NO
Novita AI
Aggregator Featured
Budget AI inference platform with broad model catalog across LLM, image, video, and audio. Very competitive per-token pricing.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per token Free tier: Available
Details
Models 92
API Base
https://api.novita.ai/v3/openai Audio / MusicImage GenerationLLM InferenceVideo Generation
Model Catalog (92)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| DeepSeek R1 0528 DeepSeek · 671B MoE | llm | $0.700 | $2.50 | — | — | |
| DeepSeek V3 DeepSeek · 671B MoE | llm | $0.270 | $1.12 | — | — | |
| DeepSeek V3.1 DeepSeek · 671B MoE | llm | $0.270 | $1.00 | — | — | |
| DeepSeek V3.2 DeepSeek · 671B MoE (37B active) | llm | $0.269 | $0.400 | — | — | |
| DeepSeek V4 Flash DeepSeek | llm | $0.140 | $0.280 | — | — | |
| DeepSeek V4 Flash DeepSeek 0731 | llm | $0.440 | $1.32 | 1.0M | — | |
| DeepSeek V4 Pro DeepSeek | llm | $1.60 | $3.20 | — | — | |
| DeepSeek V4 Pro DeepSeek 0813 | llm | $1.32 | $3.96 | 1.0M | — | |
| DeepSeek V4.1 Flash DeepSeek | llm | $0.300 | $1.20 | 1.0M | — | |
| Flux Kontext Dev Black Forest Labs | image gen | $0.022/img | — | — | — | |
| Flux Kontext Max Black Forest Labs | image gen | $0.072/img | — | — | — | |
| Flux Kontext Pro Black Forest Labs | image gen | $0.036/img | — | — | — | |
| GLM 4.5 Zhipu AI · 106B MoE (12B active) | llm | $0.600 | $2.20 | — | — | |
| GLM 4.5 Air Z.ai | llm | $0.130 | $0.850 | 131k | — | |
| GLM 4.5V Z.ai | multimodal | $0.600 | $1.80 | 66k | — | |
| GLM 4.6 Zhipu AI · 355B | llm | $0.550 | $2.20 | — | — | |
| GLM 4.6V Z.ai | multimodal | $0.300 | $0.900 | 131k | — | |
| GLM 4.7 Zhipu AI | llm | $0.600 | $2.20 | — | — | |
| GLM 4.7 Flash Z.ai | llm | $0.070 | $0.400 | — | — | |
| GLM 5 Zhipu AI · 744B | llm | $1.00 | $3.20 | — | — | |
| GLM 5 Turbo Z.ai | llm | $1.20 | $4.00 | 203k | — | |
| GLM 5.1 Z.ai · 744B MoE (40B active) | llm | $1.38 | $4.40 | — | — | |
| GLM 5.2 Z.ai | llm | $1.40 | $4.40 | — | — | |
| GLM 5.3 Z.ai | llm | $1.40 | $4.40 | 1.0M | — | |
| GLM 5.3 Flash Z.ai | llm | $0.150 | $0.500 | 1.0M | — | |
| GLM 5V Turbo Z.ai | multimodal | $1.20 | $4.00 | 205k | — | |
| GPT OSS 120B OpenAI · 117B MoE (5.1B active) | llm | $0.050 | $0.250 | 131k | — | |
| Gemma 3 12B Google · 12B | llm | $0.050 | $0.100 | 131k | — | |
| Gemma 3 27B Google · 27B | llm | $0.119 | $0.200 | — | — | |
| Gemma 4 26B A4B Google | llm | $0.130 | $0.400 | 262k | — | |
| Gemma 4 31B Google · 27B | llm | $0.140 | $0.400 | — | — | |
| Hailuo 02 MiniMax | video gen | $0.250/req | — | — | — | |
| Hailuo 2.3 MiniMax | video gen | $0.190/req | — | — | — | |
| HunyuanImage 3.0 Tencent | image gen | $0.100/img | — | — | — | |
| HunyuanVideo 1.5 Tencent | video gen | $0.300/req | — | — | — | |
| Hy3 Tencent | llm | $0.140 | $0.580 | 262k | — | |
| Hy4 Preview Tencent | llm | $0.834 | $2.50 | 1M | — | |
| Kimi K2 Moonshot AI · 1T MoE (32B active) | llm | $0.570 | $2.30 | — | — | |
| Kimi K2 Thinking Moonshot AI · 1T MoE (32B active) | llm | $0.600 | $2.50 | 262k | — | |
| Kimi K2.5 Moonshot AI · 1T MoE (32B active) | llm | $0.600 | $3.00 | — | — | |
| Kimi K2.6 Moonshot AI · 1T MoE (32B active) | llm | $0.800 | $3.40 | — | — | |
| Kimi K2.7 Code Moonshot AI · 1T MoE (32B active) | code | $0.950 | $4.00 | — | — | |
| Kimi K3 Moonshot AI | llm | $3.00 | $15.00 | 1.0M | — | |
| Kling 2.5 Turbo Kuaishou | video gen | $0.350/req | — | — | — | |
| Kling 2.6 Kuaishou | video gen | $0.350/req | — | — | — | |
| Kling 3.0 Kuaishou | video gen | $0.084/sec | — | — | — | |
| Llama 3.1 8B Instruct Meta | llm | $0.020 | $0.050 | — | — | |
| Llama 3.2 1B Instruct Meta | llm | $0.020 | $0.020 | 131k | — | |
| Llama 3.3 70B Meta · 70B | llm | $0.135 | $0.400 | — | — | |
| Llama 4 Maverick Meta · 400B (17B active) | llm | $0.270 | $0.850 | — | — | |
| Llama 4 Scout Meta · 109B (17B active) | llm | $0.180 | $0.590 | — | — | |
| MiMo V2.5 Xiaomi | llm | $0.168 | $0.336 | 1.0M | — | |
| MiMo V2.5 Pro Xiaomi | llm | $0.522 | $1.04 | 1.0M | — | |
| MiMo V2.6 Flash Xiaomi | llm | $0.140 | $0.280 | 1.0M | — | |
| MiMo V2.6 Pro Xiaomi | llm | $0.435 | $0.870 | 1.0M | — | |
| MiniMax M1 MiniMax | llm | $0.550 | $2.20 | — | — | |
| MiniMax M2 MiniMax | llm | $0.300 | $1.20 | 205k | — | |
| MiniMax M2.1 MiniMax | llm | $0.300 | $1.20 | 205k | — | |
| MiniMax M2.5 MiniMax | llm | $0.300 | $1.20 | — | — | |
| MiniMax M2.7 MiniMax | llm | $0.300 | $1.20 | — | — | |
| MiniMax M3 MiniMax | llm | $0.300 | $1.20 | 1M | — | |
| Qwen 3 235B Alibaba · 235B MoE | llm | $0.200 | $0.800 | — | — | |
| Qwen 3 32B Alibaba · 32B | llm | $0.100 | $0.450 | — | — | |
| Qwen 3 Max Alibaba | llm | $2.11 | $8.45 | — | — | |
| Qwen 3.5 122B Alibaba · 122B MoE (10B active) | llm | $0.400 | $3.20 | — | — | |
| Qwen 3.5 35B Alibaba · 35B MoE (3B active) | llm | $0.250 | $2.00 | — | — | |
| Qwen 3.5 397B Alibaba · 397B MoE (17B active) | llm | $0.600 | $3.60 | — | — | |
| Qwen Image Alibaba | image gen | $0.020/img | — | — | — | |
| Qwen3 235B A22B Thinking 2507 Alibaba | llm | $0.300 | $3.00 | 131k | — | |
| Qwen3 Coder 30B A3B Instruct Alibaba | code | $0.070 | $0.270 | 160k | — | |
| Qwen3 Coder 480B A35B Alibaba | code | $0.380 | $1.55 | 262k | — | |
| Qwen3 Coder Next Alibaba | code | $0.200 | $1.50 | 262k | — | |
| Qwen3 Next 80B A3B Instruct Alibaba | llm | $0.150 | $1.50 | 131k | — | |
| Qwen3 VL 235B A22B Instruct Alibaba | multimodal | $0.300 | $1.50 | 131k | — | |
| Qwen3 VL 235B A22B Thinking Alibaba | multimodal | $0.980 | $3.95 | 131k | — | |
| Qwen3 VL 30B A3B Instruct Alibaba | multimodal | $0.200 | $0.700 | 131k | — | |
| Qwen3.5-27B Alibaba | llm | $0.300 | $2.40 | 262k | — | |
| Qwen3.6 27B Alibaba | llm | $0.600 | $3.60 | 262k | — | |
| Qwen3.6 35B A3B Alibaba | llm | $0.248 | $1.49 | 262k | — | |
| Qwen3.7 Max Alibaba | llm | $1.25 | $3.75 | — | — | |
| Qwen3.8 2.4T A95B Alibaba | llm | $2.00 | $6.00 | 1M | — | |
| Qwen3.8 27B Alibaba | llm | $0.420 | $3.00 | 1M | — | |
| Qwen3.8 Flash Alibaba | llm | $0.150 | $0.470 | 1M | — | |
| Qwen3.8 Max Alibaba | llm | $2.00 | $6.00 | 1M | — | |
| Seedance 1.0 ByteDance | video gen | $0.080/req | — | — | — | |
| Seedream 3.0 ByteDance | image gen | $0.030/img | — | — | — | |
| Seedream 4.0 ByteDance | image gen | $0.030/img | — | — | — | |
| Vidu Q2 Vidu | video gen | $0.080/req | — | — | — | |
| Vidu V2.0 Vidu | video gen | $0.090/req | — | — | — | |
| Wan 2.5 Alibaba | video gen | $0.250/req | — | — | — | |
| Wan 2.6 Alibaba | video gen | $0.500/req | — | — | — | |
| gpt-oss-20b OpenAI | llm | $0.040 | $0.150 | 131k | — |
Novita AI API FAQ
Is the Novita AI API free?
Yes, Novita AI has a free tier. Paid usage is billed per model.
What is the cheapest Novita AI model?
Llama 3.1 8B Instruct at $0.02 in / $0.05 out per 1M tokens, based on the 92 models we track for Novita AI.
How many models does Novita AI offer?
We track 92 Novita AI models: 64 LLM, 11 video generation, 7 image generation, 6 multimodal, 4 coding.
Is the Novita AI API OpenAI-compatible?
Yes. Novita AI exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.