Novita AI API pay-as-you-go

Understand the fit and limits

Entitlements and usage

Allowance

Billed by model and usage; no fixed monthly allowance

Benefits

Access models from multiple developers with documented OpenAI-compatible integration.

Models listed in source

GLM 5.3 Flash, MiMo V2.6 Flash, MiMo V2.6 Pro, Hy4 Preview, DeepSeek V4.1 Flash, GLM 5.3, DeepSeek V4 Pro 0813, Kimi K3, Hy3, GLM 5.2, Kimi K2.7 Code, Qwen3.8 Flash, DeepSeek V4 Flash 0731, Macaron V1 Venti, MiniMax M3, DeepSeek V4 Pro, Apodex 1.1 Mini, Step 5 Preview, Ling 3.1 Flash, Qwen3.8 27B, Ling 3.0 Flash Fin, Qwen3.8 2.4T A95B, Qwen3.8 Max, Ling 3.0 Flash, Macaron V1 Tall, Step 3.7 Flash, NVIDIA Nemotron 3 Nano 30B A3B, CoBuddy, Qwen3.7 Max, Qwen3.6 27B, Kimi K2.6, GLM 5.1, Gemma 4 26B A4B, Gemma 4 31B, MiniMax M2.7, Qwen3.5 27B, Qwen3.5 122B A10B, Qwen3.5 35B A3B, Qwen3.5 397B A17B, MiniMax M2.5, GLM 5, DeepSeek OCR 2, Kimi K2.5, GLM 4.7 Flash, GLM 4.7, AutoGLM Phone 9B Multilingual, Kimi K2 Thinking, GLM 4.6V, GLM 4.6, Qwen3.6 35B A3B, Kimi K2 Instruct 0905, OpenAI GPT OSS 120B, Kimi K2 Instruct, Llama 3.1 8B Instruct, GLM 4.5V, Llama 3.3 70B Instruct, MiniMax M1, DeepSeek R1 0528, WizardLM 2 8x22B, Llama 4 Maverick Instruct, Llama 4 Scout Instruct, Gemma 3 27B, DeepSeek R1 Turbo, Llama 3 8B Stheno V3.2, Ling 3.0 Flash VL, Ling 3.0 Flash Sante, GLM 4.5 Air, Qwen3 VL 30B A3B Instruct, Qwen3 Omni 30B A3B Thinking, Qwen MT Plus, ERNIE 4.5 21B A3B

Tool compatibility and access

openai sdk: OpenAI-compatible — Use a Novita AI API key and follow the official LLM API configuration.

Source notes and limits

Prepaid usage billing; manual top-ups must exceed $10. Credit purchases are not monthly fees. Input, output and cache reads follow each model rate; MiniMax M3 uses length tiers and Qwen3 Omni uses modality-specific rates. Dedicated Endpoints, Sandbox and GPUs are billed separately.

API input and output pricing