Qwen3 Coder Next
qwen/qwen3-coder-nextQwen3 Coder Next is an open-weight coding model built on Qwen3-Next-80B-A3B-Base (hybrid attention + MoE). It is agentically trained at scale on executable tasks and environment interaction, delivering strong coding and tool-use performance at lower inference cost. Native 256K context.
- Tool calling
- Structured output
Pricing
Includes our margin. Charged per request from your balance.
- Input
- $0.132 per 1M tokens
- Output
- $0.88 per 1M tokens
- Cache read
- $0.077 per 1M tokens
- Typical message
- $0.00093
Details
- Provider
- Qwen
- Context
- 262K tokens
- Max output
- 66K tokens
- Added
- Dec 8, 2025
Use it from the API
Replace $HIDE_API_KEY with a key from the Developers page. Base URL https://hide.st/api/v1.
curl https://hide.st/api/v1/chat/completions \
-H "Authorization: Bearer $HIDE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-coder-next",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'