DeepSeek-V3.2 (Non-thinking Mode)

zenmux/deepseek/deepseek-chat · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$0.32Blended $/1M (3:1)

$0.28Input $/1M

$0.42Output $/1M

$0.701M in + 1M out

$0.03 −89%Cache read $/1M

#1764 of 5,000Cheapest rank

Provider: ZenMux (zenmux)
Context: 128,000 tokens
Max output: 64,000 tokens
Capabilities: toolstext

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at ZenMux 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-chat","messages":[{"role":"user","content":"hello"}]}'

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