novita
deepseek-ai/deepseek-r1-0528
Context
128K
Input
text
Output
text
Tool calling
Supported
About this model
DeepSeek-R1-0528 is an updated version of the DeepSeek-R1 reasoning model, featuring enhanced reasoning capabilities, improved mathematical problem-solving, and optimized inference performance while maintaining the 671B MoE architecture.
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": "87dff6f4d58e44fc82d854c46bbc46bd",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'Providers
Available routing options for this model through OneInfer.
novita
87dff6f4d58e44fc82d854c46bbc46bd
Input
$0.700 / 1M
Output
$2.500 / 1M
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Input tokens | $0.700 / 1M |
| Output tokens | $2.500 / 1M |
Performance
Published evaluation results associated with this model.
Advanced Reasoning
GPQA71.2
ARC-Challenge93.5
LogiQA91.3
ReClor87.8
BigBench-Hard85.7
Mathematical Reasoning
MATH81.4
GSM8K97.1
AIME70.3
Olympiad-Level Math62.8
Scientific Reasoning
TheoremQA75.9
ScienceQA93.2
Physics87.6
Chemistry84.5
Coding & Logical Proofs
HumanEval79.2
MBPP82.1
CodeContests71.8
ProofWriter86.9
Multilingual Reasoning
MGSM-Reasoning83.9
XStoryCloze89.1
XCOPA-Reasoning85.4
Long-Context Reasoning
LongBench-Reasoning82.7
NeedleInAHaystack-Reasoning96.3
MultiStep-Reasoning88.5
API example
curl https://api.oneinfer.ai/v1/chat/completions \
-H "Authorization: Bearer $ONEINFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "87dff6f4d58e44fc82d854c46bbc46bd",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'