jishie

DeepSeek V4 Flash

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

$0.36
Blended $/1M (3:1)
$0.242
Input $/1M
$0.726
Output $/1M
$0.97
1M in + 1M out
$0.0077 −97%
Cache read $/1M
#2150 of 7,012
Cheapest rank
Provider
above.dev (above)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
384,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“DeepSeek V4 Flash” is offered by 58 providers — cheapest-effective first. Umans AI Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Umans AI Coding Planfreefree$0.001M
Alibaba Token Planfreefree$0.001M
Kenarifreefree$0.001M
UnoRouterfreefree$0.001M
Volcengine Ark Coding Planfreefree$0.001M
Pendrafreefree$0.001M
SCNet Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
DevPass (LLM Gateway)$0.051$0.104$0.061.1M
DigitalOcean$0.0679$0.168$0.091M
OpenRouter$0.0806$0.1613$0.101M
Deep Infra$0.09$0.18$0.111M
above.dev (this)$0.242$0.726$0.361M

Call it

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

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

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

← all above.dev models · model index · JSON