Novita AI

Novita AI provides 200+ Model APIs, custom deployment, GPU Instances, and Serverless GPUs. Scale AI, optimize performance, and innovate with ease and efficiency.

158
Models available: $0.020
Cheapest /1M input

Model price list

updated 1 hour ago

Free only

				Cache
meta-llama/llama-3.1-8b-instruct	16K	$0.020	$0.050	—
paddlepaddle/paddleocr-vl	16K	$0.020	$0.020	—
meta-llama/llama-3.2-1b-instruct	131K	$0.020	$0.020	—
qwen/qwen3-4b-fp8	128K	$0.030	$0.030	—
deepseek/deepseek-ocr	8K	$0.030	$0.030	—
deepseek/deepseek-ocr-2	8K	$0.030	$0.030	—
meta-llama/llama-3.2-3b-instruct	33K	$0.030	$0.050	—
qwen/qwen3-8b-fp8	128K	$0.035	$0.138	—
zai-org/autoglm-phone-9b-multilingual	66K	$0.035	$0.138	—
meta-llama/llama-3-8b-instruct	8K	$0.040	$0.040	—
mistralai/mistral-nemo	60K	$0.040	$0.170	—
hermes/mercury-oss-20b	131K	$0.040	$0.150	—
google/gemma-3-12b-it	131K	$0.050	$0.100	—
nvidia/nemotron-3-nano-30b-a3b	262K	$0.050	$0.200	—
sao10k/l3-8b-lunaris	8K	$0.050	$0.050	—
hermes/mercury-oss-120b	131K	$0.050	$0.250	—
Sao10K/L3-8B-Stheno-v3.2	8K	$0.050	$0.050	—
qwen/qwen-2-7b-instruct	33K	$0.054	$0.054	—
deepseek/deepseek-r1-0528-qwen3-8b	128K	$0.060	$0.090	—
openchat/openchat-7b	4K	$0.060	$0.060	—
inclusionai/ling-3.0-flash-fast	262K	$0.060	$0.180	$0.012
inclusionai/ling-3.0-flash	262K	$0.060	$0.180	$0.012
qwen/qwen2.5-7b-instruct	32K	$0.070	$0.070	—
zai-org/glm-4.7-flash	200K	$0.070	$0.400	$0.010
qwen/qwen3-coder-30b-a3b-instruct	160K	$0.070	$0.270	—
baichuan/baichuan-m2-32b	131K	$0.070	$0.070	—
baidu/ernie-4.5-21B-a3b	120K	$0.070	$0.280	—
baidu/ernie-4.5-21B-a3b-thinking	131K	$0.070	$0.280	—
qwen/qwen3-vl-8b-instruct	131K	$0.080	$0.500	—
qwen/qwen3-30b-a3b-fp8	41K	$0.090	$0.450	—
gryphe/mythomax-l2-13b	4K	$0.090	$0.090	—
qwen/qwen3-235b-a22b-instruct-2507	131K	$0.090	$0.580	—
inclusionai/ling-2.6-flash	262K	$0.100	$0.300	$0.020
qwen/qwen3-32b-fp8	41K	$0.100	$0.450	—
elephant	262K	$0.100	$0.300	$0.020
xiaomimimo/mimo-v2-flash	262K	$0.110	$0.330	$0.024
google/gemma-3-27b-it	98K	$0.119	$0.200	—
zai-org/glm-4.5-air	131K	$0.130	$0.850	$0.025
google/gemma-4-26b-a4b-it	262K	$0.130	$0.400	—
meta-llama/llama-3.3-70b-instruct	12K	$0.135	$0.400	—
tencent/hy3	262K	$0.140	$0.580	$0.035
baidu/ernie-4.5-vl-28b-a3b	30K	$0.140	$0.560	—
deepseek/deepseek-v4-flash	1.0M	$0.140	$0.280	$0.028
nousresearch/hermes-2-pro-llama-3-8b	8K	$0.140	$0.140	—
google/gemma-4-31b-it	262K	$0.140	$0.400	—
qwen/qwen3-next-80b-a3b-thinking	131K	$0.150	$1.50	—
zai-org/glm-5.3-flash	1.0M	$0.150	$0.500	$0.030
qwen/qwen3.8-flash	1M	$0.150	$0.470	$0.016
deepseek/deepseek-r1-distill-qwen-14b	33K	$0.150	$0.150	—
qwen/qwen3-next-80b-a3b-instruct	131K	$0.150	$1.50	—
xiaomimimo/mimo-v2.5	1.0M	$0.168	$0.336	$0.0034
teknium/openhermes-2.5-mistral-7b	4K	$0.170	$0.170	—
nousresearch/nous-hermes-llama2-13b	4K	$0.170	$0.170	—
meta-llama/llama-4-scout-17b-16e-instruct	131K	$0.180	$0.590	—
qwen/qwen3-vl-30b-a3b-thinking	131K	$0.200	$1.00	—
qwen/qwen3-vl-30b-a3b-instruct	131K	$0.200	$0.700	—
qwen/qwen3-coder-next	262K	$0.200	$1.50	—
stepfun/step-3.7-flash	262K	$0.200	$1.15	$0.040
qwen/qwen3-235b-a22b-fp8	41K	$0.200	$0.800	—
mindai/macaron-v1-tall	262K	$0.248	$1.43	$0.044
qwen/qwen3.6-35b-a3b	262K	$0.248	$1.49	—
qwen/qwen-mt-plus	16K	$0.250	$0.750	—
qwen/qwen3-omni-30b-a3b-instruct	66K	$0.250	$0.970	—
qwen/qwen3.5-35b-a3b	262K	$0.250	$2.00	—
qwen/qwen3-omni-30b-a3b-thinking	66K	$0.250	$0.970	—
deepseek/deepseek-v3.2	164K	$0.269	$0.400	$0.135
deepseek/deepseek-v3.1-terminus	131K	$0.270	$1.00	$0.135
meta-llama/llama-4-maverick-17b-128e-instruct-fp8	1.0M	$0.270	$0.850	—
deepseek/deepseek-v3.2-exp	164K	$0.270	$0.410	—
deepseek/deepseek-v3-0324	164K	$0.270	$1.12	$0.135
deepseek/deepseek-v3.1	131K	$0.270	$1.00	$0.135
baidu/cobuddy	131K	$0.280	$1.13	$0.070
baidu/ernie-4.5-300b-a47b-paddle	123K	$0.280	$1.10	—
qwen/qwen3.5-27b	262K	$0.300	$2.40	—
deepseek/deepseek-r1-distill-qwen-32b	64K	$0.300	$0.300	—
deepseek/deepseek-v4.1-flash	1.0M	$0.300	$1.20	$0.0060
inclusionai/ling-2.6-1t	262K	$0.300	$2.50	$0.060
inclusionai/ring-2.6-1t	262K	$0.300	$2.50	$0.060
kwaipilot/kat-coder-pro	256K	$0.300	$1.20	$0.060
minimax/minimax-m2	205K	$0.300	$1.20	$0.030
minimax/minimax-m2.1	205K	$0.300	$1.20	$0.030
minimax/minimax-m2.5	205K	$0.300	$1.20	$0.030
minimax/minimax-m2.7	205K	$0.300	$1.20	$0.060
minimax/minimax-m3	1M	$0.300	$1.20	$0.060
qwen/qwen3-235b-a22b-thinking-2507	131K	$0.300	$3.00	—
qwen/qwen3-vl-235b-a22b-instruct	131K	$0.300	$1.50	—
zai-org/glm-4.6v	131K	$0.300	$0.900	$0.055
qwen/qwen3-coder-480b-a35b-instruct	262K	$0.380	$1.55	—
qwen/qwen-2.5-72b-instruct	32K	$0.380	$0.400	—
baidu/ernie-4.5-vl-28b-a3b-thinking	131K	$0.390	$0.390	—
deepseek/deepseek-v3-turbo	64K	$0.400	$1.30	—
qwen/qwen3.5-122b-a10b	262K	$0.400	$3.20	—
qwen/qwen3.8-27b	1M	$0.420	$3.00	$0.085
baidu/ernie-4.5-vl-424b-a47b	123K	$0.420	$1.25	—
deepseek/deepseek-v4-flash-vision-exp	1.0M	$0.440	$1.32	$0.028
deepseek/deepseek-v4-flash-0731	1.0M	$0.440	$1.32	$0.028
qwen/qwen-2-vl-72b-instruct	33K	$0.450	$0.450	—
meta-llama/llama-3-70b-instruct	8K	$0.510	$0.740	—
xiaomimimo/mimo-v2.5-pro	1.0M	$0.522	$1.04	$0.0043
thudm/glm-4-32b-0414	32K	$0.550	$1.66	—
minimaxai/minimax-m1-80k	1M	$0.550	$2.20	—
zai-org/glm-4.6	205K	$0.550	$2.20	$0.110
moonshotai/kimi-k2-instruct	131K	$0.570	$2.30	—
moonshotai/kimi-k2-thinking	262K	$0.600	$2.50	$0.150
zai-org/glm-4.5	131K	$0.600	$2.20	$0.110
zai-org/glm-4.7-h	205K	$0.600	$2.20	$0.110
zai-org/glm-4.7	205K	$0.600	$2.20	$0.110
moonshotai/kimi-k2.5	262K	$0.600	$3.00	$0.100
moonshotai/kimi-k2-0905	262K	$0.600	$2.50	—
minimax/minimax-m2.5-highspeed	205K	$0.600	$2.40	$0.030
minimax/minimax-m2.7-highspeed	205K	$0.600	$2.40	$0.060
qwen/qwen3.5-397b-a17b	262K	$0.600	$3.60	—
zai-org/glm-4.5v	66K	$0.600	$1.80	$0.110
qwen/qwen3.6-27b	262K	$0.600	$3.60	—
microsoft/wizardlm-2-8x22b	66K	$0.620	$0.620	—
deepseek/deepseek-prover-v2-671b	160K	$0.700	$2.50	—
deepseek/deepseek-r1-0528	164K	$0.700	$2.50	$0.350
deepseek/deepseek-r1-turbo	64K	$0.700	$2.50	—
qwen/qwen2.5-vl-72b-instruct	33K	$0.800	$0.800	—
deepseek/deepseek-r1-distill-llama-70b	8K	$0.800	$0.800	—
moonshotai/kimi-k2.6	262K	$0.800	$3.40	$0.160
mindai/macaron-v1-venti	1.0M	$0.825	$2.48	$0.165
deepseek/deepseek_v3	64K	$0.890	$0.890	—
deepseek/deepseek-v3/community	64K	$0.890	$0.890	—
moonshotai/kimi-k2.7-code	262K	$0.950	$4.00	$0.190
qwen/qwen3-vl-235b-a22b-thinking	131K	$0.980	$3.95	—
zai-org/glm-5	203K	$1.00	$3.20	$0.200
zai-org/glm-5v-turbo	205K	$1.20	$4.00	$0.240
zai-org/glm-5-turbo	203K	$1.20	$4.00	$0.240
qwen/qwen3.7-max	1M	$1.25	$3.75	$0.250
deepseek/deepseek-v4-pro-0813	1.0M	$1.32	$3.96	$0.044
zai-org/glm-5.1	205K	$1.38	$4.40	$0.260
zai-org/glm-5.3	1.0M	$1.40	$4.40	$0.260
zai-org/glm-5.2	1.0M	$1.40	$4.40	$0.260
sao10k/l3-70b-euryale-v2.1	8K	$1.48	$1.48	—
sao10k/l31-70b-euryale-v2.2	8K	$1.48	$1.48	—
deepseek/deepseek-v4-pro	1.0M	$1.60	$3.20	$0.135
qwen/qwen3.8-max	1M	$2.00	$6.00	$0.250
qwen/qwen3.8-2.4t-a95b	1M	$2.00	$6.00	$0.250
xiaomimimo/mimo-v2-pro	1.0M	$2.00	$6.00	$0.400
qwen/qwen3-max	262K	$2.11	$8.45	—
moonshotai/kimi-k3	1.0M	$3.00	$15.00	$0.300
deepseek/deepseek-r1	64K	$4.00	$4.00	—
deepseek/deepseek-r1/community	64K	$4.00	$4.00	—
ai_infer_test_1	200K	—	—	—
deepseek/deepseek-v4.1-flash-expires-on-0910	1.0M	—	—	—
dev/glm46	256K	—	—	—
ai_infer_test_2	200K	—	—	—
gt-4p	—	—	—	—
inclusionai/ling-3.0-flash-fin	262K	—	—	—
inclusionai/ling-3.0-flash-sante	262K	—	—	—
inclusionai/ling-3.0-flash-vl	262K	—	—	—
inclusionai/ling-3.0-tiny	262K	—	—	—
bunny	262K	—	—	—
nex-agi/nex-n2-pro	262K	—	—	—
qwen/qwen3.6-plus	1M	—	—	—
ai_infer_test_3	200K	—	—	—
qwen/qwen3.5-plus	1M	—	—	—

158 of 158 models · free ones are pinned to the top

Not every gateway lists prices in its API. The blanks are filled in by hand from each pricing page or dashboard, and that happens gradually — 14 models here are still waiting their turn.