Qwen vision-language model for visual reasoning, documents, and agent tasks
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.
Context
128K
128,000 tokens
Max output
115K
115,200 tokens
Input
$0.80
per 1M tokens
Output
$1.00
per 1M tokens
Providers
5
5 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Kilo Gateway
| Token type | Standard |
|---|---|
| Input | $0.80 |
| Output | $1.00 |
| Cache read | $0.40 |
Lowest input price across providers: $0.70.
Capabilities
ReasoningNo
Tool callNo
Structured outputYes
TemperatureYes
AttachmentsYes
Interleaved reasoningNo
Open weightsYes
ModeratedNo
Input
TextImage
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 5
5 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Cortecs | qwen2.5-vl-72b-instruct | 32K | — | 32K | $1.01 | $1.01 | — | — | — | — | — | No | No | Yes | No | Jan 26, 2025 |
 Kilo Gateway | qwen/qwen2.5-vl-72b-instruct | 128K | — | 115K | $0.80 | $1.00 | — | $0.40 | — | — | — | No | No | Yes | Yes | Jan 26, 2025 |
 NanoGPT | TEE/qwen2.5-vl-72b-instruct | 66K | 66K | 8K | $0.70 | $0.70 | — | $0.35 | — | — | — | No | No | No | Yes | Jan 26, 2025 |
 OVHcloud AI Endpoints | qwen2.5-vl-72b-instruct | 33K | — | 33K | $1.01 | $1.01 | — | — | — | — | — | No | No | Yes | Yes | Jan 26, 2025 |
 Qiniu | qwen2.5-vl-72b-instruct | 128K | — | 8K | $2.32 | $6.96 | — | — | — | — | — | No | Yes | Yes | Yes | Jan 26, 2025 |