Qwen2.5 VL 72B Instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
- Input / output price
- $0.80 / $1.00 per 1M
- Context
- 131K tokens
- Released
- Jan 26, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Parasail parasail/qwen2.5-vl-72b-instruct | $0.80/M | $1.00/M |
OpenRouter openrouter/qwen2.5-vl-72b-instruct | $0.80/M | $1.00/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 2 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.80 per 1M
- Average output
- $1.00 per 1M
- Average cache read
- $0.40 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better5.9tokens/sacross providers
Response latency
Lower is better0.5sacross providers
Benchmarks
10 published scores from 3 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OSWorld-VerifiedXLANG | 5% | XLANG | Jul 28, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| DocVQA VALhuggingface.co | 96.4% | huggingface.co | Jan 27, 2025 |
| ChartQA TESThuggingface.co | 89.5% | huggingface.co | Jan 27, 2025 |
| MMBench DEV EN v1.1huggingface.co | 88% | huggingface.co | Jan 27, 2025 |
| MathVista MINIhuggingface.co | 74.8% | huggingface.co | Jan 27, 2025 |
| MMStarhuggingface.co | 70.8% | huggingface.co | Jan 27, 2025 |
| MMMUhuggingface.co | 70.2% | huggingface.co | Jan 27, 2025 |
| MMMU-Prohuggingface.co | 51.1% | huggingface.co | Jan 27, 2025 |
| MathVision FULLhuggingface.co | 38.1% | huggingface.co | Jan 27, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena VisionLMArena | 1121 Elo · #88 of 91 | LMArena | Nov 19, 2026 |
Apps
Use Qwen2.5 VL 72B Instruct in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Qwen2.5 VL 72B Instruct FAQ
Short answers, built from the data on this page.
Qwen2.5 VL 72B Instruct is a model from Qwen, released on Jan 26, 2025. Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
On the Respan gateway, Qwen2.5 VL 72B Instruct costs $0.80 per 1M input tokens and $1.00 per 1M output tokens on every provider, after gateway discounts.
Qwen2.5 VL 72B Instruct is available through 2 providers: Parasail and OpenRouter.
Qwen2.5 VL 72B Instruct accepts up to 131K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen2.5-vl-72b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen2.5 VL 72B Instruct has 10 published benchmark scores, including OSWorld-Verified 5%, DocVQA VAL 96.4%, and LMArena Vision 1121. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.