anoman

DeepSeek

V3.1

modeldeepseek-chat-v3-1
BudgetStableStreamingToolsBatchLong contextGlobal

Context

164K

Input / 1M tokens

Rp 4.620

Output / 1M tokens

Rp 17.556

Cached input / 1M tokens

Rp 2.736

Cache write / 1M tokens

โ€” (bills at input price)

About this model

V3.1

V3.1 is a model by DeepSeek, available through the Anoman AI OpenAI-compatible API with a 164K-token context window. It costs Rp 4.620 per 1M input tokens and Rp 17.556 per 1M output tokens, and is available from the Pro plan.

Key facts

Maker
DeepSeek
Context window
164K tokens
Max output
147K tokens
Lane
Guarded: the provider has confirmed it does not train on your data
Modality
Text
Input price
Rp 4.620 per 1M tokens
Output price
Rp 17.556 per 1M tokens
Processing region(s)
global
Route
Via OpenRouter
Precision
Never routed to providers that report below FP8; some providers do not report precision
Cheapest plan
Available from the Pro plan
Price comparison
Priced below 186 of 248 pro-band guarded models on Anoman (blended price: 1 part input to 3 parts output).

More models by DeepSeek

Code example

Chat completion with V3.1

from openai import OpenAI

client = OpenAI(
    base_url="https://api.anoman.io/v1",
    api_key="anm-sk-..."
)

response = client.chat.completions.create(
    model="deepseek-chat-v3-1",
    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 V3.1 in the Anoman catalog.

Use V3.1 through Anoman.