Language model
qwen2.5 Vl 72b Instruct API
qwen2.5 Vl 72b Instruct is a language model from Alibaba, live in the language lane of the Corent catalog. It answers in the standard chat completions format on POST /v1/chat/completions, with the exact charge on every response.
Pin it by name, or let the router earn it.
You pick
POST /v1/chat/completions{ "model": "corent-qwen2.5-vl-72b-instruct", "messages": [{ "role": "user", "content": "Write a haiku about shipping fast." }]}
Direct access runs qwen2.5 Vl 72b Instruct and no other model. No substitution, flat cost-plus, billed only on success, and the receipt names the model you pinned.
The router picks
POST /v1/chat/completions{ "model": "corent/text-premium", "messages": [{ "role": "user", "content": "Write a haiku about shipping fast." }]}
Name a tier and the router reads the prompt, scores every live language model on quality and price, and may pick qwen2.5 Vl 72b Instruct whenever it wins. Failed attempts cost $0.
One key, one request.
curl -X POST https://api.corent.tech/v1/chat/completions \ -H "Authorization: Bearer $CORENT_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "corent-qwen2.5-vl-72b-instruct", "messages": [{"role": "user", "content": "Write a haiku about shipping fast."}]}'
The response carries the result and a receipt: the model that served you and the exact cost in cents. Full request and response shapes are in the docs.
qwen2.5 Vl 72b Instruct, as the API serves it today.
- Pin by name
corent-qwen2.5-vl-72b-instruct- Modality
- Language
- Endpoint
- POST /v1/chat/completions
- Lab
- Alibaba
- Quality
- 4.8 out of 10, Corent's score
- Status
- Live
These fields come from the live catalog, the same GET /v1/models payload the full model ledger prints, so they can never drift from what the API actually serves.
Common questions
Does qwen2.5 Vl 72b Instruct have an API?
Yes. qwen2.5 Vl 72b Instruct is served through the Corent API on POST /v1/chat/completions. Pin the exact name corent-qwen2.5-vl-72b-instruct and you get that model or nothing: no substitution, and a failed generation is never billed. One Corent key covers it alongside every other model in the catalog.
How much does qwen2.5 Vl 72b Instruct cost via Corent?
Corent does not publish a per-model rate card. Direct access is flat cost-plus, you are billed only on success, and every response carries the exact charge on its receipt. Tier prices are public on the pricing page at corent.tech/pricing.
Do I have to pick qwen2.5 Vl 72b Instruct?
No. Send a tier instead of a model and the router reads each prompt, picks the best live model at that moment, and reroutes on failure. Pinning corent-qwen2.5-vl-72b-instruct is for when you want exactly this model on every request.
Related models
Every one of them runs on the same key and the same endpoint as qwen2.5 Vl 72b Instruct, and the full model ledger lists the whole catalog.
Run qwen2.5 Vl 72b Instruct in your next request
One key opens the whole catalog: pin qwen2.5 Vl 72b Instruct, or name a tier and never pick a model again. Start with $5 in prepaid credits.
Get an API key