Qwen2.5 72B Instruct
Qwen2.5 72B is the latest series of Qwen large language models.
Qwen2.5-72B-InstructReleased 19 Sep 2024 (Sep 2024)Pricing
List prices at Hyperbolic, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.12 | $0.30 |
What it costs a month
At Hyperbolic list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$58.50
- RAG over documents2,000 requests a day, 8K in / 0.6K out$68.40
- Coding agent1,000 requests a day, 40K in / 2K out$162
- Overnight batch20,000 requests a day, 4K in / 0.4K out$360
Where to run it
5 hosts serve Qwen2.5 72B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
HyperbolicInference Qwen2.5-72B-Instruct | $0.12 / $0.30 | Qwen2.5-72B-Instruct | |
Nebius AI StudioInference Qwen2.5-72B-Instruct | $0.13 / $0.40 +20% vs headline | Qwen2.5-72B-Instruct | |
DeepInfraInference Qwen2.5-72B-Instruct | $0.36 / $0.40 +124% vs headline | Qwen2.5-72B-Instruct | |
Fireworks AIInference qwen2p5-72b-instruct | $0.90 / $0.90 +445% vs headline | qwen2p5-72b-instruct | |
Together AIInference Qwen2.5-72B-Instruct | $1.20 / $1.20 +627% vs headline | Qwen2.5-72B-Instruct |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Parallel tool calls
- Open weights
- License: Apache-2.0Runs in about 174.5 GB of GPU memoryRuntimes: Ollama, SGLang, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Hyperbolic.
Smaller Alibaba Qwen models
No cheaper Alibaba Qwen model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 3% less
- 9% less
- 14% less
- 15% less
Benchmarks
Scores published on the model card.
- BBH61.9%
- GPQA16.7%
- IFEval86.4%
- MATH Lvl 559.8%
- MMLU-Pro51.4%
- MUSR11.7%
- Open LLM Average48.0%
Model line
Newer and older versions, at each lab's own price.
- Sep 2024Qwen2.5 72B InstructLatest$0.12 / $0.30
- Sep 2024Qwen 2.5 72B Instruct$0.38 / $0.40
- UndatedQwen2 72B Instruct$0.90 / $0.90
Call it
Using Hyperbolic's API.
from litellm import completion
response = completion(
model="hyperbolic/Qwen2.5-72B-Instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen2.5 72B Instruct cost?
On Hyperbolic, Qwen2.5 72B Instruct costs $0.12 per million input tokens and $0.30 per million output tokens.
Which APIs offer Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct runs on 5 APIs: Hyperbolic, Nebius AI Studio, DeepInfra, Fireworks AI and Together AI.
What is Qwen2.5 72B Instruct's context window?
131K tokens, with up to 131K tokens in one reply.
Is Qwen2.5 72B Instruct being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Qwen2.5 72B Instruct?
No. Qwen2.5 72B Instruct is the newest model in its line.
What are cheaper alternatives to Qwen2.5 72B Instruct?
Models that cost less and keep most of what it can do: Gemma 4 31B IT on W&B Inference (3% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen2.5 72B Instruct released?
Alibaba Qwen released it on 19 Sep 2024.
What is Qwen2.5 72B Instruct's API model id?
Use Qwen2.5-72B-Instruct with Hyperbolic. Other hosts use their own ids: qwen2p5-72b-instruct on Fireworks AI.
Sources
Raw catalog entry for Qwen2.5-72B-Instruct on Hyperbolic
{
"input_cost_per_token": 1.2e-7,
"litellm_provider": "hyperbolic",
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3e-7,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true
}