Qwen2.5 Coder 3B Instruct API Pricing
As of October 10, 2026, Qwen2.5 Coder 3B Instruct costs $0.01 per 1M input tokens and $0.03 per 1M output tokens from Nscale, the lowest of 2 providers. It has a 32,768-token context window and returns up to 32,768 tokens per response.
- Input
- $0.01 / 1M tokens
- Output
- $0.03 / 1M tokens
- Context window
- 32,768 tokens
- Max output
- 32,768 tokens
- Providers
- 2
- Added to LiteLLM
- May 2025
Qwen2.5 Coder 3B Instruct pricing by provider
2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Nscale | nscale/Qwen/Qwen2.5-Coder-3B-Instruct | $0.01 | $0.03 | – |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct | $0.10 | $0.10 | 32K |
What Qwen2.5 Coder 3B Instruct costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Nscale | $0.035 |
| Fireworks AI | $0.25 |
Use Qwen2.5 Coder 3B Instruct with LiteLLM
Call Qwen2.5 Coder 3B Instruct through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="nscale/Qwen/Qwen2.5-Coder-3B-Instruct",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: qwen2.5-coder-3b-instruct
litellm_params:
model: nscale/Qwen/Qwen2.5-Coder-3B-Instruct
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "qwen2.5-coder-3b-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'Qwen2.5 Coder 3B Instruct FAQ
How much does Qwen2.5 Coder 3B Instruct cost?
Qwen2.5 Coder 3B Instruct costs $0.01 per 1M input tokens and $0.03 per 1M output tokens from Nscale, the lowest of 2 providers.
What is the context window of Qwen2.5 Coder 3B Instruct?
Qwen2.5 Coder 3B Instruct has a 32,768-token context window and returns up to 32,768 tokens per response.
Which providers offer Qwen2.5 Coder 3B Instruct?
Qwen2.5 Coder 3B Instruct is available from 2 providers through LiteLLM: Nscale and Fireworks AI. The lowest price is on Nscale.
How do I call Qwen2.5 Coder 3B Instruct with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="nscale/Qwen/Qwen2.5-Coder-3B-Instruct", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Qwen2.5 Coder 3B Instruct?
Qwen2.5 Coder 3B Instruct was added to LiteLLM's model price file in May 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: Nscale, Fireworks AI.
Provider pages: Nscale, Fireworks AI.
