impulse

Qwen2.5 Coder 3B Instruct

Open weights
API id Qwen2.5-Coder-3B-Instruct
Input / 1M
$0.01
at Nscale
Output / 1M
$0.03
at Nscale
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.01$0.03

What it costs a month

At Nscale list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$5.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$5.88
  • Coding agent1,000 requests a day, 40K in / 2K out$13.80
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$31.20
Use your own numbers

Where to run it

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

HostIn / out per 1M
NscaleInference
Qwen2.5-Coder-3B-Instruct
$0.01 / $0.03
Fireworks AIInference
qwen2p5-coder-3b-instruct
$0.10 / $0.10
+567% 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 Nscale.

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

No cheaper open-weight match.

Call it

Using Nscale's API.

Python
from litellm import completion

response = completion(
    model="nscale/Qwen2.5-Coder-3B-Instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen2.5 Coder 3B Instruct cost?

On Nscale, Qwen2.5 Coder 3B Instruct costs $0.01 per million input tokens and $0.03 per million output tokens.

Which APIs offer Qwen2.5 Coder 3B Instruct?

Qwen2.5 Coder 3B Instruct runs on 2 APIs: Nscale and Fireworks AI.

What is Qwen2.5 Coder 3B Instruct's context window?

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

Is Qwen2.5 Coder 3B Instruct being retired?

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

What is Qwen2.5 Coder 3B Instruct's API model id?

Use Qwen2.5-Coder-3B-Instruct with Nscale. Other hosts use their own ids: qwen2p5-coder-3b-instruct on Fireworks AI.

Sources

Raw catalog entry for Qwen2.5-Coder-3B-Instruct on Nscale
{
  "input_cost_per_token": 1e-8,
  "litellm_provider": "nscale",
  "mode": "chat",
  "output_cost_per_token": 3e-8,
  "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
}