Early access: features, availability, and pricing may change as Kyara Intelligence evolves.

Below baseline Reasoning

DeepSeek: DeepSeek V4 Pro 0813

The GA release of DeepSeek's V4 Pro flagship, tuned for deep, long-running narratives.

Model ID deepseek/deepseek-v4-pro-0813

Quick start

Drop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.

curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro-0813",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

See the full API reference

Overview

The general-availability release of DeepSeek's V4 Pro, built on the same 1.6T-parameter MoE flagship with 49B active parameters. This refresh consolidates the V4 Pro line with steadier reasoning and tighter instruction-following, keeping layered characters, multi-thread plots, and emotionally charged scenes coherent from start to finish. With a 1M-token context window and configurable reasoning depth, it carries sprawling long-horizon storylines without losing its footing.

Specifications

Context / Memory 🌌 Extreme · 1M tokens

Cost vs baseline Below baseline

Input

Output

0.7x

Input

7.8M

cr / M tokens

Output

15.7M

cr / M tokens

Multiples are relative to the catalog median; bars are scaled to the most expensive model.

Model ID

deepseek/deepseek-v4-pro-0813

Reasoning

Available

Status

Current

Upstream moderation

All models on Kyara Intelligence are accessed through their original API providers (Mistral, Z.AI/GLM, xAI, DeepSeek, and others). Each provider's content policies and moderation apply to all requests.

Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. Users are responsible for complying with the relevant provider's terms of service in addition to Kyara's terms.