Novita AI Models — Pricing & Benchmarks

102 models available

Last refreshed 2026-09-30. Next refresh: weekly.

Novita AI hosts 102 AI models in this catalog. The lowest listed input price is BGE M3 at $0.01/1M input tokens. LLM Reference compares these models across all 97 providers.

Model	Input (per 1M)	Output (per 1M)	Context
BGE M3	$0.01	—	8k
BGE Reranker V2 M3	$0.01	—	8k
Llama 3.1 8B Instruct	$0.02	$0.05	128k
PaddleOCR VL	$0.02	$0.02	16k
DeepSeek OCR	$0.03	$0.03	8k
DeepSeek OCR 2	$0.03	$0.03	8k
Llama 3.2 3B Instruct	$0.03	$0.05	128k
AutoGLM Phone 9B Multilingual	$0.035	$0.138	66k
Qwen3-8B	$0.035	$0.138	128k
gpt-oss-20b	$0.04	$0.15	131k
Llama 3 8B Instruct	$0.04	$0.04	8k
Mistral NeMo (2407)	$0.04	$0.17	128k
Gemma 3 12B	$0.05	$0.1	33k
gpt-oss-120b	$0.05	$0.25	131k
L3 8B Lunaris	$0.05	$0.05	8k
L3 8B Stheno V3.2	$0.05	$0.05	8k
Phi-4 Mini	$0.05	$0.15	128k
Qwen3 Reranker 8B	$0.05	—	33k
DeepSeek R1 0528 Qwen3-8B	$0.06	$0.09	160k
Baichuan M2 32B	$0.07	$0.07	131k
ERNIE 4.5 21B A3B	$0.07	$0.28	120k
GLM-4.7 Flash	$0.07	$0.4	198k
Qwen2.5-7B-Instruct	$0.07	$0.07	128k
Qwen3 Embedding 0.6B	$0.07	—	33k
Qwen3 Embedding 8B	$0.07	—	33k
Qwen3-Coder-30B-A3B-Instruct	$0.07	$0.27	262k
Mistral NeMo Instruct (2407)	$0.08	$0.24	128k
Qwen3 VL 8B Instruct	$0.08	$0.5	128k
MythoMax L2 13B	$0.09	$0.09	4k
Qwen3-235B-A22B	$0.09	$0.58	128k
Qwen3-30B-A3B	$0.09	$0.45	128k
Ling-2.6-Flash	$0.1	$0.3	262k
Qwen3-32B	$0.1	$0.45	40k
Xiaomi MiMo-V2-Flash	$0.1	$0.3	262k
Gemma 3 27B	$0.119	$0.2	131k
DeepSeek Coder V2 Lite Instruct	$0.12	$0.36	128k
Gemma 4 26B A4B IT	$0.13	$0.4	256k
GLM-4.5-Air	$0.13	$0.85	128k
Llama 3.3 70B Instruct (free)	$0.135	$0.4	66k
DeepSeek V4 Flash	$0.14	$0.28	1m
ERNIE 4.5 VL 28B A3B	$0.14	$0.56	30k
Gemma 4 31B IT	$0.14	$0.4	256k
Hermes 2 Pro Llama 3 8B	$0.14	$0.14	8k
DeepSeek R1 Distill Qwen-14B	$0.15	$0.15	128k
Qwen3-Next-80B-A3B	$0.15	$1.50	—
Llama 4 Scout 17B-16E Instruct	$0.18	$0.59	10m
Qwen3 VL 30B A3B Instruct	$0.2	$0.7	128k
Qwen3-Coder-Next	$0.2	$1.50	256k
Qwen3.6-35B-A3B	$0.248	$1.49	262k
Qwen-MT-Plus	$0.25	$0.75	8k
Qwen3 Omni 30B A3B	$0.25	$0.97	66k
Qwen3.5-35B-A3B	$0.25	$2.00	262k
DeepSeek V3.2	$0.269	$0.4	160k
DeepSeek V3 0324	$0.27	$1.12	160k
DeepSeek V3.1	$0.27	$1.00	64k
DeepSeek V3.1 Terminus	$0.27	$1.00	164k
DeepSeek V3.2 Exp	$0.27	$0.41	164k
Llama 4 Maverick 17B Instruct FP8	$0.27	$0.85	1m
ERNIE 4.5 300B A47B	$0.28	$1.10	123k
DeepSeek R1 Distill Qwen-32B	$0.3	$0.3	128k
GLM 4.6V	$0.3	$0.9	128k
KAT Coder Pro V2	$0.3	$1.20	256k
Ling-2.6-1T	$0.3	$2.50	262k
MiniMax M2	$0.3	$1.20	197k
MiniMax M2.1	$0.3	$1.20	200k
MiniMax M2.5	$0.3	$1.20	197k
MiniMax M2.7	$0.3	$1.20	205k
Qwen3 VL 235B A22B Instruct	$0.3	$1.50	256k
Qwen3.5-27B	$0.3	$2.40	262k
Ring-2.6-1T	$0.3	$2.50	262k
Qwen2.5-72B-Instruct	$0.38	$0.4	128k
Qwen3-Coder-480B-A35B-Instruct	$0.38	$1.55	262k
Qwen3.5-122B-A10B	$0.4	$3.20	262k
ERNIE 4.5 VL 424B A47B	$0.42	$1.25	123k
Llama 3 70B Instruct	$0.51	$0.74	8k
GLM-4.6	$0.55	$2.20	198k
MiniMax-M1-80k	$0.55	$2.20	80k
Kimi K2 Instruct	$0.57	$2.30	131k
GLM 4.5V	$0.6	$1.80	64k
GLM 4.7	$0.6	$2.20	200k
GLM-4.5	$0.6	$2.20	128k
Kimi K2 0905 Preview	$0.6	$2.50	262k
Kimi K2 Thinking	$0.6	$2.50	256k
Kimi K2.5	$0.6	$3.00	256k
MiniMax M2.5 Highspeed	$0.6	$2.40	205k
Qwen3.5-397B-A17B	$0.6	$3.60	262k
Qwen3.6-27B	$0.6	$3.60	262k
WizardLM-2 8x22B	$0.62	$0.62	—
DeepSeek Prover V2	$0.7	$2.50	160k
DeepSeek R1 0528	$0.7	$2.50	130k
DeepSeek R1 Distill Llama 70B	$0.8	$0.8	128k
Kimi K2.6	$0.8	$3.40	262k
Qwen2.5-VL-72B	$0.8	$0.8	33k
Qwen3-VL-235B-A22B	$0.98	$3.95	128k
GLM-5	$1.00	$3.20	200k
Qwen3.7-Max	$1.25	$3.75	1m
GLM-5.1	$1.38	$4.40	200k
L3 70B Euryale V2.1	$1.48	$1.48	8k
L3.1 70B Euryale V2.2	$1.48	$1.48	131k
DeepSeek V4 Pro	$1.60	$3.20	1m
Xiaomi MiMo-V2.5-Pro	$2.00	$6.00	1.05m
Qwen3-Max	$2.11	$8.45	262k