Skip to main content
kRouter
All models

DeepSeek R1

DeepSeek R1 is served by 3 providers that kRouter can route to, with a 128K-token context window and pricing from $0.14 per 1M input tokens. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.

Where to get DeepSeek R1

ProviderRoute as
Together AItogether/deepseek-ai/DeepSeek-R1
SiliconFlowsiliconflow/deepseek-ai/DeepSeek-R1
Hyperbolichyperbolic/deepseek-ai/DeepSeek-R1

What DeepSeek R1 is suited for

At 128K the window is modest, so it is better suited to focused edits than to long agent runs that accumulate history. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop. Cached input is billed at $0.00 against $0.14 fresh, which is the difference that matters most for agent work — the same context is resent on every turn.

Specs

Context window
128K
Max output
64K
Input / 1M
$0.14
Output / 1M
$0.28

DeepSeek R1 FAQ

How much does DeepSeek R1 cost?

DeepSeek R1 is $0.14 per 1M input tokens and $0.28 per 1M output tokens. Cached input is $0.00, which matters a lot for agent work that resends the same context each turn.

Which providers serve DeepSeek R1?

3 providers: Together AI, SiliconFlow, Hyperbolic. Through kRouter you can switch between them by changing the route prefix, without changing your tool.

What is DeepSeek R1's context window?

128K tokens, with up to 64K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.

Route to DeepSeek R1 from any tool

kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.

Install kRouter