impulse

Qwen2.5 7B Instruct

Open weights
API id Qwen2.5-7B-Instruct
Input / 1M
$0.04
at DeepInfra
Output / 1M
$0.10
at DeepInfra
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.04$0.10

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$19.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$22.80
  • Coding agent1,000 requests a day, 40K in / 2K out$54.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$120
Use your own numbers

Where to run it

3 hosts serve Qwen2.5 7B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
Qwen2.5-7B-Instruct
$0.04 / $0.10
Novita AIInference
qwen2.5-7b-instruct
$0.07 / $0.07
+27% vs headline
Fireworks AIInference
qwen2p5-7b-instruct
$0.20 / $0.20
+264% 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
Open weights
License: Apache-2.0
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 DeepInfra.

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 3 4B IT
    Google · on Amazon Bedrock
    $0.04 / $0.08
    Has every key capability
    9% less
  • Llama 3.2 3B
    Meta · on LlamaGate
    $0.04 / $0.08
    Has every key capability
    9% less
  • Qwen3.7 Flash Variant1
    Alibaba Qwen · on EmpirioLabs AI
    $0.028 / $0.11
    Has every key capability
    12% less
  • Granite 4.0 H Micro
    IBM · on Cloudflare Workers AI
    $0.017 / $0.112
    Has every key capability
    26% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedQwen2.5 7B InstructLatest$0.04 / $0.10
  2. UndatedQwen2 7B Instruct$0.20 / $0.20

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Qwen2.5-7B-Instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen2.5 7B Instruct cost?

On DeepInfra, Qwen2.5 7B Instruct costs $0.04 per million input tokens and $0.10 per million output tokens.

Which APIs offer Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct runs on 3 APIs: DeepInfra, Novita AI and Fireworks AI.

What is Qwen2.5 7B Instruct's context window?

33K tokens, with up to 33K tokens in one reply.

Is Qwen2.5 7B Instruct being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Qwen2.5 7B Instruct?

No. Qwen2.5 7B Instruct is the newest model in its line.

What are cheaper alternatives to Qwen2.5 7B Instruct?

Models that cost less and keep most of what it can do: Gemma 3 4B IT on Amazon Bedrock (9% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Qwen2.5 7B Instruct's API model id?

Use Qwen2.5-7B-Instruct with DeepInfra. Other hosts use their own ids: qwen2.5-7b-instruct on Novita AI, qwen2p5-7b-instruct on Fireworks AI.

Sources

Raw catalog entry for Qwen2.5-7B-Instruct on DeepInfra
{
  "max_input_tokens": 32768,
  "max_output_tokens": 32768,
  "input_cost_per_token": 4e-8,
  "output_cost_per_token": 1e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": false
}