Qwen2.5-VL-72B-Instruct
ovhcloud/qwen2.5-vl-72b-instruct · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: text image.
$1.01
Blended $/1M (3:1)
$1.01
Input $/1M
$1.01
Output $/1M
$2.02
1M in + 1M out
—
Cache read $/1M
#4107 of 7,708
Cheapest rank
- Provider
- OVHcloud AI Endpoints (
ovhcloud) - Kind
- text (outputs text)
- Context
- 32,768 tokens
- Max output
- 32,768 tokens
- Capabilities
- text image
Same model, other providers
“Qwen2.5-VL-72B-Instruct” is offered by 2 providers — cheapest-effective first. This one (OVHcloud AI Endpoints) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OVHcloud AI Endpoints (this) | $1.01 | $1.01 | $1.01 | 33k |
| Cortecs | $1.01 | $1.01 | $1.01 | 32k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at OVHcloud AI Endpoints and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"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):