DeepSeek R1

drun/public/deepseek-r1 · family deepseek-thinking · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.96Blended $/1M (3:1)

$0.55Input $/1M

$2.2Output $/1M

$2.751M in + 1M out

—Cache read $/1M

#3101 of 5,000Cheapest rank

Provider: D.Run (China) (drun)
Context: 131,072 tokens
Max output: 32,000 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“DeepSeek R1” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $0.73 blended.

Provider	Input	Output	Blended	Context
NanoGPT	$0.4	$1.7	$0.73	128k
D.Run (China) (this)	$0.55	$2.2	$0.96	131k
Alibaba (China)	$0.574	$2.294	$1.00	131k
Merge Gateway	$1.35	$5.4	$2.36	164k
IO.NET	$2	$8.75	$3.69	128k
Abacus	$3	$7	$4.00	128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at D.Run (China) and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"public/deepseek-r1","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):