NovitaAI API
NovitaAI's OpenAI-compatible large language models
Data & Privacy
HQ:US
Safety identifier:Not forwarded
API Training:No
Prompt Logging:No
Retention:0 days
Available Models
MiniMax M3.1 Flash
minimax
minimax-m3.1-flashStreaming
Vision
Tools
Reasoning
NovitaAI
Context: 1M
Input
$0.15
/M tokens
Cached
$0.015
/M tokens
Output
$0.6
/M tokens
DeepSeek V4.1 Flash 1017
deepseek
deepseek-v4.1-flash-1017Streaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 1.0M
Input
$0.3
/M tokens
Cached
$0.006
/M tokens
Output
$1.2
/M tokens
DeepSeek V4.1 Flash
deepseek
deepseek-v4.1-flashStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 1.0M
Input
$0.3
/M tokens
Cached
$0.006
/M tokens
Output
$1.2
/M tokens
Qwen3.8 Flash
alibaba
qwen3.8-flashStreaming
Tools
Reasoning
JSON Output
JSON Schema
NovitaAI
Context: 1M
Input
$0.15
/M tokens
Cached
$0.016
/M tokens
Output
$0.47
/M tokens
GLM-5.3 Flash
zai
glm-5.3-flashStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 1.0MQuant: fp8
Input
$0.15
/M tokens
Cached
$0.03
/M tokens
Output
$0.5
/M tokens
Qwen3.8 27B
alibaba
qwen3.8-27bStreaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 1M
Input
$0.42
/M tokens
Cached
$0.085
/M tokens
Output
$3
/M tokens
GLM-5.3
zai
glm-5.3Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 1.0M
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Qwen3.8 2.4T A95B
alibaba
qwen3.8-2.4t-a95bStreaming
Tools
Reasoning
JSON Output
JSON Schema
NovitaAI
Context: 1M
Input
$2
/M tokens
Cached
$0.25
/M tokens
Output
$6
/M tokens
Ling 3.0 Flash
inclusionai
ling-3.0-flashStreaming
Tools
Reasoning
NovitaAI
Context: 262.1k
Input
$0.06
/M tokens
Cached
$0.012
/M tokens
Output
$0.18
/M tokens
Qwen3.8 Max
alibaba
qwen3.8-maxStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
NovitaAI
Context: 1M
Input
$2
/M tokens
Cached
$0.25
/M tokens
Output
$6
/M tokens
Kimi K3
moonshotPremium
kimi-k3Streaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 1.0M
Input
$3
/M tokens
Cached
$0.3
/M tokens
Output
$15
/M tokens
Hy3
tencent
hy3Streaming
Tools
Reasoning
JSON Schema
NovitaAI
Context: 262.1k
Input
$0.14
/M tokens
Cached
$0.035
/M tokens
Output
$0.58
/M tokens
GLM-5.2
zai
glm-5.2Streaming
Tools
Reasoning
NovitaAI
Context: 1.0M
Input
$1.4
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Kimi K2.7 Code
moonshot
kimi-k2.7-codeStreaming
Vision
Tools
Reasoning
JSON Output
JSON Schema
NovitaAI
Context: 262.1k
Input
$0.95
/M tokens
Cached
$0.19
/M tokens
Output
$4
/M tokens
Step 3.7 Flash
stepfun
step-3.7-flashStreaming
Vision
Tools
Reasoning
NovitaAI
Context: 262.1kQuant: fp8
Input
$0.2
/M tokens
Cached
$0.04
/M tokens
Output
$1.15
/M tokens
Qwen3.7 Max
alibaba
qwen3.7-maxStreaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 1M
Input
$1.25
/M tokens
Cached
$0.25
/M tokens
Output
$3.75
/M tokens
Qwen3.6 35B A3B
alibaba
qwen3.6-35b-a3bStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 262.1k
Input
$0.248
/M tokens
Cached
—
/M tokens
Output
$1.485
/M tokens
DeepSeek V4 Flash
deepseek
deepseek-v4-flashStreaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 1.1MQuant: fp8
Input
$0.14
/M tokens
Cached
$0.028
/M tokens
Output
$0.28
/M tokens
Kimi K2.6
moonshot
kimi-k2.6Streaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 262.1k
Input
$0.8
/M tokens
Cached
$0.16
/M tokens
Output
$3.4
/M tokens
GLM-5.1
zai
glm-5.1Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 204.8kQuant: fp8
Input
$1.38
/M tokens
Cached
$0.26
/M tokens
Output
$4.4
/M tokens
Gemma 4 31B IT
google
gemma-4-31b-itStreaming
Tools
JSON Output
NovitaAI
Context: 262.1kQuant: bf16
Input
$0.14
/M tokens
Cached
—
/M tokens
Output
$0.4
/M tokens
Gemma 4 26B A4B IT
google
gemma-4-26b-a4b-itStreaming
Tools
JSON Output
NovitaAI
Context: 262.1kQuant: bf16
Input
$0.13
/M tokens
Cached
—
/M tokens
Output
$0.4
/M tokens
MiniMax M2.7
minimax
minimax-m2.7Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 204.8kQuant: fp8
Input
$0.3
/M tokens
Cached
$0.06
/M tokens
Output
$1.2
/M tokens
Qwen3.5 122B A10B
alibaba
qwen3.5-122b-a10bStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 262.1kQuant: bf16
Input
$0.4
/M tokens
Cached
—
/M tokens
Output
$3.2
/M tokens
Qwen3.5 397B A17B
alibaba
qwen35-397b-a17bStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 262.1k
Input
$0.6
/M tokens
Cached
—
/M tokens
Output
$3.6
/M tokens
MiniMax M2.5
minimax
minimax-m2.5Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 204.8kQuant: fp8
Input
$0.3
/M tokens
Cached
$0.03
/M tokens
Output
$1.2
/M tokens
GLM-5
zai
glm-5Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 202.8kQuant: fp8
Input
$1
/M tokens
Cached
$0.2
/M tokens
Output
$3.2
/M tokens
GLM-4.7
zai
glm-4.7Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 204.8kQuant: fp8
Input
$0.6
/M tokens
Cached
$0.11
/M tokens
Output
$2.2
/M tokens
GLM-4.6V
zai
glm-4.6vStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 131.1kQuant: bf16
Input
$0.3
/M tokens
Cached
$0.055
/M tokens
Output
$0.9
/M tokens
Qwen3 VL 30B A3B Instruct
alibaba
qwen3-vl-30b-a3b-instructStreaming
Vision
Tools
NovitaAI
Context: 131.1kQuant: bf16
Input
$0.2
/M tokens
Cached
—
/M tokens
Output
$0.7
/M tokens
GLM-4.6
zai
glm-4.6Streaming
Tools
Reasoning
JSON Output
NovitaAI
Context: 204.8kQuant: bf16
Input
$0.55
/M tokens
Cached
$0.11
/M tokens
Output
$2.2
/M tokens
GLM-4.5V
zai
glm-4.5vStreaming
Vision
Tools
Reasoning
JSON Output
NovitaAI
Context: 65.5kQuant: fp8
Input
$0.6
/M tokens
Cached
$0.11
/M tokens
Output
$1.8
/M tokens
Kimi K2
moonshot
kimi-k2Streaming
Tools
NovitaAI
Context: 131.1kQuant: fp8
Input
$0.57
/M tokens
Cached
—
/M tokens
Output
$2.3
/M tokens
Llama 4 Scout 17B Instruct
meta
llama-4-scout-17b-instructStreaming
Vision
JSON Output
NovitaAI
Context: 131.1kQuant: bf16
Input
$0.18
/M tokens
Cached
—
/M tokens
Output
$0.59
/M tokens
Llama 4 Maverick 17B Instruct
meta
llama-4-maverick-17b-instructStreaming
Vision
JSON Output
NovitaAI
Context: 1.0MQuant: fp8
Input
$0.27
/M tokens
Cached
—
/M tokens
Output
$0.85
/M tokens
Llama 3.3 70B Instruct
meta
llama-3.3-70b-instructStreaming
Tools
NovitaAI
Context: 131.1kQuant: bf16
Input
$0.135
/M tokens
Cached
—
/M tokens
Output
$0.4
/M tokens
Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to minimax-m3.1-flash. On pay-as-you-go keys, novita/minimax-m3.1-flash pins every request to NovitaAI; DevPass coding plans do not support provider pinning. You do not need a separate NovitaAI account or SDK.