jishie

Qwen2.5-VL-72B-Instruct

nebius/Qwen/Qwen2.5-VL-72B-Instruct · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimage.

$0.38Blended $/1M (3:1)
$0.25Input $/1M
$0.75Output $/1M
$1.001M in + 1M out
$0.025 −90%Cache read $/1M
#1875 of 5,000Cheapest rank
Provider
Nebius Token Factory (nebius)
Context
128,000 tokens
Max output
8,192 tokens
Capabilities
toolstextimage

Same model, other providers

“Qwen2.5-VL-72B-Instruct” is offered by 3 providers — cheapest-effective first. Cortecs is the cheapest at $0.37 blended.

ProviderInputOutputBlendedContext
Cortecs$0.25$0.747$0.3732k
Nebius Token Factory (this)$0.25$0.75$0.38128k
OVHcloud AI Endpoints$1.01$1.01$1.0133k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Nebius Token Factory 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-VL-72B-Instruct","messages":[{"role":"user","content":"hello"}]}'

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