Qwen2.5-VL 72B Instruct
by Alibaba (Qwen)Chat
Qwen vision-language model for visual reasoning, documents, and agent tasks
- Context
- 131K tokens
- Max output
- 8,192 tokens
- Parameters
- 73.4B total
- Released
- 2024-09
- Weights
- Open
- Licence
- qwen
alibaba/qwen2-5-vl-72b-instruct · also seen as qwen/qwen2.5-vl-72b-instruct, TEE/qwen2.5-vl-72b-instruct, accounts/fireworks/models/qwen2p5-vl-72b-instruct
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2024-09
- Weights
- Opennot gated
- License
- qwen
- Input
- Text, Image
- Output
- Text
- Context window
- 131,072 max across endpoints
- Max output
- 8,192
- Providers
- 11 + 5 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.25–$1.01 in · $0.60–$1.01 out per 1M tokens · 8 of 11 providers have a comparable price
More details
- Last updated
- 2025-08-05
- Knowledge cutoff
- 2024-04
- Weights link
- Hugging Face · Qwen/Qwen2.5-VL-72B-Instruct
- Parameters
- 73.4B total
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.25 in / $0.75 out per 1M tokens at Nebius Token Factory on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Qwen2.5-VL 72B Instruct |
|---|---|---|---|---|---|
| Llama 3.3 70B WayfarerLatitude | $0.70 | $0.70 | $0.70 | 32.8K | +0% |
| GLM LatestZ.ai (Zhipu AI) | $0.683 | $0.60 | $1.10 | 1.05M | −2% cheaper |
| Qwen3 VL 235B A22B ThinkingAlibaba (Qwen) | $0.717 | $0.287 | $2.87 | 131K | +2% |
| llama-3-2-90bMeta | $0.72 | $0.72 | $0.72 | 128K | +3% |
| minicpm-v-4.5OpenBMB | $0.725 | $0.651 | $1.10 | 32K | +4% |
| Seed 2.0 CodeByteDance Seed | $0.733 | $0.40 | $2.40 | 262K | +5% |
| Devstral 2Mistral AI | $0.733 | $0.44 | $2.20 | 262K | +5% |
| Moonshot Kimi K2 ThinkingMoonshot AI | $0.733 | $0.48 | $2.00 | 262K | +5% |
More from Alibaba (Qwen)
Newest Alibaba (Qwen) models in the catalogue. All Alibaba (Qwen) models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Qwen Image 2.1 Pro | 2026-10-16 | 65.5K | unpriced |
| Qwen 3.8 27B Fimi | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Kiwen | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Swift | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Kimiko | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Synthia | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Antislop | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B DarkIdol | 2026-10-05 | 262K | $0.10 via NanoGPT |