jishie

DeepSeek-R1

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

freeBlended $/1M (3:1)
freeInput $/1M
freeOutput $/1M
free1M in + 1M out
Cache read $/1M
#290 of 5,000Cheapest rank
Provider
iFlow (iflowcn)
Context
128,000 tokens
Max output
32,000 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“DeepSeek-R1” is offered by 9 providers — cheapest-effective first. This one (iFlow) is the cheapest.

ProviderInputOutputBlendedContext
iFlow (this)freefree$0.00128k
Kilo Gateway$0.7$2.5$1.1564k
OpenRouter$0.7$2.5$1.15164k
Hugging Face$0.7$2.5$1.1564k
Azure Cognitive Services$1.35$5.4$2.36164k
Azure$1.35$5.4$2.36164k
Amazon Bedrock$1.35$5.4$2.36128k
Vercel AI Gateway$1.35$5.4$2.36128k
Together AI$3$7$4.00164k

Call it

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

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

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