DeepSeek
V4 Flash
model
deepseek-v4-flash-globalBudgetStableโ
Low cost in tierStreamingToolsBatchLong contextGlobal
Context
1.0M
Input / 1M tokens
Rp 1.786
Output / 1M tokens
Rp 3.558
Cached input / 1M tokens
Rp 577
Cache write / 1M tokens
โ (bills at input price)
About this model
V4 Flash
V4 Flash is a model by DeepSeek, available through the Anoman AI OpenAI-compatible API with a 1.0M-token context window. It costs Rp 1.786 per 1M input tokens and Rp 3.558 per 1M output tokens. Usable on: Free (from credit or balance), Budget Pass, Plus Pass, Pro, Enterprise.
Key facts
- Maker
- DeepSeek
- Context window
- 1.0M tokens
- Max output
- 393K tokens
- Lane
- Guarded: the provider has confirmed it does not train on your data
- Modality
- Text
- Input price
- Rp 1.786 per 1M tokens
- Output price
- Rp 3.558 per 1M tokens
- Processing region(s)
- global
- Precision
- Never routed to providers that report below FP8; some providers do not report precision
- Usable on
- Free (from credit or balance), Budget Pass, Plus Pass, Pro, Enterprise
Code example
Chat completion with V4 Flash
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="deepseek-v4-flash-global",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Alternatives
Similar models in our catalog
Same maker first, then the closest price to V4 Flash in the Anoman catalog.