jishie

DeepSeek V4 Flash 0731

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

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
free
Cache read $/1M
#84 of 9,397
Cheapest rank
Provider
AMD (amd)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
384,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“DeepSeek V4 Flash 0731” is offered by 59 providers — cheapest-effective first. This one (AMD) is the cheapest.

ProviderInputOutputBlendedContext
AMD (this)freefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
SCNet Token Planfreefree$0.001M
Alibaba Token Planfreefree$0.001M
JoinGonka$0.006171$0.0185$0.01380k
SAGG$0.0397$0.0794$0.05400k
engy$0.045$0.09$0.061M
Adaption$0.0444$0.1333$0.071M
NanoGPT$0.05$0.16$0.081M
Boundless$0.04$0.21$0.081M
Deep Infra$0.06$0.18$0.091M
OpenRouter$0.0434$0.3$0.111M
Doubleword$0.09$0.18$0.111M

Call it

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

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

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

← all AMD models · model index · JSON