jishie

DeepSeek V4.1 Flash 1017

scx-ai/DeepSeek-V4.1-flash-1017 · family deepseek-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.

$0.52
Blended $/1M (3:1)
$0.3
Input $/1M
$1.2
Output $/1M
$1.50
1M in + 1M out
$0.006 −98%
Cache read $/1M
#3488 of 9,495
Cheapest rank
Provider
SCX.ai (scx-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 V4.1 Flash 1017” is offered by 76 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
cheapllm.shopfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
Umans AI Coding Planfreefree$0.001M
Refuseless$0.01$0.08$0.031M
engy$0.03$0.12$0.051M
Liquid Inference$0.059$0.206$0.101M
50X$0.064$0.24$0.111M
Ambient$0.098$0.294$0.151M
OpenRouter$0.036$0.5$0.151M
Runcrate$0.1029$0.3087$0.151M
DevPass (LLM Gateway)$0.0776$0.5869$0.201.1M
SCX.ai (this)$0.3$1.2$0.521M

Call it

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

Most providers are OpenAI-compatible — point base_url at SCX.ai and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"DeepSeek-V4.1-flash-1017","messages":[{"role":"user","content":"hello"}]}'

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

← all SCX.ai models · model index · JSON