jishie

DeepSeek V4 Flash 0731

hetzner/DeepSeek-V4-Flash-0731 · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtext.

freeBlended $/1M (3:1)
freeInput $/1M
freeOutput $/1M
free1M in + 1M out
freeCache read $/1M
#302 of 5,810Cheapest rank
Provider
Hetzner (hetzner)
Kind
text (outputs text)
Context
512,000 tokens
Max output
384,000 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“DeepSeek V4 Flash 0731” is offered by 25 providers — cheapest-effective first. This one (Hetzner) is the cheapest.

ProviderInputOutputBlendedContext
Hetzner (this)freefree$0.00512k
Alibaba Token Planfreefree$0.001000k
Alibaba Token Plan (China)freefree$0.001000k
OpenRouter$0.08$0.18$0.101049k
Deep Infra$0.08$0.18$0.101049k
DigitalOcean$0.08$0.252$0.121049k
Baseten$0.13$0.26$0.161049k
Weights & Biases$0.13$0.28$0.17262k
Cortecs$0.13$0.28$0.171049k
Fireworks AI$0.14$0.28$0.181000k
NanoGPT$0.14$0.28$0.181000k
Ambient$0.14$0.28$0.181049k
EmpirioLabs AI$0.14$0.28$0.181000k

Call it

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

Most providers are OpenAI-compatible — point base_url at Hetzner 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-0731","messages":[{"role":"user","content":"hello"}]}'

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