DeepSeek R1

DeepSeek · 160K token context · text

Pricing: $0.56 per 1M input tokens, $2.22 per 1M output tokens

DeepSeek R1 - reasoning model with chain-of-thought. Excels at math, code, and complex logic.

Pricing

$0.56 per 1M input tokens and $2.22 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

Prices checked 2026-11-04

Context and limits

The context window is 160,000 tokens (160K).

The maximum output is 32,768 tokens.

When to use DeepSeek R1

DeepSeek R1 (model ID `deepseek-r1`) takes text input and returns text output.

Supported features in the catalog: streamed responses over SSE, JSON-schema structured output.

Use DeepSeek R1 for text generation and chat.

FAQ

How much does DeepSeek R1 cost?

$0.56 per 1M input tokens and $2.22 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

What is the context window and output limit of DeepSeek R1?

The context window is 160,000 tokens (160K). The maximum output is 32,768 tokens.

How do I get access to DeepSeek R1?

Create an API key in the llmka.dev dashboard and send requests to model "deepseek-r1" at https://api.llmka.dev/v1. The endpoint is OpenAI-compatible. One key and one balance cover all models on the gateway.

Links

All models and prices · API documentation · Quick start

Available through the llmka.dev gateway: OpenAI- and Anthropic-compatible endpoints, one key, USDT top-up.