LiteLLMModels

Qwen3 Coder Next API Pricing

As of October 10, 2026, Qwen3 Coder Next costs $0.137 per 1M input tokens and $0.548 per 1M output tokens from AIHubMix, the lowest of 4 providers. It has a 262,144-token context window and returns up to 65,536 tokens per response.

By AlibabaModel ID aihubmix/qwen3-coder-nextPrices updated Checked
Input
$0.137 / 1M tokens
Output
$0.548 / 1M tokens
Context window
262,144 tokens
Max output
65,536 tokens
Providers
4
Added to LiteLLM
February 2026

Qwen3 Coder Next pricing by provider

15 listings across 4 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
AIHubMixaihubmix/qwen3-coder-next$0.137$0.548256K
Amazon Bedrockqwen.qwen3-coder-next$0.50$1.20256K
Novita AInovita/qwen/qwen3-coder-next$0.20$1.50256K
Amazon Bedrockap-northeast-1bedrock/ap-northeast-1/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockap-south-1bedrock/ap-south-1/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockap-southeast-3bedrock/ap-southeast-3/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockeu-central-1bedrock/eu-central-1/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockeu-south-1bedrock/eu-south-1/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockeu-west-1bedrock/eu-west-1/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockeu-west-2bedrock/eu-west-2/qwen.qwen3-coder-next$0.78$1.86256K
Amazon Bedrocksa-east-1bedrock/sa-east-1/qwen.qwen3-coder-next$0.60$1.44256K
Amazon Bedrockus-east-1bedrock/us-east-1/qwen.qwen3-coder-next$0.50$1.20256K
Amazon Bedrockus-east-2bedrock/us-east-2/qwen.qwen3-coder-next$0.50$1.20256K
Amazon Bedrockus-west-2bedrock/us-west-2/qwen.qwen3-coder-next$0.50$1.20256K
Together AIfp8together_ai/Qwen/Qwen3-Coder-Next-FP8$0.50$1.20256K

What Qwen3 Coder Next costs in practice

1,000 requests with 2,000 input and 500 output tokens each

AIHubMix$0.548
Novita AI$1.15
Amazon Bedrock$1.60

100 long-document requests with 100,000 input and 2,000 output tokens each

AIHubMix$1.48
Novita AI$2.30
Amazon Bedrock$5.24

Qwen3 Coder Next features

Use Qwen3 Coder Next with LiteLLM

Call Qwen3 Coder Next 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.

Python SDK
from litellm import completion

response = completion(
    model="aihubmix/qwen3-coder-next",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: qwen3-coder-next
    litellm_params:
      model: aihubmix/qwen3-coder-next
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen3-coder-next",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen3 Coder Next FAQ

How much does Qwen3 Coder Next cost?

Qwen3 Coder Next costs $0.137 per 1M input tokens and $0.548 per 1M output tokens from AIHubMix, the lowest of 4 providers.

What is the context window of Qwen3 Coder Next?

Qwen3 Coder Next has a 262,144-token context window and returns up to 65,536 tokens per response.

Which providers offer Qwen3 Coder Next?

Qwen3 Coder Next is available from 4 providers through LiteLLM: AIHubMix, Amazon Bedrock, Novita AI and Together AI. The lowest price is on AIHubMix.

How do I call Qwen3 Coder Next with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="aihubmix/qwen3-coder-next", 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.

What features does Qwen3 Coder Next support?

Qwen3 Coder Next supports function calling and structured output.

When did LiteLLM add Qwen3 Coder Next?

Qwen3 Coder Next was added to LiteLLM's model price file in February 2026.

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: AIHubMix, Amazon Bedrock, Together AI.

Provider pages: AIHubMix, Amazon Bedrock, Novita AI, Together AI.