DeepSeek V4

Chat completions on DeepSeek V4 through one OpenAI-compatible endpoint: Flash for everyday work, Pro for hard reasoning.

POST/v3/llm/deepseek-v4/chat/completionsTry it

• Price0.01 / 0.02 ICper 1k tokens, in / out
• Served19Kcalls

• v4
• Active

Sign in to run this demo.

50 credits free on sign-up. No card.

Create a free accountLog in

Request

curl -X POST 'https://api.iapp.co.th/v3/llm/deepseek-v4/chat/completions' \
  -H 'apikey: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{ \
    "model": "deepseek-v4-flash", \
    "messages": [ \
      {"role": "user", "content": "สวัสดีครับ คุณช่วยอะไรได้บ้าง?"} \
    ], \
    "max_tokens": 4096, \
    "temperature": 0.7, \
    "top_p": 0.9 \
  }'

Response

401No API key in the request, or the key is not valid.

The body is the gateway's own and is not reproduced here.

Request

JSON, in the OpenAI chat-completions shape, so an OpenAI client works with the base URL changed.

Headers

apikeystringrequired

Your API key, created under API Keys in the control panel.

Body

modelstringrequired

deepseek-v4-flash or deepseek-v4-pro. Any other value returns 400, so a typo cannot bill you the dearer tier.

messagesarrayrequired

The conversation: objects with role, one of system, user, assistant, and content.

max_tokensinteger

The most tokens to generate. Default 4096.

streamboolean

true for server-sent events, a token at a time. Default false.

temperaturefloat

0 to 2, default 0.7. Near 0 for code and maths, 1.0 for analysis, 1.3 for conversation and translation, 1.5 for creative writing.

top_pfloat

Nucleus sampling, default 0.9.

Price

Model	For	Input	Output
deepseek-v4-flash	Chat, questions over documents, classification, drafting	0.01 IC per 1K tokens	0.02 IC per 1K tokens
deepseek-v4-pro	Hard reasoning, multi-step agents, olympiad-level maths and code	0.20 IC per 1K tokens	0.40 IC per 1K tokens

Use Flash by default: Pro costs twenty times as much per token, so send it only the requests that need the deeper reasoning.

Response

The OpenAI chat-completion object, as in the panel: the answer is choices[0].message.content and usage holds the billed token counts. With stream: true the same arrives as data: lines, each a chunk with choices[0].delta, ending in data: [DONE].

The OpenAI chat-completion object, as in the panel: the answer is choices[0].message.content and usage holds the billed token counts. With stream: true the same arrives as data: lines, each a chunk with choices[0].delta, ending in data: [DONE].

Details

Measured

Limits

• 5 requests per second and 200 per minute per key.