Chat

Qwen-2.5 API

Name: Qwen-2.5
Brand: Alibaba (Qwen)
SKU: Qwen-2.5

Qwen2.5 0.5B instruction-tuned chat model, quantized to Q4_K_M for low-cost serverless inference.

$0.15 / 1M tokens · read from the live catalogue

Qwen-2.5 costs $0.15 / 1M tokens on Open LLMs. Call it by sending Qwen-2.5 as the model id to /v1/chat/completions, using any OpenAI-compatible client.

What are Qwen-2.5's specifications?

Every value here is read from the catalogue that serves the API, so this page and the service cannot disagree.

Model id: Qwen-2.5
Task: Chat
Price: $0.15 / 1M tokens
Context window: 33K tokens
Modality: text → text
Parameters: 500M
Licence: Apache-2.0
Endpoint: /v1/chat/completions

How do I call Qwen-2.5?

Point an OpenAI client at our base URL and name the model. Nothing else about your request changes.

Qwen-2.5 — first requestbash

curl https://api.openllms.co/v1/chat/completions \
  -H "Authorization: Bearer $OPENLLMS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen-2.5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Before your first call

An inference call needs an API key and a positive wallet balance. The first call to an idle model can answer 503 with a Retry-After header while it starts — wait, then retry. Full reference: the API docs.

How is Qwen-2.5 licensed?

Qwen-2.5 is served under the Apache-2.0 licence. The upstream licence passes through to you: what you may do with the output is governed by it, not by us. The obligations we pass through are listed on model licences, and the model card itself is at its source.

What else can I call?

See every model in the catalogue with its price, context window and licence.