jishie

DeepSeek V4 Pro

scnet-token-plan/DeepSeek-V4-Pro · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
free
Cache read $/1M
#72 of 6,384
Cheapest rank
Provider
SCNet Token Plan (scnet-token-plan)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
384,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“DeepSeek V4 Pro” is offered by 57 providers — cheapest-effective first. This one (SCNet Token Plan) is the cheapest.

ProviderInputOutputBlendedContext
SCNet Token Plan (this)freefree$0.001M
Umans AI Coding Planfreefree$0.001M
Alibaba Token Planfreefree$0.001M
Kenarifreefree$0.001M
UnoRouterfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
routing.run$0.348$0.696$0.431M
CrofAI$0.35$0.8$0.461M
EBCloud$0.4286$0.8571$0.541M
Nvidia$0.435$0.87$0.541M
DeepSeek$0.435$0.87$0.541M
Hugging Face$0.435$0.87$0.541M
Auriko$0.435$0.87$0.541M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at SCNet Token Plan and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"DeepSeek-V4-Pro","messages":[{"role":"user","content":"hello"}]}'

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

← all SCNet Token Plan models · model index · JSON