jishie

DeepSeek V4 Pro 0813

kilo/deepseek/deepseek-v4-pro-0813 · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtext.

$0.54Blended $/1M (3:1)
$0.435Input $/1M
$0.87Output $/1M
$1.301M in + 1M out
$0.003625 −99%Cache read $/1M
#2350 of 5,828Cheapest rank
Provider
Kilo Gateway (kilo)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
384,000 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“DeepSeek V4 Pro 0813” is offered by 4 providers — cheapest-effective first. This one (Kilo Gateway) is the cheapest.

ProviderInputOutputBlendedContext
Kilo Gateway (this)$0.435$0.87$0.541049k
NanoGPT$0.435$0.87$0.541049k
Vercel AI Gateway$0.435$0.87$0.541000k
OpenRouter$0.435$0.87$0.541049k

Call it

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

Most providers are OpenAI-compatible — point base_url at Kilo Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4-pro-0813","messages":[{"role":"user","content":"hello"}]}'

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