/DeepSeek-V4-Flash

curl 'https://api.intelligence.io.solutions/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-ai/DeepSeek-V4-Flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://api.intelligence.io.solutions/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-ai/DeepSeek-V4-Flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://api.intelligence.io.solutions/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-ai/DeepSeek-V4-Flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

NEAR AI Cloud · openai-chat · deepseek-ai/DeepSeek-V4-Flash

curl 'https://cloud-api.near.ai/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-ai/DeepSeek-V4-Flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "thinking": {
    "type": "enabled"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://cloud-api.near.ai/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-ai/DeepSeek-V4-Flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "thinking": {
        "type": "enabled"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://cloud-api.near.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-ai/DeepSeek-V4-Flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "thinking": {
      "type": "enabled"
    }
  }),
})
console.log(await resp.json())

Ollama Cloud · openai-chat · deepseek-v4-flash:0731

curl 'https://ollama.com/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-v4-flash:0731",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://ollama.com/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-v4-flash:0731",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://ollama.com/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-v4-flash:0731",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

OpenCode Go · openai-chat · deepseek-v4-flash

curl 'https://opencode.ai/zen/go/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/go/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-v4-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/go/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenCode Zen · openai-chat · deepseek-v4-flash

curl 'https://opencode.ai/zen/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek-v4-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenRouter · openai-chat · deepseek/deepseek-v4-flash-0731

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-v4-flash-0731",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek/deepseek-v4-flash-0731",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-v4-flash-0731",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenRouter · openai-chat · deepseek/deepseek-v4-flash

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "deepseek/deepseek-v4-flash",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).