jishie

Qwen2.5 VL 72B Instruct

novita-ai/qwen/qwen2.5-vl-72b-instruct · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: text image video.

$0.80
Blended $/1M (3:1)
$0.8
Input $/1M
$0.8
Output $/1M
$1.60
1M in + 1M out
—
Cache read $/1M
#3703 of 7,708
Cheapest rank
Provider
NovitaAI (novita-ai)
Kind
text (outputs text)
Context
32,768 tokens
Max output
32,768 tokens
Capabilities
text image video

Same model, other providers

“Qwen2.5 VL 72B Instruct” is offered by 2 providers — cheapest-effective first. This one (NovitaAI) is the cheapest.

ProviderInputOutputBlendedContext
NovitaAI (this)$0.8$0.8$0.8033k
OpenRouter$0.8$1$0.85128k

Call it

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

Most providers are OpenAI-compatible — point base_url at NovitaAI 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):

← all NovitaAI models · model index · JSON