Qwen2.5-72B-Instruct
deepinfra · chat model
Qwen2.5-72B-Instruct is listed here as a chat model from deepinfra. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$0.1200 / 1M tokens
Output
$0.3900 / 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 | $0.1200 / 1M tokens |
| Output | $0.3900 / 1M tokens |
| Embedding | $0.1200 / 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 |
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 |
|---|---|---|---|---|---|
| Qwen2.5-72B-Instruct deepinfra | In $0.1200 / 1M tokens Out $0.3900 / 1M tokens | text
Output: text | Function callingTool choice | 32.8K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| Mixtral-8x7B-Instruct-v0.1 deepinfra | In $0.4000 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Function callingTool choice | 32.8K | Same provider Overall 93% |
| Qwen3-32B deepinfra | In $0.1000 / 1M tokens Out $0.2800 / 1M tokens | text
Output: text | Function callingTool choice | 41.0K | Same provider Overall 92% |
| Qwen3-30B-A3B deepinfra | In $0.0800 / 1M tokens Out $0.2900 / 1M tokens | text
Output: text | Function callingTool choice | 41.0K | Same provider Overall 91% |
| Qwen3-235B-A22B deepinfra | In $0.1800 / 1M tokens Out $0.5400 / 1M tokens | text
Output: text | Function callingTool choice | 41.0K | Same provider Overall 91% |
| Phi-4 azure_ai | In $0.1250 / 1M tokens Out $0.5000 / 1M tokens | text
Output: text | Function callingTool choice | 16.4K | Text covered Overall 90% |
| qwen-3-32b vercel_ai_gateway | In $0.1000 / 1M tokens Out $0.3000 / 1M tokens | text
Output: text | Function callingTool choice | 16.4K | Text covered Overall 88% |
| Qwen3-14B deepinfra | In $0.0600 / 1M tokens Out $0.2400 / 1M tokens | text
Output: text | Function callingTool choice | 41.0K | Same provider Overall 88% |
| Llama-3.3-70B-Instruct-Turbo deepinfra | In $0.1300 / 1M tokens Out $0.3900 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Same provider Overall 88% |
| Llama-3.3-Nemotron-Super-49B-v1.5 deepinfra | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Same provider Overall 87% |
| QwQ-32B deepinfra | In $0.1500 / 1M tokens Out $0.4000 / 1M tokens | text
Output: text | Function callingTool choice | 131.1K | Same provider Overall 87% |
| Llama-3.3-70B-Instruct azure_ai | In $0.7100 / 1M tokens Out $0.7100 / 1M tokens | text
Output: text | Function callingTool choice | 2.0K | Text covered Overall 74% |
| gpt-3.5-turbo Azure | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Text covered Overall 72% |
| gpt-35-turbo Azure | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Text covered Overall 72% |
| gpt-35-turbo-16k-0613 Azure | In $3.0000 / 1M tokens Out $4.0000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Text covered Overall 68% |
| gpt-4-0613 Azure | In $30.0000 / 1M tokens Out $60.0000 / 1M tokens | text
Output: text | Function callingTool choice | 4.1K | Text covered Overall 67% |
| gemini-2.0-flash-001 deepinfra | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | text audiocode
Output: text | Function callingTool choice | 1.0M | Same provider Overall 65% |
| Llama-3.3-70B-Instruct nebius | In $0.1300 / 1M tokens Out $0.4000 / 1M tokens | text
Output: unknown | Function calling | 128.0K | Partial I/O overlap Overall 35% Missing text |
| Meta-Llama-3.1-70B-Instruct nebius | In $0.1300 / 1M tokens Out $0.4000 / 1M tokens | text
Output: unknown | Function calling | 128.0K | Partial I/O overlap Overall 35% Missing text |
| Qwen2.5-72B-Instruct nebius | In $0.1300 / 1M tokens Out $0.4000 / 1M tokens | text
Output: unknown | Function calling | 128.0K | Partial I/O overlap Overall 35% Missing text |
| Qwen2.5-VL-72B-Instruct nebius | In $0.1300 / 1M tokens Out $0.4000 / 1M tokens | text
Output: unknown | Function calling | 131.1K | Partial I/O overlap Overall 31% Missing text |
| Qwen2-VL-72B-Instruct nebius | In $0.1300 / 1M tokens Out $0.4000 / 1M tokens | text
Output: unknown | Function calling | 131.1K | Partial I/O overlap Overall 31% Missing text |
No models match this filter.