jishie

DeepSeek V4 Flash Vision Exp

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

$0.33
Blended $/1M (3:1)
$0.22
Input $/1M
$0.66
Output $/1M
$0.88
1M in + 1M out
$0.007 −97%
Cache read $/1M
#2083 of 7,019
Cheapest rank
Provider
Fireworks AI (fireworks-ai)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
384,000 tokens
Capabilities
tools reasoning text image

Same model, other providers

“DeepSeek V4 Flash Vision Exp” is offered by 13 providers — cheapest-effective first. DevPass (LLM Gateway) is the cheapest at $0.18 blended.

ProviderInputOutputBlendedContext
DevPass (LLM Gateway)$0.14$0.28$0.181.1M
DeepSeek$0.14$0.28$0.181M
OrcaRouter$0.147$0.295$0.181M
Fireworks AI (this)$0.22$0.66$0.331M
NanoGPT$0.22$0.66$0.331M
Vercel AI Gateway$0.22$0.66$0.331M
OpenRouter$0.22$0.66$0.331M
Vancine$0.22$0.66$0.331M
OpenCode Go$0.22$0.66$0.331M
Eden AI$0.22$0.66$0.331M
CrossModel$0.405$1.22$0.611M
Kilo Gateway$0.44$1.32$0.661M
Ofox$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 Fireworks AI and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"accounts/fireworks/models/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 Fireworks AI models · model index · JSON