Novita LLM API pricing

Every model Novita serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

129

on this provider

Cheapest input

$0.02

per 1M tokens

Cheapest output

$0.02

per 1M tokens

Max context

10.5M

tokens

Model ID
Llama 3.2 1B InstructMeta131K$0.02$0.02novita/meta-llama/llama-3.2-1b-instruct
Llama 3.1 8B InstructMeta200K$0.02$0.05novita/meta-llama/llama-3.1-8b-instruct
Paddleocr VLOther16K$0.02$0.02novita/paddlepaddle/paddleocr-vl
DeepSeek Ocr 2DeepSeek8K$0.03$0.03novita/deepseek/deepseek-ocr-2
Qwen3 4B FP8Alibaba128K$0.03$0.03novita/qwen/qwen3-4b-fp8
Llama 3.2 3B InstructMeta131K$0.03$0.05novita/meta-llama/llama-3.2-3b-instruct
DeepSeek OcrDeepSeek8K$0.03$0.03novita/deepseek/deepseek-ocr
Qwen3 8B FP8Alibaba128K$0.04$0.14novita/qwen/qwen3-8b-fp8
Autoglm Phone 9B MultilingualZhipu66K$0.04$0.14novita/zai-org/autoglm-phone-9b-multilingual
Llama 3 8B InstructMeta8K$0.04$0.04novita/meta-llama/llama-3-8b-instruct
gpt-oss-20bOpenAI131K$0.04$0.15novita/openai/gpt-oss-20b
Mistral NemoMistral131K$0.04$0.17novita/mistralai/mistral-nemo
Nemotron 3 Nano 30B A3BNVIDIA262K$0.05$0.20novita/nvidia/nemotron-3-nano-30b-a3b
Gemma 3 12BGoogle131K$0.05$0.10novita/google/gemma-3-12b-it
L3 8B Stheno V3 2Other8K$0.05$0.05novita/Sao10K/L3-8B-Stheno-v3.2
gpt-oss-120bOpenAI131K$0.05$0.25novita/openai/gpt-oss-120b
L3 8B LunarisOther8K$0.05$0.05novita/sao10k/l3-8b-lunaris
Ling 3.0 Flash FastOther262K$0.06$0.18novita/inclusionai/ling-3.0-flash-fast
Ling-3.0-flashOther262K$0.06$0.18novita/inclusionai/ling-3.0-flash
DeepSeek R1 0528 Qwen3 8BDeepSeek128K$0.06$0.09novita/deepseek/deepseek-r1-0528-qwen3-8b
GLM 4.7 FlashZhipu203K$0.07$0.40novita/zai-org/glm-4.7-flash
Ernie 4.5 21B A3bBaidu120K$0.07$0.28novita/baidu/ernie-4.5-21B-a3b
Qwen3 Coder 30B A3B InstructAlibaba262K$0.07$0.27novita/qwen/qwen3-coder-30b-a3b-instruct
Ernie 4.5 21B A3b ThinkingBaidu131K$0.07$0.28novita/baidu/ernie-4.5-21B-a3b-thinking
Qwen2 5 7B InstructAlibaba33K$0.07$0.07novita/qwen/qwen2.5-7b-instruct
Baichuan M2 32BOther131K$0.07$0.07novita/baichuan/baichuan-m2-32b
Qwen3 VL 8B InstructAlibaba131K$0.08$0.50novita/qwen/qwen3-vl-8b-instruct
Qwen3 30B A3b FP8Alibaba41K$0.09$0.45novita/qwen/qwen3-30b-a3b-fp8
Qwen3 235B A22b Instruct 2507Alibaba262K$0.09$0.58novita/qwen/qwen3-235b-a22b-instruct-2507
MythoMax 13BOther4K$0.09$0.09novita/gryphe/mythomax-l2-13b
Qwen3 32B FP8Alibaba131K$0.10$0.45novita/qwen/qwen3-32b-fp8
Mimo V2 FlashXiaomi262K$0.11$0.33novita/xiaomimimo/mimo-v2-flash
Gemma 3 27BGoogle131K$0.12$0.20novita/google/gemma-3-27b-it
GLM 4.5 AirZhipu131K$0.13$0.85novita/zai-org/glm-4.5-air
Gemma 4 26B A4B Google262K$0.13$0.40novita/google/gemma-4-26b-a4b-it
Llama 3.3 70B InstructMeta131K$0.14$0.40novita/meta-llama/llama-3.3-70b-instruct
Hy3Other262K$0.14$0.58novita/tencent/hy3
DeepSeek V4 Flash 0423DeepSeek1M$0.14$0.28novita/deepseek/deepseek-v4-flash
Gemma 4 31BGoogle262K$0.14$0.40novita/google/gemma-4-31b-it
Ernie 4.5 VL 28B A3bBaidu30K$0.14$0.56novita/baidu/ernie-4.5-vl-28b-a3b
Hermes 2 Pro Llama 3 8BNous Research8K$0.14$0.14novita/nousresearch/hermes-2-pro-llama-3-8b
DeepSeek R1 Distill Qwen 14BDeepSeek131K$0.15$0.15novita/deepseek/deepseek-r1-distill-qwen-14b
Qwen3 Next 80B A3B ThinkingAlibaba262K$0.15$1.50novita/qwen/qwen3-next-80b-a3b-thinking
Qwen3 Next 80B A3B InstructAlibaba262K$0.15$1.50novita/qwen/qwen3-next-80b-a3b-instruct
MiMo-V2.5Xiaomi1M$0.17$0.34novita/xiaomimimo/mimo-v2.5
Llama 4 Scout 17B 16e InstructMeta10.5M$0.18$0.59novita/meta-llama/llama-4-scout-17b-16e-instruct
Step 3.7 FlashOther262K$0.20$1.15novita/stepfun/step-3.7-flash
Qwen3 Coder NextAlibaba262K$0.20$1.50novita/qwen/qwen3-coder-next
Qwen3 235B A22b FP8Alibaba41K$0.20$0.80novita/qwen/qwen3-235b-a22b-fp8
R1v4 LiteOther262K$0.20$0.60novita/skywork/r1v4-lite
150 of 129
Page 1 of 3
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI