jishie

DeepSeek V4 Pro

arcee/deepseek/deepseek-v4-pro · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$2.17
Blended $/1M (3:1)
$1.74
Input $/1M
$3.48
Output $/1M
$5.22
1M in + 1M out
$0.2 −89%
Cache read $/1M
#6448 of 9,407
Cheapest rank
Provider
Arcee (arcee)
Kind
text (outputs text)
Context
512,000 tokens
Max output
384,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“DeepSeek V4 Pro” is offered by 69 providers — cheapest-effective first. Alibaba Token Plan (China) is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Plan (China)freefree$0.001M
SenseNova (China)freefree$0.001M
Volcengine Ark Coding Planfreefree$0.001M
SCNet Token Planfreefree$0.001M
Alibaba Token Planfreefree$0.001M
UnoRouterfreefree$0.001M
routing.run$0.348$0.696$0.431M
EBCloud$0.4286$0.8571$0.541M
Hugging Face$0.435$0.87$0.541M
TokenGo$0.435$0.87$0.541M
Modelis$0.435$0.87$0.541M
APIKO$0.405$1.21$0.611M
Arcee (this)$1.74$3.48$2.17512k

Call it

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

Most providers are OpenAI-compatible — point base_url at Arcee 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","messages":[{"role":"user","content":"hello"}]}'

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

← all Arcee models · model index · JSON