jishie

DeepSeek V4 Flash Vision Exp

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

$0.32
Blended $/1M (3:1)
$0.2156
Input $/1M
$0.6468
Output $/1M
$0.86
1M in + 1M out
$0.00686 −97%
Cache read $/1M
#2367 of 7,920
Cheapest rank
Provider
OpenRouter (openrouter)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
262,144 tokens
Capabilities
tools reasoning text image

Same model, other providers

“DeepSeek V4 Flash Vision Exp” is offered by 17 providers — cheapest-effective first. CrofAI is the cheapest at $0.11 blended.

ProviderInputOutputBlendedContext
CrofAI$0.08$0.2$0.111M
OpenCode Zen$0.14$0.28$0.181M
AMD$0.14$0.28$0.181M
OrcaRouter$0.147$0.295$0.181M
DeepSeek$0.15$0.6$0.261M
OpenCode Go$0.15$0.6$0.261M
Eden AI$0.15$0.6$0.261M
AIHubMix$0.155$0.62$0.271M
OpenRouter (this)$0.2156$0.6468$0.321M
Vercel AI Gateway$0.2156$0.6468$0.321M
NanoGPT$0.22$0.66$0.331M
CrossModel$0.3$1.2$0.521M
Deep Infra$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 OpenRouter and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4-flash-vision-exp","messages":[{"role":"user","content":"hello"}]}'

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

← all OpenRouter models · model index · JSON