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

Below baseline Reasoning

DeepSeek: DeepSeek V4 Flash

DeepSeek's latest-generation model, setting a new bar for speed and intelligence in RP.

Model ID deepseek/deepseek-v4-flash

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-flash",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

See the full API reference

Overview

DeepSeek's newest generation model, delivering fast premium intelligence across character-driven roleplay and creative storytelling. Built on a 284B-parameter MoE with 13B activated, Nami 4 pairs exceptional response speed with a massive 1M-token context window so no plot thread, character detail, or scene callback ever slips through the cracks. Hybrid attention keeps long sessions sharp without the drift that plagues smaller context models.

Specifications

Context / Memory 🌌 Extreme · 1M tokens

Cost vs baseline Below baseline

Input

0.2x

Output

0.2x

Input

1.8M

cr / M tokens

Output

3.5M

cr / M tokens

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

Model ID

deepseek/deepseek-v4-flash

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.