DeepSeek V4 Flash is a state-of-the-art large language model combining efficient sparse attention, strong reasoning, and integrated agent capabilities for robust long-context understanding and versatile AI applications.
A list of messages comprising the conversation so far.
rolestringrequired
The role of the message author. One of "system", "user", or "assistant".
systemuserassistant
contentstringrequired
The content of the message.
temperaturenumber
Controls the variety of the model's responses. Lower values make output more predictable and deterministic, higher values more diverse and random.
Default: 1Min: 0Max: 2
top_pnumber
Nucleus sampling: limits the model's choices to the smallest set of tokens whose cumulative probability reaches top_p. It is recommended to adjust either this or temperature, not both.
Default: 1Min: 0Max: 1
top_kinteger
Limits the model's choice to the k most likely tokens at each step. Set to 0 or omit to disable.
Default: 0Min: 0
min_pnumber
Minimum probability threshold for a token to be considered, measured relative to the probability of the most likely token. Tokens below this threshold are filtered out.
Default: 0Min: 0Max: 1
frequency_penaltynumber
Penalizes tokens based on how frequently they have appeared in the text so far, reducing verbatim repetition. Negative values encourage token reuse.
Default: 0Min: -2Max: 2
presence_penaltynumber
Penalizes tokens that have already appeared in the text regardless of frequency, encouraging the model to introduce new topics.
Default: 0Min: -2Max: 2
repetition_penaltynumber
Multiplicative penalty applied to previously generated tokens. Values greater than 1 discourage repetition; 1 disables it.
Default: 1Min: 0Max: 2
stopstring | array[string]
One or more sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
seedinteger
Random seed for deterministic sampling. Repeated requests with the same seed and parameters should return the same result.
max_tokensinteger
The maximum number of tokens to generate in the completion. The maximum value is the model's context length minus the prompt length.
Min: 1
logit_biasobject
A map of token IDs to bias values from -100 to 100 that adjust the likelihood of those tokens appearing in the output.
streamboolean
If set to true, partial message deltas will be sent as server-sent events.
Unix timestamp of when the completion was created.
modelstringrequired
The model used for the completion.
choicesarray[object]required
List of completion choices.
indexintegerrequired
Index of the choice.
messageobjectrequired
The generated message.
finish_reasonstringrequired
The reason generation stopped.
stoplengthcontent_filter
usageobjectrequired
Token usage statistics.
prompt_tokensintegerrequired
Number of tokens in the prompt.
completion_tokensintegerrequired
Number of tokens in the completion.
total_tokensintegerrequired
Total tokens used.
مثال على الاستجابة
json
{"id":"chatcmpl-abc123","object":"chat.completion","created":1700000000,"model":"model-name","choices":[{"index":0,"message":{"role":"assistant","content":"Hello! How can I assist you today?"},"finish_reason":"stop"}],"usage":{"prompt_tokens":10,"completion_tokens":20,"total_tokens":30}}
Atlas Cloud Skills
يدمج Atlas Cloud Skills أكثر من 400 نموذج ذكاء اصطناعي مباشرة في مساعد البرمجة بالذكاء الاصطناعي الخاص بك. أمر واحد للتثبيت، ثم استخدم اللغة الطبيعية لتوليد الصور ومقاطع الفيديو والدردشة مع LLM.
العملاء المدعومون
Claude Code
OpenAI Codex
Gemini CLI
Cursor
Windsurf
VS Code
Trae
GitHub Copilot
Cline
Roo Code
Amp
Goose
Replit
40+ العملاء المدعومون
التثبيت
bash
npx skills add AtlasCloudAI/atlas-cloud-skills
إعداد مفتاح API
احصل على مفتاح API الخاص بك من لوحة تحكم Atlas Cloud وعيّنه كمتغير بيئة.
bash
exportATLASCLOUD_API_KEY="your-api-key-here"
الإمكانيات
بمجرد التثبيت، يمكنك استخدام اللغة الطبيعية في مساعد الذكاء الاصطناعي الخاص بك للوصول إلى جميع نماذج Atlas Cloud.
توليد الصورأنشئ صورًا باستخدام نماذج مثل Nano Banana 2 و Z-Image والمزيد.
إنشاء الفيديوأنشئ مقاطع فيديو من نص أو صور باستخدام Kling و Vidu و Veo وغيرها.
دردشة LLMتحدث مع Qwen و DeepSeek ونماذج اللغة الكبيرة الأخرى.
رفع الوسائطارفع الملفات المحلية لتحرير الصور وسير عمل تحويل الصور إلى فيديو.