LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Providers

NovitaAI

novita-ai·Gateway·107 models·Official docs ↗

NovitaAI is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.

It lists 107 models on this page. Coverage spans text and chat (107). The lowest-priced model hosted here is PaddleOCR-VL.

NovitaAI is the lowest paid channel for 20 models that have at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.

Coverage & pricing
Models hosted107With public price 107
Cheapest anywhere20
Model typesText / Chat 107
Cheapest model herepaPaddleOCR-VL
SDK package@ai-sdk/openai-compatible
APIhttps://api.novita.ai/openai

Hosted models by blended price asc

⌕
107 of 107
Cheapest here?
paPaddleOCR-VLpaddlepaddle/paddleocr-vl$0.02$0.02—16,384Only channel
Llama-3.1-8B-Instructmeta-llama/llama-3.1-8b-instruct$0.02$0.05—16,3841.1× pricier
DeepSeek OCR 2deepseek/deepseek-ocr-2$0.03$0.03—8,192Lowest anywhere
DeepSeek-OCRdeepseek/deepseek-ocr$0.03$0.03—8,192Lowest anywhere
Qwen3 4Bqwen/qwen3-4b-fp8$0.03$0.03—128,000Only channel
Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct$0.03$0.05—32,7681.8× pricier
Llama 3 8B Instructmeta-llama/llama-3-8b-instruct$0.04$0.04—8,192Only channel
L3 8B Stheno V3.2sao10K/L3-8B-stheno-v3.2$0.05$0.05—8,192Lowest anywhere
saSao10k L3 8B Lunaris sao10K/l3-8b-lunaris$0.05$0.05—8,192Only channel
Qwen3 8Bqwen/qwen3-8b-fp8$0.035$0.14—128,0001.0× pricier
AutoGLM-Phone-9B-Multilingualzai-org/autoglm-phone-9b-multilingual$0.035$0.14—65,536Only channel
Gemma 3 12B ITgoogle/gemma-3-12b-it$0.05$0.10—131,072Lowest anywhere
GPT OSS 20Bopenai/gpt-oss-20b$0.04$0.15—131,0721.9× pricier
DeepSeek R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8b$0.06$0.09—128,000Only channel
Qwen2.5 7B Instructqwen/qwen2.5-7b-instruct$0.07$0.07—32,000Lowest anywhere
babaichuan-m2-32bbaichuan/baichuan-m2-32b$0.07$0.07—131,072Only channel
Mistral Nemomistralai/mistral-nemo$0.04$0.17—60,2883.3× pricier
grMythomax L2 13Bgryphe/mythomax-l2-13b$0.09$0.09—4,096Only channel
GPT OSS 120Bopenai/gpt-oss-120b$0.05$0.25—131,0721.7× pricier
Qwen3-Coder 30B-A3B Instructqwen/qwen3-coder-30b-a3b-instruct$0.07$0.27—160,0001.1× pricier
baBaidu Ernie 4.5 21B A3B Thinkingbaidu/ernie-4.5-21B-a3b-thinking$0.07$0.28—131,0721.0× pricier
baERNIE 4.5 21B A3Bbaidu/ernie-4.5-21B-a3b$0.07$0.28—120,000Only channel
Gemma 3 27B ITgoogle/gemma-3-27b-it$0.12$0.20—98,3041.4× pricier
Hermes 2 Pro Llama 3 8Bnousresearch/hermes-2-pro-llama-3-8b$0.14$0.14—8,192Lowest anywhere
DeepSeek R1 Distill Qwen 14Bdeepseek/deepseek-r1-distill-qwen-14b$0.15$0.15—32,768Lowest anywhere
MiMo-V2-Flashxiaomimimo/mimo-v2-flash$0.10$0.30—262,1441.0× pricier
inLing-2.6-flashinclusionai/ling-2.6-flash$0.10$0.30$0.02262,144Lowest anywhere
GLM-4.7-Flashzai-org/glm-4.7-flash$0.07$0.40$0.01200,0001.1× pricier
DeepSeek V4 Flashdeepseek/deepseek-v4-flash$0.14$0.28$0.0281,048,5764.0× pricier
Qwen3 30B A3Bqwen/qwen3-30b-a3b-fp8$0.09$0.45—40,9601.4× pricier
Qwen/Qwen3-VL-8B-Instructqwen/qwen3-vl-8b-instruct$0.08$0.50—131,072Lowest anywhere
Qwen3 32Bqwen/qwen3-32b-fp8$0.10$0.45—40,9601.4× pricier
Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it$0.13$0.40—262,1442.3× pricier
Llama-3.3-70B-Instructmeta-llama/llama-3.3-70b-instruct$0.14$0.40—131,0722.1× pricier
Gemma 4 31Bgoogle/gemma-4-31b-it$0.14$0.40—262,1441.3× pricier
Qwen3 235B-A22B Instruct 2507qwen/qwen3-235b-a22b-instruct-2507$0.09$0.58—131,0721.4× pricier
baERNIE 4.5 VL 28B A3Bbaidu/ernie-4.5-vl-28b-a3b$0.14$0.56—30,000Only channel
Llama 4 Scout 17B 16E Instructmeta-llama/llama-4-scout-17b-16e-instruct$0.18$0.59—131,0721.9× pricier
DeepSeek-R1-Distill-Qwen-32Bdeepseek/deepseek-r1-distill-qwen-32b$0.30$0.30—64,000Lowest anywhere
DeepSeek V3.2deepseek/deepseek-v3.2$0.27$0.40$0.13163,8401.4× pricier
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp$0.27$0.41—163,8401.2× pricier
GLM-4.5-Airzai-org/glm-4.5-air$0.13$0.85$0.025131,0721.9× pricier
Qwen/Qwen3-VL-30B-A3B-Instructqwen/qwen3-vl-30b-a3b-instruct$0.20$0.70—131,0721.4× pricier
Qwen3 235B-A22Bqwen/qwen3-235b-a22b-fp8$0.20$0.80—40,9601.0× pricier
Qwen-MT Plusqwen/qwen-mt-plus$0.25$0.75—16,384Lowest anywhere
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct$0.38$0.40—32,0002.2× pricier
baERNIE-4.5-VL-28B-A3B-Thinkingbaidu/ernie-4.5-vl-28b-a3b-thinking$0.39$0.39—131,072Only channel
Qwen/Qwen3-VL-30B-A3B-Thinkingqwen/qwen3-vl-30b-a3b-thinking$0.20$1.00—131,072Lowest anywhere
Llama 4 Maverick 17B 128E Instruct FP8meta-llama/llama-4-maverick-17b-128e-instruct-fp8$0.27$0.85—1,048,5761.2× pricier
Qwen3 Omni 30B A3B Instructqwen/qwen3-omni-30b-a3b-instruct$0.25$0.97—65,536Only channel
Qwen3 Omni 30B A3B Thinkingqwen/qwen3-omni-30b-a3b-thinking$0.25$0.97—65,536Only channel
GLM-4.6Vzai-org/glm-4.6v$0.30$0.90$0.055131,0722.2× pricier
DeepSeek-V3.1deepseek/deepseek-v3.1$0.27$1.00$0.14131,0721.4× pricier
DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus$0.27$1.00$0.14131,0721.2× pricier
DeepSeek V3 0324deepseek/deepseek-v3-0324$0.27$1.12$0.14163,8401.4× pricier
baERNIE 4.5 300B A47Bbaidu/ernie-4.5-300b-a47b-paddle$0.28$1.10—123,000Lowest anywhere
Qwen3-Next 80B-A3B Instructqwen/qwen3-next-80b-a3b-instruct$0.15$1.50—131,0721.9× pricier
Qwen3-Next 80B-A3B (Thinking)qwen/qwen3-next-80b-a3b-thinking$0.15$1.50—131,0721.8× pricier
MiniMax-M2.7minimax/minimax-m2.7$0.30$1.20$0.06204,8003.7× pricier
MiniMax-M2.5minimax/minimax-m2.5$0.30$1.20$0.03204,8001.4× pricier
MiniMax-M2.1minimax/minimax-m2.1$0.30$1.20$0.03204,8001.1× pricier
MiniMax-M2minimax/minimax-m2$0.30$1.20$0.03204,8001.3× pricier
kwKat Coder Prokwaipilot/kat-coder-pro$0.30$1.20$0.06256,000Lowest anywhere
Qwen3 Coder Nextqwen/qwen3-coder-next$0.20$1.50—262,1442.1× pricier
Llama3 70B Instructmeta-llama/llama-3-70b-instruct$0.51$0.74—8,192Lowest anywhere
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct$0.30$1.50—131,0721.6× pricier
WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b$0.62$0.62—65,5351.3× pricier
DeepSeek V3 (Turbo) deepseek/deepseek-v3-turbo$0.40$1.30—64,000Only channel
baERNIE 4.5 VL 424B A47Bbaidu/ernie-4.5-vl-424b-a47b$0.42$1.25—123,000Lowest anywhere
MiMo-V2.5-Proxiaomimimo/mimo-v2.5-pro$0.52$1.04$0.00431,048,5761.3× pricier
Qwen3-Coder 480B-A35B Instructqwen/qwen3-coder-480b-a35b-instruct$0.38$1.55—262,1441.9× pricier
Qwen3.5 35B-A3Bqwen/qwen3.5-35b-a3b$0.25$2.00—262,1444.4× pricier
Qwen2.5-VL 72B Instructqwen/qwen2.5-vl-72b-instruct$0.80$0.80—32,768Lowest anywhere
DeepSeek R1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70b$0.80$0.80—8,19214.5× pricier
Qwen3.5 27Bqwen/qwen3.5-27b$0.30$2.40—262,1443.5× pricier
inLing-2.6-1Tinclusionai/ling-2.6-1t$0.30$2.50$0.06262,144Lowest anywhere
inRing-2.6-1Tinclusionai/ring-2.6-1t$0.30$2.50$0.06262,144Lowest anywhere
GLM-4.5Vzai-org/glm-4.5v$0.60$1.80$0.1165,5362.1× pricier
GLM-4.6zai-org/glm-4.6$0.55$2.20$0.11204,8002.0× pricier
MiniMax M1minimaxai/minimax-m1-80k$0.55$2.20—1,000,0002.3× pricier
Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507$0.30$3.00—131,0724.2× pricier
GLM-4.7zai-org/glm-4.7$0.60$2.20$0.11204,8002.9× pricier
GLM-4.5zai-org/glm-4.5$0.60$2.20$0.11131,0722.0× pricier
Kimi K2 Instructmoonshotai/kimi-k2-instruct$0.57$2.30—131,0721.3× pricier
MiniMax-M2.7-highspeedminimax/minimax-m2.7-highspeed$0.60$2.40$0.06204,8002.0× pricier
MiniMax-M2.5-highspeedminimax/minimax-m2.5-highspeed$0.60$2.40$0.03204,800Lowest anywhere
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking$0.60$2.50$0.15262,1441.3× pricier
Kimi K2 0905moonshotai/kimi-k2-0905$0.60$2.50—262,1441.4× pricier
Qwen3.5 122B-A10Bqwen/qwen3.5-122b-a10b$0.40$3.20—262,1443.6× pricier
DeepSeek R1 0528deepseek/deepseek-r1-0528$0.70$2.50$0.35163,8401.3× pricier
Deepseek Prover V2 671Bdeepseek/deepseek-prover-v2-671b$0.70$2.50—160,000Only channel
DeepSeek R1 (Turbo) deepseek/deepseek-r1-turbo$0.70$2.50—64,000Only channel
Kimi K2.5moonshotai/kimi-k2.5$0.60$3.00$0.10262,1441.7× pricier
Qwen3.5 397B-A17Bqwen/qwen3.5-397b-a17b$0.60$3.60—262,1443.6× pricier
Kimi K2.6moonshotai/kimi-k2.6$0.80$3.40$0.16262,1443.0× pricier
saL31 70B Euryale V2.2sao10K/l31-70b-euryale-v2.2$1.48$1.48—8,192Only channel
saL3 70B Euryale V2.1 sao10K/l3-70b-euryale-v2.1$1.48$1.48—8,192Only channel
GLM-5zai-org/glm-5$1.00$3.20$0.20202,8002.1× pricier
Kimi K2.7 Codemoonshotai/kimi-k2.7-code$0.95$4.00$0.19262,1443.6× pricier
Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking$0.98$3.95—131,0721.8× pricier
Qwen3.7 Maxqwen/qwen3.7-max$1.25$3.75$0.251,000,0001.5× pricier
DeepSeek V4 Prodeepseek/deepseek-v4-pro$1.60$3.20$0.141,048,5767.7× pricier
GLM-5.1zai-org/glm-5.1$1.38$4.40$0.26204,8002.4× pricier
GLM-5.2zai-org/glm-5.2$1.40$4.40$0.261,048,5764.4× pricier
MiMo-V2-Proxiaomimimo/mimo-v2-pro$2.00$6.00$0.401,048,5765.5× pricier
Qwen3 Maxqwen/qwen3-max$2.11$8.45—262,1445.9× pricier
Kimi K3moonshotai/kimi-k3$3.00$15.00$0.301,048,5761.7× pricier