jishie

DeepSeek V4 Pro 0813

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

$1.74
Blended $/1M (3:1)
$1.16
Input $/1M
$3.48
Output $/1M
$4.64
1M in + 1M out
$0.1159 −90%
Cache read $/1M
#4790 of 7,326
Cheapest rank
Provider
Melious (melious)
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 0813” is offered by 32 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
Nvidiafreefree$0.001M
SCNet Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
OrcaRouter$0.442$0.884$0.551M
OpenRouter$0.5795$1.74$0.871M
RunInfra$0.6$1.9$0.921M
Vercel AI Gateway$0.66$1.98$0.991M
Merge Gateway$0.66$1.98$0.991M
AIHubMix$0.6918$2.08$1.041M
NanoGPT$1.1$2.5$1.451M
Deep Infra$1.3$2.6$1.631M
Melious (this)$1.16$3.48$1.741M

Call it

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

Most providers are OpenAI-compatible — point base_url at Melious 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 Melious models · model index · JSON