qwen2.5-vl-72b-instruct
novita · chat model
qwen2.5-vl-72b-instruct is listed here as a chat model from novita. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.8000 / 1M tokens
Output
$0.8000 / 1M tokens
Cached input
N/A
Context
32.8K
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.8000 / 1M tokens |
| Output | $0.8000 / 1M tokens |
| Embedding | $0.8000 / 1M tokens |
Token limits
Context window
32.8K
Max input tokens
32.8K
Max output tokens
32.8K
Max tokens
32.8K
Capabilities
| Capability | Supported |
|---|---|
| Vision | ✅ |
| Function calling | — |
| Parallel function calling | — |
| Tool choice | — |
| Prompt caching | — |
| Reasoning | — |
| Response schema | — |
| System messages | ✅ |
| Audio input | — |
| Audio output | — |
| Web search | — |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| MMLU | 74.2% | accuracy | Base model: Qwen2.5 (Qwen2.5-7B-Instruct) | 2026-05-31 | Link |
| MMLU | 83.3% | accuracy | Base model: Qwen2.5 (Qwen2.5-32B-Instruct) | 2026-05-31 | Link |
| MATH | 49.8% | accuracy | Base model: Qwen2.5 (Qwen2.5-7B-Instruct) | 2026-05-31 | Link |
| MATH | 57.7% | accuracy | Base model: Qwen2.5 (Qwen2.5-32B-Instruct) | 2026-05-31 | Link |
| HumanEval | 57.9% | pass@1 | Base model: Qwen2.5 (Qwen2.5-7B-Instruct) | 2026-05-31 | Link |
| HumanEval | 58.5% | pass@1 | Base model: Qwen2.5 (Qwen2.5-32B-Instruct) | 2026-05-31 | Link |
| Artificial Analysis Coding Index | 11.9 | score | Base model: qwen2.5 (qwen/qwen-2.5-72b-instruct) | 2026-05-31 | Link |
| GPQA Diamond | 49.1% | accuracy | Base model: qwen2.5 (qwen/qwen-2.5-72b-instruct) | 2026-05-31 | Link |
| Humanity's Last Exam | 4.2% | accuracy | Base model: qwen2.5 (qwen/qwen-2.5-72b-instruct) | 2026-05-31 | Link |
| IFBench | 36.9% | accuracy | Base model: qwen2.5 (qwen/qwen-2.5-72b-instruct) | 2026-05-31 | Link |
| SciCode | 26.7% | accuracy | Base model: qwen2.5 (qwen/qwen-2.5-72b-instruct) | 2026-05-31 | Link |
| MMMU | 70 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| MMMU-Pro | 49.5 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| MMStar | 69.5 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| MathVista | 74.7 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| MathVision | 40.0 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| CC-OCR | 77.1 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| DocVQA | 94.8 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
| InfoVQA | 83.4 | score | Base model: Qwen2.5-VL (Qwen2.5-VL-32B) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| qwen2.5-vl-72b-instruct novita | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| qwen3-vl-235b-a22b-thinking novita | In $0.9800 / 1M tokens Out $3.9500 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Same provider Overall 81% |
| glm-4.6v novita | In $0.3000 / 1M tokens Out $0.9000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Same provider Overall 75% |
| qwen3-vl-30b-a3b-instruct novita | In $0.2000 / 1M tokens Out $0.7000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Same provider Overall 75% |
| qwen3-vl-30b-a3b-thinking novita | In $0.2000 / 1M tokens Out $1.0000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Same provider Overall 74% |
| llama-4-maverick-17b-128e-instruct-fp8 novita | In $0.2700 / 1M tokens Out $0.8500 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 8.2K | Same provider Overall 74% |
| qwen3-vl-235b-a22b-instruct novita | In $0.3000 / 1M tokens Out $1.5000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Same provider Overall 73% |
| nvidia.nemotron-nano-12b-v2 bedrock_converse | In $0.2000 / 1M tokens Out $0.6000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 8.2K | Text + image covered Overall 71% |
| qwen3-vl-8b-instruct novita | In $0.0800 / 1M tokens Out $0.5000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 32.8K | Same provider Overall 71% |
| llama-4-scout-17b-16e-instruct novita | In $0.1800 / 1M tokens Out $0.5900 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 131.1K | Same provider Overall 71% |
| gemma-3-27b-it novita | In $0.1190 / 1M tokens Out $0.2000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 16.4K | Same provider Overall 69% |
| moonshotai.kimi-k2.5 bedrock_converse | In $0.6000 / 1M tokens Out $3.0000 / 1M tokens | imagetextvideo
Output: text | VisionSystem messages | 262.1K | Text + image covered Overall 64% |
| google.gemma-3-27b-it bedrock_converse | In $0.2300 / 1M tokens Out $0.3800 / 1M tokens | imagetextvideo
Output: image, text | VisionSystem messages | 8.2K | Text + image covered Overall 61% |
| google.gemma-3-12b-it bedrock_converse | In $0.0900 / 1M tokens Out $0.2900 / 1M tokens | imagetextvideo
Output: image, text | VisionSystem messages | 8.2K | Text + image covered Overall 58% |
| deepseek-r1-distill-llama-70b novita | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: text | System messages | 8.2K | Same provider Overall 53% Missing image |
| gpt-oss-120b crusoe | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: unknown | System messages | 131.1K | Partial I/O overlap Overall 29% Missing text, image |
| hermes3-405b lambda_ai | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: unknown | System messages | 131.1K | Partial I/O overlap Overall 29% Missing text, image |
| llama3.1-405b-instruct-fp8 lambda_ai | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: unknown | System messages | 131.1K | Partial I/O overlap Overall 29% Missing text, image |
| deepseek-r1-671b lambda_ai | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: unknown | System messages | 131.1K | Partial I/O overlap Overall 28% Missing text, image |
| together-ai-21.1b-41b Together AI | In $0.8000 / 1M tokens Out $0.8000 / 1M tokens | imagetextvideo
Output: unknown | Low overlap | N/A | Partial I/O overlap Overall 20% Missing text, image |
No models match this filter.