impulse

Qwen2.5 72B Instruct

Open weights

Qwen2.5 72B is the latest series of Qwen large language models.

API id Qwen2.5-72B-InstructReleased 19 Sep 2024 (Sep 2024)
Input / 1M
$0.12
at Hyperbolic
Output / 1M
$0.30
at Hyperbolic
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
5
5 listings
Released
Sep 2024
19 Sep 2024

Pricing

List prices at Hyperbolic, in US dollars per million tokens.

TierInput / 1MOutput / 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
Use your own numbers

Where to run it

5 hosts serve Qwen2.5 72B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
HyperbolicInference
Qwen2.5-72B-Instruct
$0.12 / $0.30
Qwen2.5-72B-Instruct
$0.13 / $0.40
+20% vs headline
DeepInfraInference
Qwen2.5-72B-Instruct
$0.36 / $0.40
+124% vs headline
Fireworks AIInference
qwen2p5-72b-instruct
$0.90 / $0.90
+445% vs headline
Together AIInference
Qwen2.5-72B-Instruct
$1.20 / $1.20
+627% vs headline

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-2.0
Runs in about 174.5 GB of GPU memory
Runtimes: 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

  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    3% less
  • Ministral 8B 2512
    Mistral AI · on Mistral AI
    $0.15 / $0.15
    Has every key capability
    9% less
  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    14% less
  • MiMo V2.6 Flash
    Xiaomi · on GMI Cloud
    $0.112 / $0.224
    Has every key capability
    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.

  1. Sep 2024Qwen2.5 72B InstructLatest$0.12 / $0.30
  2. Sep 2024Qwen 2.5 72B Instruct$0.38 / $0.40
  3. UndatedQwen2 72B Instruct$0.90 / $0.90

Call it

Using Hyperbolic's API.

Python
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
}