novita
qwen/qwen3-coder-next
Context
262K
Input
text
Output
text
Tool calling
Supported
About this model
Qwen3-Coder-Next is a coding-focused language model optimized for agentic coding workflows and local development. Built on a novel hybrid attention and MoE architecture, it has been agentically trained at scale with large-scale executable task synthesis and environment interaction. It runs natively in non-thinking mode for ultra-quick code responses.
Capabilities
text
Available through the unified API
Quick start
View API docscurl https://api.oneinfer.ai/v1/chat/completions \
-H "Authorization: Bearer $ONEINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "1e972bd902a74b61b279e6ad4927b36b",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'Providers
Available routing options for this model through OneInfer.
novita
1e972bd902a74b61b279e6ad4927b36b
Input
$0.200 / 1M
Output
$1.500 / 1M
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Input tokens | $0.200 / 1M |
| Output tokens | $1.500 / 1M |
Performance
Published evaluation results associated with this model.
Coding
SWE-Bench Verified74.8
SWE-Bench Multilingual66.2
SWE-Bench Pro44.3
Terminal-Bench 2.039.3
API example
curl https://api.oneinfer.ai/v1/chat/completions \
-H "Authorization: Bearer $ONEINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "1e972bd902a74b61b279e6ad4927b36b",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'