NA
Novita AI
novita
· 73 models · synced never
Cost-effective APIs for open-source LLMs and image models.
| Model | Type | Input $/MTok | Output $/MTok | Context | Upstream ID |
|---|---|---|---|---|---|
| Llama 3.1 8B Instruct meta-llama | LLM | $0.02 | $0.05 | 16K | meta-llama/llama-3.1-8b-instruct |
| Ling 3.0 Flash inclusionai | LLM | $0.021 | $0.063 | 262K | inclusionai/ling-3.0-flash |
| Ling 3.0 Flash VL inclusionai | LLM | $0.021 | $0.0616 | 262K | inclusionai/ling-3.0-flash-vl |
| Mistral Nemo mistralai | LLM | $0.04 | $0.17 | 60K | mistralai/mistral-nemo |
| gpt-oss-20b (batch) openai | LLM | $0.04 | $0.15 | 131K | openai/gpt-oss-20b |
| Llama 3 8B Lunaris sao10k | LLM | $0.05 | $0.05 | 8K | sao10k/l3-lunaris-8b |
| Nemotron 3 Nano 30B A3B nvidia | LLM | $0.05 | $0.2 | 262K | nvidia/nemotron-3-nano-30b-a3b |
| gpt-oss-120b (batch) openai | LLM | $0.05 | $0.25 | 131K | openai/gpt-oss-120b |
| GLM 4.7 Flash z-ai | LLM | $0.07 | $0.4 | 200K | z-ai/glm-4.7-flash |
| Qwen3 Coder 30B A3B Instruct qwen | LLM | $0.07 | $0.27 | 160K | qwen/qwen3-coder-30b-a3b-instruct |
| Qwen3 235B A22B Instruct 2507 qwen | LLM | $0.09 | $0.58 | 131K | qwen/qwen3-235b-a22b-2507 |
| Gemma 3 27B google | LLM | $0.119 | $0.2 | 98K | google/gemma-3-27b-it |
| GLM 4.5 Air z-ai | LLM | $0.13 | $0.85 | 131K | z-ai/glm-4.5-air |
| Gemma 4 26B A4B (free) google | LLM | $0.13 | $0.4 | 262K | google/gemma-4-26b-a4b-it |
| GLM 5.3 Flash (batch) z-ai | LLM | $0.132 | $0.44 | 1.0M | z-ai/glm-5.3-flash |
| Llama 3.3 70B Instruct meta-llama | LLM | $0.135 | $0.4 | 12K | meta-llama/llama-3.3-70b-instruct |
| DeepSeek V4 Flash 0423 deepseek | LLM | $0.14 | $0.28 | 1.0M | deepseek/deepseek-v4-flash |
| Gemma 4 31B (free) google | LLM | $0.14 | $0.4 | 262K | google/gemma-4-31b-it |
| Hy3 tencent | LLM | $0.14 | $0.58 | 262K | tencent/hy3 |
| Qwen3 Next 80B A3B Instruct qwen | LLM | $0.15 | $1.50 | 131K | qwen/qwen3-next-80b-a3b-instruct |
| MiMo-V2.5 xiaomi | STT | $0.168 | $0.336 | 1.0M | xiaomi/mimo-v2.5 |
| Llama 4 Scout meta-llama | LLM | $0.18 | $0.59 | 131K | meta-llama/llama-4-scout |
| Qwen3 Coder Next qwen | LLM | $0.2 | $1.50 | 262K | qwen/qwen3-coder-next |
| Qwen3 VL 30B A3B Instruct qwen | LLM | $0.2 | $0.7 | 131K | qwen/qwen3-vl-30b-a3b-instruct |
| Step 3.7 Flash stepfun | LLM | $0.2 | $1.15 | 262K | stepfun/step-3.7-flash |
| DeepSeek V3.2 deepseek | LLM | $0.269 | $0.4 | 164K | deepseek/deepseek-v3.2 |
| DeepSeek V3.1 deepseek | LLM | $0.27 | $1.00 | 131K | deepseek/deepseek-chat-v3.1 |
| DeepSeek V3.1 Terminus deepseek | LLM | $0.27 | $1.00 | 131K | deepseek/deepseek-v3.1-terminus |
| DeepSeek V3.2 Exp deepseek | LLM | $0.27 | $0.41 | 164K | deepseek/deepseek-v3.2-exp |
| Llama 4 Maverick meta-llama | LLM | $0.27 | $0.85 | 1.0M | meta-llama/llama-4-maverick |
| MiniMax M2.7 minimax | LLM | $0.27 | $1.08 | 205K | minimax/minimax-m2.7 |
| DeepSeek V4.1 Flash (batch) deepseek | LLM | $0.285 | $1.14 | 1.0M | deepseek/deepseek-v4.1-flash |
| GLM 4.6V z-ai | LLM | $0.3 | $0.9 | 131K | z-ai/glm-4.6v |
| MiniMax M2 minimax | LLM | $0.3 | $1.20 | 205K | minimax/minimax-m2 |
| MiniMax M2.1 minimax | LLM | $0.3 | $1.20 | 205K | minimax/minimax-m2.1 |
| MiniMax M2.5 minimax | LLM | $0.3 | $1.20 | 205K | minimax/minimax-m2.5 |
| MiniMax M3 minimax | LLM | $0.3 | $1.20 | 1M | minimax/minimax-m3 |
| Qwen3 235B A22B Thinking 2507 qwen | LLM | $0.3 | $3.00 | 131K | qwen/qwen3-235b-a22b-thinking-2507 |
| Qwen3 VL 235B A22B Instruct qwen | LLM | $0.3 | $1.50 | 131K | qwen/qwen3-vl-235b-a22b-instruct |
| Qwen3.5-27B qwen | LLM | $0.3 | $2.40 | 262K | qwen/qwen3.5-27b |
| Qwen2.5 72B Instruct qwen | LLM | $0.38 | $0.4 | 32K | qwen/qwen-2.5-72b-instruct |
| Qwen3 Coder 480B A35B qwen | LLM | $0.38 | $1.55 | 262K | qwen/qwen3-coder |
| Qwen3.5-122B-A10B qwen | LLM | $0.4 | $3.20 | 262K | qwen/qwen3.5-122b-a10b |
| DeepSeek V4 Flash 0731 deepseek | LLM | $0.4092 | $1.23 | 1.0M | deepseek/deepseek-v4-flash-0731 |
| ERNIE 4.5 VL 424B A47B baidu | LLM | $0.42 | $1.25 | 123K | baidu/ernie-4.5-vl-424b-a47b |
| Qwen3.8 27B (free) qwen | LLM | $0.42 | $3.00 | 1M | qwen/qwen3.8-27b |
| DeepSeek V4 Flash Vision Exp deepseek | LLM | $0.44 | $1.32 | 1.0M | deepseek/deepseek-v4-flash-vision-exp |
| MiMo-V2.5-Pro xiaomi | LLM | $0.48024 | $0.96048 | 1.0M | xiaomi/mimo-v2.5-pro |
| GLM 4.7 z-ai | LLM | $0.54 | $1.98 | 205K | z-ai/glm-4.7 |
| GLM 4.6 z-ai | LLM | $0.55 | $2.20 | 205K | z-ai/glm-4.6 |
| MiniMax M1 minimax | LLM | $0.55 | $2.20 | 1M | minimax/minimax-m1 |
| Kimi K2 0711 moonshotai | LLM | $0.57 | $2.30 | 131K | moonshotai/kimi-k2 |
| Kimi K2.5 moonshotai | LLM | $0.57 | $2.85 | 262K | moonshotai/kimi-k2.5 |
| GLM 4.5V z-ai | LLM | $0.6 | $1.80 | 66K | z-ai/glm-4.5v |
| Kimi K2 0905 moonshotai | LLM | $0.6 | $2.50 | 262K | moonshotai/kimi-k2-0905 |
| Kimi K2 Thinking moonshotai | LLM | $0.6 | $2.50 | 262K | moonshotai/kimi-k2-thinking |
| Qwen3.5 397B A17B qwen | LLM | $0.6 | $3.60 | 262K | qwen/qwen3.5-397b-a17b |
| WizardLM-2 8x22B microsoft | LLM | $0.62 | $0.62 | 66K | microsoft/wizardlm-2-8x22b |
| GLM 5.2 (free) z-ai | LLM | $0.6496 | $2.04 | 1.0M | z-ai/glm-5.2 |
| R1 deepseek | LLM | $0.7 | $2.50 | 64K | deepseek/deepseek-r1 |
| R1 0528 deepseek | LLM | $0.7 | $2.50 | 164K | deepseek/deepseek-r1-0528 |
| GLM 5.3 (batch) z-ai | LLM | $0.7826 | $2.46 | 1.0M | z-ai/glm-5.3 |
| Kimi K2.6 moonshotai | LLM | $0.8 | $3.40 | 262K | moonshotai/kimi-k2.6 |
| R1 Distill Llama 70B deepseek | LLM | $0.8 | $0.8 | 8K | deepseek/deepseek-r1-distill-llama-70b |
| Hy4 preview tencent | LLM | $0.834 | $2.50 | 1M | tencent/hy4-preview |
| Kimi K2.7 Code moonshotai | LLM | $0.912 | $3.84 | 262K | moonshotai/kimi-k2.7-code |
| Qwen3 VL 235B A22B Thinking qwen | LLM | $0.98 | $3.95 | 131K | qwen/qwen3-vl-235b-a22b-thinking |
| DeepSeek V4 Pro 0813 deepseek | LLM | $0.99 | $2.97 | 1.0M | deepseek/deepseek-v4-pro-0813 |
| GLM 5 z-ai | LLM | $1.00 | $3.20 | 203K | z-ai/glm-5 |
| GLM 5.1 z-ai | LLM | $1.38 | $4.40 | 205K | z-ai/glm-5.1 |
| Llama 3.1 Euryale 70B v2.2 sao10k | LLM | $1.45 | $1.45 | 8K | sao10k/l3.1-euryale-70b |
| DeepSeek V4 Pro 0423 deepseek | LLM | $1.60 | $3.20 | 1.0M | deepseek/deepseek-v4-pro |
| Qwen3.8 2.4T A95B qwen | LLM | $2.00 | $6.00 | 1M | qwen/qwen3.8-2.4t-a95b |