Using Qwen2.5-7B-Instruct on Together AI

Implementation guide · Qwen2.5 · Alibaba

ServerlessOpen Source

Together AI exposes Qwen2.5-7B-Instruct through model ID Qwen/Qwen2.5-7B-Instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-15. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Together AI and generate an API key.
  2. 2
    Use the Together AI SDK or REST API to call Qwen/Qwen2.5-7B-Instruct — see the documentation for request format.
  3. 3
    You'll be billed $0.15/1M input, $0.15/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

Install
pip install together
API key
TOGETHER_API_KEY
Model ID
Qwen/Qwen2.5-7B-Instruct

Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="Qwen/Qwen2.5-7B-Instruct",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Together AI

TypePrice (per 1M)
Input tokens$0.15
Output tokens$0.15

Capabilities

Structured Outputs

About Qwen2.5-7B-Instruct

Instruction-tuned 7B variant combining strong reasoning with real-time inference on single GPUs, ideal for developer tools and vision applications.

Full model details →

Model Specs

Released2024-06-07
Parameters7.61B
Context128k
ArchitectureDecoder Only

Also available on(7)

DeepInfra$0.03/1MOpenRouter$0.04/1MSiliconFlow$0.04/1M
Compare all providers →

Provider

Together AI

San Francisco, California, United States