Novita AI
Catalogue / Novita AI
Novita AI currently lists 120 offers we track. The lowest output price is meta-llama/llama-3.2-1b-instruct at $0.020, the highest is moonshotai/kimi-k3.1-pro-highspeed at $20.00. 53 more are no longer listed by Novita AI. These are the prices Novita AI charges as a seller, which are not necessarily the list prices of the vendor whose name a model carries.
Read between 9 September 2026 and 3 November 2026. Every figure below carries the date it was observed on its own page.
Novita AI prices per model
| Model | Input | Output | Context | Last read |
|---|---|---|---|---|
| moonshotai/kimi-k3.1-pro-highspeed | $4.00 | $20.00 | 1 048 576 | 3 November 2026 |
| moonshotai/kimi-k3 | $3.00 | $15.00 | 1 048 576 | 3 November 2026 |
| moonshotai/kimi-k3-p | $3.00 | $15.00 | 1 048 576 | 30 October 2026 |
| moonshotai/kimi-k3.1-pro | $2.00 | $10.00 | 1 048 576 | 3 November 2026 |
| qwen/qwen3.8-2.4t-a95b | $2.00 | $6.00 | 1 000 000 | 3 November 2026 |
| qwen/qwen3.8-max | $2.00 | $6.00 | 1 000 000 | 3 November 2026 |
| zai-org/glm-5.1 | $1.38 | $4.40 | 204 800 | 31 October 2026 |
| zai-org/glm-5.2 | $1.40 | $4.40 | 1 048 576 | 3 November 2026 |
| zai-org/glm-5.3 | $1.40 | $4.40 | 1 048 576 | 3 November 2026 |
| zai-org/glm-5.3-p | $1.40 | $4.40 | 1 048 576 | 31 October 2026 |
| deepseek/deepseek-r1 | $4.00 | $4.00 | 64 000 | 3 November 2026 |
| deepseek/deepseek-r1/community | $4.00 | $4.00 | 64 000 | 31 October 2026 |
| moonshotai/kimi-k2.7-code | $0.950 | $4.00 | 262 144 | 3 November 2026 |
| deepseek/deepseek-v4-pro-0813 | $1.32 | $3.96 | 1 048 576 | 3 November 2026 |
| deepseek/deepseek-v4-pro-0813-p | $1.32 | $3.96 | 1 048 576 | 2 November 2026 |
| qwen/qwen3-vl-235b-a22b-thinking | $0.980 | $3.95 | 131 072 | 8 October 2026 |
| qwen/qwen3.7-max | $1.25 | $3.75 | 1 000 000 | 31 October 2026 |
| qwen/qwen3.5-397b-a17b | $0.600 | $3.60 | 262 144 | 3 November 2026 |
| qwen/qwen3.6-27b | $0.600 | $3.60 | 262 144 | 31 October 2026 |
| moonshotai/kimi-k2.6 | $0.800 | $3.40 | 262 144 | 3 November 2026 |
| deepseek/deepseek-v4-pro | $1.60 | $3.20 | 1 048 576 | 3 November 2026 |
| qwen/qwen3.5-122b-a10b | $0.400 | $3.20 | 262 144 | 3 November 2026 |
| zai-org/glm-5 | $1.00 | $3.20 | 202 800 | 3 November 2026 |
| moonshotai/kimi-k2.5 | $0.600 | $3.00 | 262 144 | 3 November 2026 |
| qwen/qwen3-235b-a22b-thinking-2507 | $0.300 | $3.00 | 131 072 | 8 October 2026 |
| qwen/qwen3.8-27b | $0.420 | $3.00 | 1 000 000 | 3 November 2026 |
| stepfun/step-5-preview | $1.00 | $2.70 | 1 000 000 | 27 October 2026 |
| tencent/hy4-preview | $0.834 | $2.501 | 1 000 000 | 3 November 2026 |
| deepseek/deepseek-r1-0528 | $0.700 | $2.50 | 163 840 | 3 November 2026 |
| deepseek/deepseek-r1-turbo | $0.700 | $2.50 | 64 000 | 31 October 2026 |
| moonshotai/kimi-k2-0905 | $0.600 | $2.50 | 262 144 | 3 November 2026 |
| moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262 144 | 3 November 2026 |
| mindai/macaron-v1-venti | $0.825 | $2.475 | 1 048 576 | 31 October 2026 |
| minimax/minimax-m2.7-highspeed | $0.600 | $2.40 | 204 800 | 31 October 2026 |
| qwen/qwen3.5-27b | $0.300 | $2.40 | 262 144 | 3 November 2026 |
| moonshotai/kimi-k2-instruct | $0.570 | $2.30 | 131 072 | 3 November 2026 |
| minimaxai/minimax-m1-80k | $0.550 | $2.20 | 1 000 000 | 3 November 2026 |
| zai-org/glm-4.6 | $0.550 | $2.20 | 204 800 | 3 November 2026 |
| zai-org/glm-4.7 | $0.600 | $2.20 | 204 800 | 3 November 2026 |
| zai-org/glm-4.7-h | $0.600 | $2.20 | 204 800 | 31 October 2026 |
| qwen/qwen3.5-35b-a3b | $0.250 | $2.00 | 262 144 | 3 November 2026 |
| zai-org/glm-4.5v | $0.600 | $1.80 | 65 536 | 3 November 2026 |
| thudm/glm-4-32b-0414 | $0.550 | $1.66 | 32 000 | 8 October 2026 |
| qwen/qwen3-coder-480b-a35b-instruct | $0.380 | $1.55 | 262 144 | 8 October 2026 |
| qwen/qwen3-coder-next | $0.200 | $1.50 | 262 144 | 8 October 2026 |
| qwen/qwen3-next-80b-a3b-instruct | $0.150 | $1.50 | 131 072 | 8 October 2026 |
| qwen/qwen3-vl-235b-a22b-instruct | $0.300 | $1.50 | 131 072 | 8 October 2026 |
| qwen/qwen3.6-35b-a3b | $0.248 | $1.485 | 262 144 | 31 October 2026 |
| sao10k/l3-70b-euryale-v2.1 | $1.48 | $1.48 | 8 192 | 31 October 2026 |
| mindai/macaron-v1-tall | $0.2475 | $1.43 | 262 144 | 31 October 2026 |
| deepseek/deepseek-v4-flash-0731 | $0.440 | $1.32 | 1 048 576 | 3 November 2026 |
| deepseek/deepseek-v4-flash-0731-p | $0.440 | $1.32 | 1 048 576 | 2 November 2026 |
| deepseek/deepseek-v4-flash-vision-exp | $0.440 | $1.32 | 1 048 576 | 8 October 2026 |
| deepseek/deepseek-v4.1-flash | $0.300 | $1.20 | 1 048 576 | 3 November 2026 |
| deepseek/deepseek-v4.1-flash-1017 | $0.300 | $1.20 | 1 048 576 | 3 November 2026 |
| deepseek/deepseek-v4.1-flash-dst | $0.300 | $1.20 | 1 048 576 | 1 November 2026 |
| deepseek/deepseek-v4.1-flash-p | $0.300 | $1.20 | 1 048 576 | 31 October 2026 |
| minimax/minimax-m2 | $0.300 | $1.20 | 204 800 | 8 October 2026 |
| minimax/minimax-m2.1 | $0.300 | $1.20 | 204 800 | 8 October 2026 |
| minimax/minimax-m2.5 | $0.300 | $1.20 | 204 800 | 3 November 2026 |
| minimax/minimax-m2.7 | $0.300 | $1.20 | 204 800 | 3 November 2026 |
| minimax/minimax-m3 | $0.300 | $1.20 | 1 000 000 | 3 November 2026 |
| stepfun/step-3.7-flash | $0.200 | $1.15 | 262 144 | 31 October 2026 |
| baidu/cobuddy | $0.280 | $1.13 | 131 072 | 31 October 2026 |
| xiaomimimo/mimo-v2.5-pro | $0.522 | $1.044 | 1 048 576 | 22 October 2026 |
| deepseek/deepseek-v3.1 | $0.270 | $1.00 | 131 072 | 28 September 2026 |
| deepseek/deepseek-v3.1-terminus | $0.270 | $1.00 | 131 072 | 28 September 2026 |
| ming-image-0.1-design | $1.00 | $1.00 | 3 November 2026 | |
| ming-image-0.1-design-layer | $1.00 | $1.00 | 3 November 2026 | |
| qwen/qwen3-omni-30b-a3b-thinking | $0.250 | $0.970 | 65 536 | 31 October 2026 |
| inclusionai/ling-3.1-flash | $0.300 | $0.900 | 1 000 000 | 3 November 2026 |
| zai-org/glm-4.6v | $0.300 | $0.900 | 131 072 | 31 October 2026 |
| deepseek/deepseek_v3 | $0.890 | $0.890 | 64 000 | 31 October 2026 |
| xiaomimimo/mimo-v2.6-pro | $0.435 | $0.870 | 1 048 576 | 31 October 2026 |
| meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | $0.270 | $0.850 | 1 048 576 | 3 November 2026 |
| zai-org/glm-4.5-air | $0.130 | $0.850 | 131 072 | 3 November 2026 |
| deepseek/deepseek-r1-distill-llama-70b | $0.800 | $0.800 | 8 192 | 28 September 2026 |
| qwen/qwen-mt-plus | $0.250 | $0.750 | 16 384 | 31 October 2026 |
| qwen/qwen3-vl-30b-a3b-instruct | $0.200 | $0.700 | 131 072 | 3 November 2026 |
| microsoft/wizardlm-2-8x22b | $0.620 | $0.620 | 65 535 | 3 November 2026 |
| minimax/minimax-m3.1-flash | $0.150 | $0.600 | 1 000 000 | 3 November 2026 |
| meta-llama/llama-4-scout-17b-16e-instruct | $0.180 | $0.590 | 131 072 | 1 November 2026 |
| qwen/qwen3-235b-a22b-instruct-2507 | $0.090 | $0.580 | 131 072 | 8 October 2026 |
| tencent/hy3 | $0.140 | $0.580 | 262 144 | 31 October 2026 |
| zai-org/glm-5.3-flash | $0.150 | $0.500 | 1 048 576 | 3 November 2026 |
| qwen/qwen3.8-flash | $0.150 | $0.470 | 1 000 000 | 3 November 2026 |
| deepseek/deepseek-v3.2-exp | $0.270 | $0.410 | 163 840 | 28 September 2026 |
| deepseek/deepseek-v3.2 | $0.269 | $0.400 | 163 840 | 28 September 2026 |
| google/gemma-4-26b-a4b-it | $0.130 | $0.400 | 262 144 | 3 November 2026 |
| google/gemma-4-31b-it | $0.140 | $0.400 | 262 144 | 3 November 2026 |
| meta-llama/llama-3.3-70b-instruct | $0.135 | $0.400 | 12 288 | 3 November 2026 |
| qwen/qwen-2.5-72b-instruct | $0.380 | $0.400 | 32 000 | 8 October 2026 |
| zai-org/glm-4.7-flash | $0.070 | $0.400 | 200 000 | 3 November 2026 |
| xiaomimimo/mimo-v2.5 | $0.168 | $0.336 | 1 048 576 | 22 October 2026 |
| deepseek/deepseek-v4-flash | $0.140 | $0.280 | 1 048 576 | 9 October 2026 |
| xiaomimimo/mimo-v2.6-flash | $0.140 | $0.280 | 1 048 576 | 31 October 2026 |
| openai/gpt-oss-120b | $0.050 | $0.250 | 131 072 | 3 November 2026 |
| inclusionai/ling-3.0-flash-fin | $0.075 | $0.220 | 262 144 | 3 November 2026 |
| inclusionai/ling-3.0-flash-sante | $0.075 | $0.220 | 262 144 | 31 October 2026 |
| inclusionai/ling-3.0-flash-vl | $0.075 | $0.220 | 262 144 | 3 November 2026 |
| google/gemma-3-27b-it | $0.119 | $0.200 | 98 304 | 31 October 2026 |
| nvidia/nemotron-3-nano-30b-a3b | $0.050 | $0.200 | 262 144 | 31 October 2026 |
| inclusionai/ling-3.0-flash | $0.060 | $0.180 | 262 144 | 3 November 2026 |
| openai/gpt-oss-20b | $0.040 | $0.150 | 131 072 | 8 October 2026 |
| nousresearch/hermes-2-pro-llama-3-8b | $0.140 | $0.140 | 8 192 | 31 October 2026 |
| zai-org/autoglm-phone-9b-multilingual | $0.035 | $0.138 | 65 536 | 3 November 2026 |
| google/gemma-3-12b-it | $0.050 | $0.100 | 131 072 | 31 October 2026 |
| deepseek/deepseek-r1-0528-qwen3-8b | $0.060 | $0.090 | 128 000 | 31 October 2026 |
| gryphe/mythomax-l2-13b | $0.090 | $0.090 | 4 096 | 31 October 2026 |
| baichuan/baichuan-m2-32b | $0.070 | $0.070 | 131 072 | 31 October 2026 |
| Sao10K/L3-8B-Stheno-v3.2 | $0.050 | $0.050 | 8 192 | 3 November 2026 |
| meta-llama/llama-3.1-8b-instruct | $0.020 | $0.050 | 16 384 | 3 November 2026 |
| deepseek/deepseek-ocr-2 | $0.030 | $0.030 | 8 192 | 31 October 2026 |
| meta-llama/llama-3.2-1b-instruct | $0.020 | $0.020 | 131 000 | 31 October 2026 |
| paddlepaddle/paddleocr-vl | $0.020 | $0.020 | 16 384 | 31 October 2026 |
| apodex/apodex-1.1-mini | $0.000 | $0.000 | 262 144 | 3 November 2026 |
| baai/bge-m3 | $0.010 | 8 192 | 3 November 2026 | |
| baai/bge-reranker-v2-m3 | $0.010 | 8 000 | 3 November 2026 | |
| qwen/qwen3-embedding-8b | $0.070 | 32 768 | 3 November 2026 | |
| qwen/qwen3-reranker-8b | $0.050 | 32 768 | 3 November 2026 |
No longer listed by Novita AI
Their last prices stay published and dated on their pages.
- baidu/ernie-4.5-21B-a3b$0.280 / 1M out
- baidu/ernie-4.5-21B-a3b-thinking$0.280 / 1M out
- baidu/ernie-4.5-300b-a47b-paddle$1.10 / 1M out
- baidu/ernie-4.5-vl-28b-a3b$0.560 / 1M out
- baidu/ernie-4.5-vl-28b-a3b-thinking$0.390 / 1M out
- baidu/ernie-4.5-vl-424b-a47b$1.25 / 1M out
- deepseek/deepseek-ocr$0.030 / 1M out
- deepseek/deepseek-prover-v2-671b$2.50 / 1M out
- deepseek/deepseek-r1-distill-qwen-14b$0.150 / 1M out
- deepseek/deepseek-r1-distill-qwen-32b$0.300 / 1M out
- deepseek/deepseek-v3-0324$1.12 / 1M out
- deepseek/deepseek-v3-turbo$1.30 / 1M out
- deepseek/deepseek-v3/community$0.890 / 1M out
- deepseek/deepseek-v4.1-flash-z$1.20 / 1M out
- elephant$0.300 / 1M out
- hermes/mercury-oss-120b$0.250 / 1M out
- hermes/mercury-oss-20b$0.150 / 1M out
- inclusionai/ling-2.6-1t$2.50 / 1M out
- inclusionai/ling-2.6-flash$0.300 / 1M out
- inclusionai/ling-3.0-flash-fast$0.180 / 1M out
- inclusionai/ring-2.6-1t$2.50 / 1M out
- kwaipilot/kat-coder-pro$1.20 / 1M out
- meta-llama/llama-3-70b-instruct$0.740 / 1M out
- meta-llama/llama-3-8b-instruct$0.040 / 1M out
- meta-llama/llama-3.2-3b-instruct$0.050 / 1M out
- minimax/minimax-m2.5-highspeed$2.40 / 1M out
- mistralai/mistral-nemo$0.170 / 1M out
- nousresearch/nous-hermes-llama2-13b$0.170 / 1M out
- openchat/openchat-7b$0.060 / 1M out
- qwen/qwen-2-7b-instruct$0.054 / 1M out
- qwen/qwen-2-vl-72b-instruct$0.450 / 1M out
- qwen/qwen2.5-7b-instruct$0.070 / 1M out
- qwen/qwen2.5-vl-72b-instruct$0.800 / 1M out
- qwen/qwen3-235b-a22b-fp8$0.800 / 1M out
- qwen/qwen3-30b-a3b-fp8$0.450 / 1M out
- qwen/qwen3-32b-fp8$0.450 / 1M out
- qwen/qwen3-4b-fp8$0.030 / 1M out
- qwen/qwen3-8b-fp8$0.138 / 1M out
- qwen/qwen3-coder-30b-a3b-instruct$0.270 / 1M out
- qwen/qwen3-embedding-0.6b5 parameters
- qwen/qwen3-max$8.45 / 1M out
- qwen/qwen3-next-80b-a3b-thinking$1.50 / 1M out
- qwen/qwen3-omni-30b-a3b-instruct$0.970 / 1M out
- qwen/qwen3-vl-30b-a3b-thinking$1.00 / 1M out
- qwen/qwen3-vl-8b-instruct$0.500 / 1M out
- sao10k/l3-8b-lunaris$0.050 / 1M out
- sao10k/l31-70b-euryale-v2.2$1.48 / 1M out
- teknium/openhermes-2.5-mistral-7b$0.170 / 1M out
- xiaomimimo/mimo-v2-flash$0.330 / 1M out
- xiaomimimo/mimo-v2-pro$6.00 / 1M out
- zai-org/glm-4.5$2.20 / 1M out
- zai-org/glm-5-turbo$4.00 / 1M out
- zai-org/glm-5v-turbo$4.00 / 1M out