Model catalog profile

DeepSeek: DeepSeek V3.1 | pricing profile

Start with DeepSeek: DeepSeek V3.1 input $0.15, output $0.75, context 32,768, and provider DeepSeek, then decide whether this pricing path is worth exploring further.

Provider

DeepSeek

11 models in catalog

Context

32,768

China model route

Input

$0.15

USD / 1M tokens

Output

$0.75

USD / 1M tokens

What this page answers

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

DeepSeek · deepseek/deepseek-chat-v3.1
text->text · China model route
32,768 context · $0.15 input

Before connecting

Do not stop at the model name. Before integration, verify base URL, protocol, visible models, parameters, and limits together.

supports frequency_penalty
supports include_reasoning
supports logit_bias
supports logprobs
supports max_tokens

Next action

After this page, the usual next step is to open the model profile, the provider profile, or run a key check to confirm the real callable range.

Check whether the model fits the use case
Then verify key permission and callable models

Continue

deepseek/deepseek-chat-v3.1