jishie

DeepSeek V4 Flash 0731 Fast

aihubmix/deepseek-v4-flash-0731-fast · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.56
Blended $/1M (3:1)
$0.28
Input $/1M
$1.4
Output $/1M
$1.68
1M in + 1M out
$0.07 −75%
Cache read $/1M
#3105 of 7,708
Cheapest rank
Provider
AIHubMix (aihubmix)
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 0731 Fast” is offered by 2 providers — cheapest-effective first. Venice AI is the cheapest at $0.44 blended.

ProviderInputOutputBlendedContext
Venice AI$0.35$0.7$0.441M
AIHubMix (this)$0.28$1.4$0.561M

Call it

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

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

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

← all AIHubMix models · model index · JSON