jishie

DeepSeek V4 Flash 0731

iteracompute/deepseek/deepseek-v4-flash-0731 · family deepseek-flash · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.52
Blended $/1M (3:1)
$0.34
Input $/1M
$1.05
Output $/1M
$1.39
1M in + 1M out
$0.035 −90%
Cache read $/1M
#2755 of 7,381
Cheapest rank
Provider
IteraCompute (iteracompute)
Kind
text (outputs text)
Context
970,000 tokens
Max output
393,216 tokens
Capabilities
tools reasoning text

Same model, other providers

“DeepSeek V4 Flash 0731” is offered by 42 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Token Planfreefree$0.001M
Nvidiafreefree$0.001M
SCNet Token Planfreefree$0.001M
Alibaba Token Plan (China)freefree$0.001M
Merge Gateway$0.035$0.07$0.041M
OpenRouter$0.06$0.12$0.071.3M
NanoGPT$0.05$0.16$0.081M
Cortecs$0.055$0.174$0.081M
Deep Infra$0.06$0.18$0.091M
Vercel AI Gateway$0.076$0.153$0.101M
Ambient$0.08$0.18$0.101M
DigitalOcean$0.08$0.252$0.121M
IteraCompute (this)$0.34$1.05$0.52970k

Call it

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

Most providers are OpenAI-compatible — point base_url at IteraCompute 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-0731","messages":[{"role":"user","content":"hello"}]}'

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

← all IteraCompute models · model index · JSON