Vigia

AI model · Qwen

Qwen2.5 72B Instruct available

qwen/qwen-2.5-72b-instruct

Qwen2.5 72B Instruct costs US$ 0.36 per million input tokens and US$ 0.4 per million output tokens (OpenRouter reference price, verified 2026-11-13).

Input price (per 1M tokens)US$ 0.36
Output price (per 1M tokens)US$ 0.4
Typical request (2,000 tokens in, 500 out)US$ 0.00092
Context window32,768
Max output tokens16,384
Announced retirement datenone
Knowledge cutoff2024-06-30
Last verified2026-11-13 16:37:47 UTC

Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.

Frequently asked questions

How much does Qwen2.5 72B Instruct cost?

Qwen2.5 72B Instruct costs US$ 0.36 per million input tokens and US$ 0.4 per million output tokens (OpenRouter reference price, verified 2026-11-13).

What is the context window of Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct accepts up to 32,768 tokens of context.

Is Qwen2.5 72B Instruct being retired?

No retirement date has been announced for Qwen2.5 72B Instruct (checked 2026-11-13).

Other Qwen models

ModelInput / 1MOutput / 1MContext
qwen/qwen3.8-max-primeUS$ 4.00US$ 12.001,000,000
qwen/qwen3.8-omni-flashUS$ 0.15US$ 0.471,000,000
qwen/qwen3.8-max-0902US$ 2.00US$ 6.001,000,000
qwen/qwen3.8-max-0902:batchUS$ 1.15US$ 3.45262,144
qwen/qwen3.8-flashUS$ 0.15US$ 0.471,000,000
qwen/qwen3.8-27bUS$ 0.15US$ 1.881,048,575
qwen/qwen3.8-27b:batchUS$ 0.16US$ 2.00262,144
qwen/qwen3.8-2.4t-a95bUS$ 2.00US$ 6.001,048,576
qwen/qwen3.7-flashUS$ 0.03US$ 0.131,000,000
qwen/qwen3.7-plusUS$ 0.32US$ 1.281,000,000
qwen/qwen3.7-plus:batchUS$ 0.23US$ 0.92262,144
qwen/qwen3.7-maxUS$ 1.48US$ 4.421,000,000
qwen/qwen3.5-plus-20260420US$ 0.3US$ 1.801,000,000
qwen/qwen3.6-flashUS$ 0.188US$ 1.131,000,000
qwen/qwen3.6-35b-a3bUS$ 0.1US$ 0.9262,144
qwen/qwen3.6-27bUS$ 0.32US$ 3.20262,144
qwen/qwen3.6-plusUS$ 0.325US$ 1.951,000,000
qwen/qwen3.5-9bUS$ 0.075US$ 0.111262,144
qwen/qwen3.5-35b-a3bUS$ 0.14US$ 1.00262,144
qwen/qwen3.5-27bUS$ 0.26US$ 2.60262,144
qwen/qwen3.5-122b-a10bUS$ 0.26US$ 2.08262,144
qwen/qwen3.5-flash-02-23US$ 0.065US$ 0.261,000,000
qwen/qwen3.5-plus-02-15US$ 0.26US$ 1.561,000,000
qwen/qwen3.5-397b-a17bUS$ 0.6US$ 3.60262,144
qwen/qwen3-coder-nextUS$ 0.12US$ 0.8262,144
qwen/qwen3-vl-8b-instructUS$ 0.25US$ 0.75262,144
qwen/qwen3-vl-30b-a3b-thinking retiring 2026-11-15US$ 0.29US$ 1.00262,144
qwen/qwen3-vl-30b-a3b-instructUS$ 0.15US$ 0.6262,144
qwen/qwen3-vl-235b-a22b-instructUS$ 0.21US$ 1.90262,144
qwen/qwen3-coder-flashUS$ 0.195US$ 0.9751,000,000
qwen/qwen3-next-80b-a3b-instructUS$ 0.09US$ 1.10262,144
qwen/qwen3-coder-30b-a3b-instructUS$ 0.15US$ 0.6262,144
qwen/qwen3-30b-a3b-instruct-2507US$ 0.1US$ 0.3262,144
qwen/qwen3-235b-a22b-thinking-2507US$ 0.45US$ 3.50128,000
qwen/qwen3-coderUS$ 0.3US$ 1.00262,144
qwen/qwen3-235b-a22b-2507US$ 0.14US$ 0.8262,144
qwen/qwen3-30b-a3bUS$ 0.12US$ 0.540,960
qwen/qwen3-14bUS$ 0.12US$ 0.2440,960
qwen/qwen3-32bUS$ 0.08US$ 0.28131,072
qwen/qwen2.5-vl-72b-instructUS$ 0.8US$ 1.00128,000

Give your AI agent these facts

Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.

claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp

Add to CursorAdd to VS Code★ Star on GitHub

Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }

Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests

For agents

GET https://vigia.coredls.cloud/v1/models/qwen/qwen-2.5-72b-instruct