jishie

Qwen/Qwen2.5-72B-Instruct

siliconflow-cn/Qwen/Qwen2.5-72B-Instruct · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$0.59Blended $/1M (3:1)
$0.59Input $/1M
$0.59Output $/1M
$1.181M in + 1M out
—Cache read $/1M
#2498 of 5,000Cheapest rank
Provider
SiliconFlow (China) (siliconflow-cn)
Context
33,000 tokens
Max output
4,000 tokens
Capabilities
toolstext

Same model, other providers

“Qwen/Qwen2.5-72B-Instruct” is offered by 2 providers — cheapest-effective first. This one (SiliconFlow (China)) is the cheapest.

ProviderInputOutputBlendedContext
SiliconFlow (China) (this)$0.59$0.59$0.5933k
SiliconFlow$0.59$0.59$0.5933k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at SiliconFlow (China) and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"Qwen/Qwen2.5-72B-Instruct","messages":[{"role":"user","content":"hello"}]}'

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