DeepSeek R1 - Kyma API

Overview

DeepSeek R1 is a frontier reasoning model from DeepSeek that processes text inputs and returns text outputs. It is designed for tasks that require deep logical deduction, mathematical problem solving, and tool use, with native support for structured outputs. On Kyma, the model runs behind automatic failover routing and returns exact request costs in the usage.cost field. It operates with a 64,000-token context window and a maximum output length of 32,768 tokens. The reasoning alias resolves directly to this model. This model does not support vision, prompt caching, or multimodal inputs. Because it runs on a slow speed tier, it is not suitable for latency-sensitive applications. Input and output tokens are billed per-token at the platform’s listed rates.

Specs

Field	Value
Model ID	`deepseek-r1`
Best for	Math, logic, complex reasoning
Context window	64,000
Max output tokens	33K
Input modalities	Text
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	No
Speed	Slow
Cost band	Balanced
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.74
Output	$2.96

Use this when

Math & Logic Problems — Solve complex mathematical and logical reasoning tasks with explicit step-by-step traces.
Document Analysis — Extract structured insights and perform deep textual analysis across long documents.
Tool-Enabled Workflows — Drive multi-step agent tasks that require explicit reasoning and function calling.

Not ideal for

Avoid this model for real-time conversational interfaces, vision-based tasks, or applications that require prompt caching and low-latency responses.

Pick something else when

You need sub-second latency for chat: use qwen-3.7-plus or gemini-3-flash.
You require vision or multimodal inputs: use qwen-3.7-max or gemini-3.5-flash.
You need prompt caching for repeated prefixes: use qwen-3.6-plus or llama-3.3-70b.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="deepseek-r1",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=frontier-open"

FAQ

Does this model support image inputs? No, it is strictly a text-only model and does not support vision or multimodal processing. How fast does it generate text on Kyma? It runs in the slow speed tier, well behind standard chat models — that is the cost of generating an explicit reasoning trace before the answer. Can I use prompt caching with this model? No, the model does not support prompt caching. Repeated prompt prefixes will be billed at the standard input rate.

Alias	Resolves to
`reasoning`	`deepseek-r1`

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ

​Related aliases