jishie

DeepSeek V4 Flash

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

$0.66
Blended $/1M (3:1)
$0.44
Input $/1M
$1.32
Output $/1M
$1.76
1M in + 1M out
$0.014 −97%
Cache read $/1M
#2737 of 6,373
Cheapest rank
Provider
Requesty (requesty)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
384,000 tokens
Capabilities
tools text

Same model, other providers

“DeepSeek V4 Flash” is offered by 54 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
SCNet Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
LLM Gateway$0.05$0.09$0.061.1M
DigitalOcean$0.0679$0.168$0.091M
OpenRouter$0.0826$0.1652$0.101M
Deep Infra$0.09$0.18$0.111M
Modelis$0.0983$0.1966$0.121M
Pioneer$0.1$0.2$0.131M
Requesty (this)$0.44$1.32$0.661M

Call it

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

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