Novita Pricing
Novita charges from $0.020 per 1 million output tokens, depending on the model. Llama 3.2 1B Instruct is the cheapest at $0.020/1M output and $0.020/1M input; its current flagship Hy4 preview costs $2.50/1M output. The largest context window is 1.0M tokens (DeepSeek DeepSeek V4 Flash). Prices are USD, current as of October 12, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.010/1M
BGE M3
Cheapest output
$0.020/1M
Llama 3.2 1B Instruct
Longest context
1.0M
DeepSeek DeepSeek V4 Flash
Models priced
209
Avg $1.63/1M output
Pricing by model
All prices in USD per 1 million tokens. Showing 80 of 209 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| BGE M3 | $0.010 | — | 8K |
| Llama 3.2 1B Instruct Tools | $0.020 | $0.020 | 131K |
| Meta Llama Llama 3.2 1B Instruct | $0.020 | $0.020 | 131K |
| PaddleOCR VL Vision | $0.020 | $0.020 | 16K |
| Paddlepaddle Paddleocr VL | $0.020 | $0.020 | 16K |
| DeepSeek DeepSeek Ocr | $0.030 | $0.030 | 8K |
| DeepSeek DeepSeek Ocr 2 | $0.030 | $0.030 | 8K |
| DeepSeek OCR 2 Vision | $0.030 | $0.030 | 8K |
| Qwen Qwen3 4B Fp8 | $0.030 | $0.030 | 128K |
| Meta Llama Llama 3 8B Instruct | $0.040 | $0.040 | 8K |
| Llama-3.1-8B-Instruct Tools | $0.020 | $0.050 | 16K |
| Meta Llama Llama 3.1 8B Instruct | $0.020 | $0.050 | 16K |
| Meta Llama Llama 3.2 3B Instruct | $0.030 | $0.050 | 33K |
| Sao10k L3 8B Lunaris | $0.050 | $0.050 | 8K |
| Sao10k L3 8B Stheno V3.2 | $0.050 | $0.050 | 8K |
| Baichuan Baichuan M2 32B | $0.070 | $0.070 | 131K |
| Baichuan M2 32B Reasoning | $0.070 | $0.070 | 131K |
| Qwen Qwen2.5 7B Instruct | $0.070 | $0.070 | 32K |
| DeepSeek DeepSeek R1 0528 Qwen3 8B | $0.060 | $0.090 | 128K |
| DeepSeek R1 0528 Qwen3 8B Reasoning | $0.060 | $0.090 | 128K |
| Gryphe Mythomax L2 13B | $0.090 | $0.090 | 4K |
| MythoMax L2 13B | $0.090 | $0.090 | 4K |
| Gemma 3 12B IT VisionTools | $0.050 | $0.100 | 131K |
| Google Gemma 3 12B It | $0.050 | $0.100 | 131K |
| AutoGLM Phone 9B Multilingual Vision | $0.035 | $0.138 | 66K |
| Qwen Qwen3 8B Fp8 | $0.035 | $0.138 | 128K |
| Zai Org Autoglm Phone 9B Multilingual | $0.035 | $0.138 | 66K |
| Hermes 2 Pro Llama 3 8B Tools | $0.140 | $0.140 | 8K |
| Nousresearch Hermes 2 Pro Llama 3 8B | $0.140 | $0.140 | 8K |
| DeepSeek DeepSeek R1 Distill Qwen 14B | $0.150 | $0.150 | 33K |
| OpenAI GPT Oss 20B | $0.040 | $0.150 | 131K |
| Mistralai Mistral Nemo | $0.040 | $0.170 | 60K |
| Inclusionai Ling 3.0 Flash | $0.060 | $0.180 | 262K |
| Inclusionai Ling 3.0 Flash Fast | $0.060 | $0.180 | 262K |
| Ling 3.0 Flash ReasoningToolsCache | $0.060 | $0.180 | 262K |
| Gemma 3 27B IT VisionTools | $0.119 | $0.200 | 98K |
| Google Gemma 3 27B It | $0.119 | $0.200 | 98K |
| Nemotron 3 Nano 30B A3B ReasoningTools | $0.050 | $0.200 | 262K |
| Nvidia Nemotron 3 Nano 30B A3b | $0.050 | $0.200 | 262K |
| Ling 3.0 Flash Fin ReasoningToolsCache | $0.075 | $0.220 | 262K |
| Ling 3.0 Flash Sante ReasoningToolsCache | $0.075 | $0.220 | 262K |
| Ling 3.0 Flash VL VisionReasoningToolsCache | $0.075 | $0.220 | 262K |
| GPT OSS 120B ReasoningTools | $0.050 | $0.250 | 131K |
| OpenAI GPT Oss 120B | $0.050 | $0.250 | 131K |
| Qwen Qwen3 Coder 30B A3b Instruct | $0.070 | $0.270 | 160K |
| Baidu Ernie 4.5 21B A3b | $0.070 | $0.280 | 120K |
| Baidu Ernie 4.5 21B A3b Thinking | $0.070 | $0.280 | 131K |
| DeepSeek DeepSeek V4 Flash | $0.140 | $0.280 | 1.0M |
| ERNIE 4.5 21B A3B Tools | $0.070 | $0.280 | 120K |
| MiMo-V2.6-Flash VisionReasoningToolsCache | $0.140 | $0.280 | 1.0M |
| DeepSeek DeepSeek R1 Distill Qwen 32B | $0.300 | $0.300 | 64K |
| Xiaomimimo Mimo V2 Flash | $0.110 | $0.330 | 262K |
| MiMo-V2.5 VisionReasoningToolsCache | $0.168 | $0.336 | 1.0M |
| Xiaomimimo Mimo V2.5 | $0.168 | $0.336 | 1.0M |
| Baidu Ernie 4.5 VL 28B A3b Thinking | $0.390 | $0.390 | 131K |
| DeepSeek DeepSeek V3.2 | $0.269 | $0.400 | 164K |
| Gemma 4 26B A4B IT VisionReasoningTools | $0.130 | $0.400 | 262K |
| Gemma 4 31B IT VisionReasoningTools | $0.140 | $0.400 | 262K |
| GLM-4.7-Flash ReasoningToolsCache | $0.070 | $0.400 | 200K |
| Google Gemma 4 26B A4b It | $0.130 | $0.400 | 262K |
| Google Gemma 4 31B It | $0.140 | $0.400 | 262K |
| Llama-3.3-70B-Instruct Tools | $0.135 | $0.400 | 12K |
| Meta Llama Llama 3.3 70B Instruct | $0.135 | $0.400 | 12K |
| Qwen Qwen 2.5 72B Instruct | $0.380 | $0.400 | 32K |
| Zai Org Glm 4.7 Flash | $0.070 | $0.400 | 200K |
| DeepSeek DeepSeek V3.2 Exp | $0.270 | $0.410 | 164K |
| Qwen Qwen3 30B A3b Fp8 | $0.090 | $0.450 | 41K |
| Qwen Qwen3 32B Fp8 | $0.100 | $0.450 | 41K |
| Qwen3.8 Flash VisionReasoningToolsCache | $0.150 | $0.470 | 1.0M |
| GLM-5.3-Flash VisionReasoningToolsCache | $0.150 | $0.500 | 1.0M |
| Qwen Qwen3 VL 8B Instruct | $0.080 | $0.500 | 131K |
| Baidu Ernie 4.5 VL 28B A3b | $0.140 | $0.560 | 30K |
| Hy3 ReasoningToolsCache | $0.140 | $0.580 | 262K |
| Qwen Qwen3 235B A22b Instruct 2507 | $0.090 | $0.580 | 131K |
| Tencent Hy3 | $0.140 | $0.580 | 262K |
| Llama 4 Scout 17B Instruct VisionTools | $0.180 | $0.590 | 131K |
| Meta Llama Llama 4 Scout 17B 16e Instruct | $0.180 | $0.590 | 131K |
| Skywork R1v4 Lite | $0.200 | $0.600 | 262K |
| Microsoft Wizardlm 2 8X22B | $0.620 | $0.620 | 66K |
| Moonshotai Kimi K3 | $3.00 | $15.00 | 1.0M |
Frequently asked questions
How much does Novita cost per 1M tokens?
Novita pricing starts at $0.020 per 1 million output tokens (Llama 3.2 1B Instruct) across 209 models, with its current flagship Hy4 preview at $2.50. Older premium models in the catalog list higher. Rates current as of October 12, 2026.
What is the cheapest Novita model?
Llama 3.2 1B Instruct is the cheapest Novita model on output tokens at $0.020 per 1M, while BGE M3 is cheapest on input at $0.010 per 1M. Which wins for you depends on your input-to-output ratio.
What is the largest Novita context window?
DeepSeek DeepSeek V4 Flash has the largest context window in the Novita catalog at 1.0M input tokens, with up to 393K output tokens per response.
Does Novita support prompt caching?
Yes. MiMo-V2.6-Flash reads cached input at $0.0028 per 1M tokens, against $0.140 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.
Which Novita models support reasoning or vision?
The Novita catalog includes 59 reasoning models, 34 vision models, 70 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.
How do I calculate my actual Novita bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator