jishie

DeepSeek V4 Pro 0813

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

$1.98
Blended $/1M (3:1)
$1.32
Input $/1M
$3.96
Output $/1M
$5.28
1M in + 1M out
$0.044 −97%
Cache read $/1M
#4156 of 6,156
Cheapest rank
Provider
DigitalOcean (digitalocean)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
1,048,576 tokens
Capabilities
tools reasoning text

Same model, other providers

“DeepSeek V4 Pro 0813” is offered by 18 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
OpenRouter$0.435$0.87$0.541M
Merge Gateway$0.435$0.87$0.541M
Ofox$0.45$0.88$0.561M
NanoGPT$1.1$2.5$1.451M
Deep Infra$1.3$2.6$1.631M
DigitalOcean (this)$1.32$3.96$1.981M
Baseten$1.32$3.96$1.981M
Cloudflare Workers AI$1.32$3.96$1.981M
Hugging Face$1.32$3.96$1.981M
EmpirioLabs AI$1.32$3.96$1.981M
Vercel AI Gateway$1.32$3.96$1.981M

Call it

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

Most providers are OpenAI-compatible — point base_url at DigitalOcean 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-0813","messages":[{"role":"user","content":"hello"}]}'

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

← all DigitalOcean models · model index · JSON