novita
qwen/qwen3-next-80b-a3b-thinking
Context
128K
Input
text
Output
text
Tool calling
Supported
About this model
Qwen3-Next-80B-A3B-Thinking is Alibaba's advanced reasoning-focused Mixture of Experts model featuring enhanced chain-of-thought capabilities, specialized for complex problem-solving, mathematical reasoning, and step-by-step logical deduction with 80B total parameters and 3B active experts per token.
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": "e1da19477ae441a49d6fb748ad7401a0",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'Providers
Available routing options for this model through OneInfer.
novita
e1da19477ae441a49d6fb748ad7401a0
Input
$0.150 / 1M
Output
$1.500 / 1M
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Input tokens | $0.150 / 1M |
| Output tokens | $1.500 / 1M |
Performance
Published evaluation results associated with this model.
Advanced Reasoning
GPQA69.8
ARC-Challenge91.7
LogiQA88.4
ReClor84.2
BigBench-Hard86.3
Mathematical Reasoning
MATH76.8
GSM8K95.3
AIME63.7
Olympiad-Level57.9
Theorem-Proving52.4
Scientific Reasoning
TheoremQA74.2
ScienceQA90.8
Physics83.6
Chemistry79.8
Biology85.1
Code & Logical Proofs
HumanEval78.9
MBPP76.4
CodeContests67.3
ProofWriter83.7
Formal-Verification71.5
Thinking Process
Step-Accuracy92.8
Logical-Consistency90.5
Error-Correction87.9
Multi-Step-Planning89.3
Reasoning-Transparency88.6
Long-Context Reasoning
Complex-Problem-Length94.7
Contextual-Reasoning86.9
Information-Synthesis83.4
Multi-Document-Analysis79.8
API example
curl https://api.oneinfer.ai/v1/chat/completions \
-H "Authorization: Bearer $ONEINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "e1da19477ae441a49d6fb748ad7401a0",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'