jishie

DeepSeek V4 Flash 0731

nvidia/deepseek-ai/deepseek-v4-flash-0731 · 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
Cache read $/1M
#64 of 6,789
Cheapest rank
Provider
Nvidia (nvidia)
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” is offered by 35 providers — cheapest-effective first. This one (Nvidia) is the cheapest.

ProviderInputOutputBlendedContext
Nvidia (this)freefree$0.001M
Alibaba Token Planfreefree$0.001M
SCNet Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
Vercel AI Gateway$0.076$0.153$0.101M
Deep Infra$0.08$0.18$0.101M
OpenRouter$0.08$0.18$0.101.3M
Ambient$0.08$0.18$0.101M
Eden AI$0.08$0.18$0.101M
DigitalOcean$0.08$0.252$0.121M
Requesty$0.126$0.252$0.161M
Perplexity Agent$0.13$0.26$0.161M
Baseten$0.13$0.26$0.161M

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"deepseek-ai/deepseek-v4-flash-0731","messages":[{"role":"user","content":"hello"}]}'

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

← all Nvidia models · model index · JSON