Novita
Models on Novita · prices & measurements for models served by Novita’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
 Ling 3.1 FlashInclusionAI | Free | Free | 262K | — | — | — | — | only provider |
 Llama 3.1 8B InstructMetaBEST PRICE | $0.02 | $0.05 | 16K | fp8 | ✕ | ✕ | 4/5 | cheapest here |
| Ling 3.0 Flash VLInclusionAIBEST PRICE | $0.021 | $0.062 | 262K | bf16 | ✕ | ✕ | — | cheapest here |
| Ling 3.0 FlashInclusionAIBEST PRICE | $0.021 | $0.063 | 262K | — | 0.98s° | 372° tok/s | — | cheapest here |
 gpt-oss-20bOpenAI | $0.04 | $0.15 | 131K | fp4 | ✕ | ✕ | 4/5 | $0.018 elsewhere |
 Mistral NemoMistral | $0.04 | $0.17 | 60K | fp8 | ✕ | ✕ | — | $0.018 elsewhere |
| Ling 3.0 Flash FinInclusionAIBEST PRICE | $0.042 | $0.123 | 262K | — | ✕ | ✕ | — | cheapest here |
 Nemotron 3 Nano 30B A3BNVIDIABEST PRICE | $0.05 | $0.20 | 262K | fp4 | 1.1s° | 268° tok/s | — | cheapest here |
| gpt-oss-120bOpenAI | $0.05 | $0.25 | 131K | fp4 | 0.78s° | 153° tok/s | 2/5 | $0.03 elsewhere |
 Llama 3 8B LunarisSao10K | $0.05 | $0.05 | 8K | bf16 | 0.5s° | 88° tok/s | — | $0.04 elsewhere |
 GLM 4.7 FlashZ.ai | $0.07 | $0.40 | 200K | bf16 | ✕ | ✕ | — | $0.06 elsewhere |
 Qwen3 Coder 30B A3B InstructQwenBEST PRICE | $0.07 | $0.27 | 160K | fp8 | 1.5s° | 107° tok/s | — | cheapest here |
| GLM 5.3 FlashZ.ai | $0.084 | $0.28 | 1.05M | fp8 | 4.2s° | 33° tok/s | — | $0.032 elsewhere |
| Qwen3 235B A22B Instruct 2507Qwen | $0.09 | $0.58 | 131K | fp8 | ✕ | ✕ | 5/5 | $0.087 elsewhere |
 Gemma 3 27BGoogle | $0.119 | $0.20 | 98K | bf16 | 1.8s° | 42° tok/s | 4/5 | $0.08 elsewhere |
| Gemma 4 26B A4B Google | $0.13 | $0.40 | 262K | bf16 | 1.2s° | 25° tok/s | 4/5 | $0.042 elsewhere |
| GLM 4.5 AirZ.aiBEST PRICE | $0.13 | $0.85 | 131K | bf16 | 1.9s° | 65° tok/s | — | cheapest here |
| Llama 3.3 70B InstructMeta | $0.135 | $0.40 | 12K | bf16 | ✕ | ✕ | 5/5 | $0.10 elsewhere |
 MiMo-V2.6-FlashXiaomi | $0.14 | $0.28 | 1.05M | fp8 | — | — | — | $0.10 elsewhere |
 Hy3Tencent | $0.14 | $0.58 | 262K | — | ✕ | ✕ | 2/5 | $0.13 elsewhere |
 DeepSeek V4 Flash 0423DeepSeek | $0.14 | $0.28 | 1.05M | fp8 | 0.97s° | 128° tok/s | — | $0.017 elsewhere |
| Gemma 4 31BGoogle | $0.14 | $0.40 | 262K | bf16 | ✕ | ✕ | — | $0.09 elsewhere |
| Qwen3 Next 80B A3B InstructQwen | $0.15 | $1.50 | 131K | bf16 | 1.7s° | 197° tok/s | — | $0.09 elsewhere |
| MiMo-V2.5Xiaomi | $0.168 | $0.336 | 1.05M | fp8 | 2.6s° | 29° tok/s | — | $0.119 elsewhere |
| Llama 4 ScoutMeta | $0.18 | $0.59 | 131K | bf16 | ✕ | ✕ | — | $0.10 elsewhere |
| DeepSeek V4.1 FlashDeepSeek | $0.195 | $0.78 | 1.05M | fp8 | ✕ | ✕ | — | $0.018 elsewhere |
 Step 3.7 FlashStepFunBEST PRICE | $0.20 | $1.15 | 262K | fp8 | 2.6s° | 150° tok/s | — | cheapest here |
| Qwen3 Coder NextQwen | $0.20 | $1.50 | 262K | fp8 | 3s° | 177° tok/s | — | $0.12 elsewhere |
| Qwen3 VL 30B A3B InstructQwen | $0.20 | $0.70 | 131K | bf16 | 1.4s° | 111° tok/s | — | $0.13 elsewhere |
 MiniMax M2.7MiniMax | $0.27 | $1.08 | 205K | fp8 | 1.7s° | 62° tok/s | 3/5 | $0.21 elsewhere |
| Llama 4 MaverickMeta | $0.27 | $0.85 | 1.05M | fp8 | 0.76s° | 41° tok/s | 4/5 | $0.188 elsewhere |
| MiniMax M3MiniMax | $0.30 | $1.20 | 1M | fp8 | ✕ | ✕ | — | $0.23 elsewhere |
| Qwen3.5-27BQwen | $0.30 | $2.40 | 262K | bf16 | ✕ | ✕ | 4/5 | $0.195 elsewhere |
| MiniMax M2.5MiniMax | $0.30 | $1.20 | 205K | fp8 | ✕ | ✕ | 2/5 | $0.27 elsewhere |
| MiniMax M2.1MiniMaxBEST PRICE | $0.30 | $1.20 | 205K | fp8 | ✕ | ✕ | — | cheapest here |
| GLM 4.6VZ.aiBEST PRICE | $0.30 | $0.90 | 131K | bf16 | 3.5s° | 72° tok/s | — | cheapest here |
| MiniMax M2MiniMax | $0.30 | $1.20 | 205K | fp8 | 1.5s° | 128° tok/s | — | $0.255 elsewhere |
| Qwen3 VL 235B A22B InstructQwen | $0.30 | $1.50 | 131K | bf16 | ✕ | ✕ | — | $0.20 elsewhere |
| Qwen3 235B A22B Thinking 2507Qwen | $0.30 | $3.00 | 131K | fp8 | 3.3s° | 35° tok/s | — | $0.23 elsewhere |
| Qwen3 Coder 480B A35BQwen | $0.38 | $1.55 | 262K | fp8 | 1.8s° | 64° tok/s | — | $0.22 elsewhere |
| Qwen2.5 72B InstructQwen | $0.38 | $0.40 | 32K | bf16 | ✕ | ✕ | — | $0.36 elsewhere |
| Qwen3.5-122B-A10BQwen | $0.40 | $3.20 | 262K | bf16 | 1.8s° | 128° tok/s | 4/5 | $0.26 elsewhere |
| DeepSeek V4 Flash 0731DeepSeek | $0.409 | $1.23 | 1.05M | fp8 | ✕ | ✕ | — | $0.01 elsewhere |
| GLM 5.3Z.ai | $0.42 | $1.32 | 1.05M | fp8 | ✕ | ✕ | — | $0.039 elsewhere |
| Qwen3.8 27BQwen | $0.42 | $3.00 | 1M | — | ✕ | ✕ | — | $0.024 elsewhere |
 ERNIE 4.5 VL 424B A47B Baidu | $0.42 | $1.25 | 123K | fp16 | 3.3s° | 39° tok/s | — | only provider |
| MiMo-V2.6-ProXiaomi | $0.435 | $0.87 | 1.05M | fp8 | ✕ | ✕ | — | $0.43 elsewhere |
| DeepSeek V4 Flash Vision ExpDeepSeek | $0.44 | $1.32 | 1.05M | — | ✕ | ✕ | — | $0.216 elsewhere |
| MiMo-V2.5-ProXiaomi | $0.48 | $0.96 | 1.05M | — | 2.2s° | 23° tok/s | 4/5 | $0.304 elsewhere |
| GLM 4.7Z.ai | $0.54 | $1.98 | 205K | fp8 | 6.7s° | 37° tok/s | 5/5 | $0.40 elsewhere |
| GLM 4.6Z.ai | $0.55 | $2.20 | 205K | bf16 | 3.7s° | 42° tok/s | 2/5 | $0.43 elsewhere |
| MiniMax M1MiniMax | $0.55 | $2.20 | 1M | bf16 | ✕ | ✕ | — | $0.40 elsewhere |
 Kimi K2.5Moonshot AI | $0.57 | $2.85 | 262K | — | 2.2s° | 54° tok/s | — | $0.45 elsewhere |
| Kimi K2 0711Moonshot AI | $0.57 | $2.30 | 131K | fp8 | 3.1s° | 55° tok/s | — | only provider |
| Qwen3.5 397B A17BQwen | $0.60 | $3.60 | 262K | — | 1.3s° | 126° tok/s | — | $0.39 elsewhere |
| Kimi K2 ThinkingMoonshot AIBEST PRICE | $0.60 | $2.50 | 262K | bf16 | 2.2s° | 206° tok/s | — | cheapest here |
| Kimi K2 0905Moonshot AI | $0.60 | $2.50 | 262K | fp8 | 0.88s° | 44° tok/s | — | only provider |
| GLM 4.5VZ.aiBEST PRICE | $0.60 | $1.80 | 66K | fp8 | 2.3s° | 51° tok/s | — | cheapest here |
 WizardLM-2 8x22BMicrosoft | $0.62 | $0.62 | 66K | bf16 | ✕ | ✕ | — | only provider |
| GLM 5.2Z.ai | $0.65 | $2.04 | 1.05M | fp8 | 1.6s° | 68° tok/s | 3/5 | $0.03 elsewhere |
| R1 0528DeepSeek | $0.70 | $2.50 | 164K | fp8 | 1.8s° | 20° tok/s | — | $0.50 elsewhere |
| R1DeepSeek | $0.70 | $2.50 | 64K | fp8 | ✕ | ✕ | — | only provider |
| Kimi K2.6Moonshot AI | $0.80 | $3.40 | 262K | — | ✕ | ✕ | — | $0.465 elsewhere |
| Hy4 previewTencentBEST PRICE | $0.834 | $2.50 | 1M | fp8 | ✕ | ✕ | — | cheapest here |
| Kimi K2.7 CodeMoonshot AI | $0.912 | $3.84 | 262K | int4 | ✕ | ✕ | — | $0.671 elsewhere |
| Qwen3 VL 235B A22B ThinkingQwen | $0.98 | $3.95 | 131K | bf16 | 2.9s° | 54° tok/s | — | $0.40 elsewhere |
| DeepSeek V4 Pro 0813DeepSeek | $0.99 | $2.97 | 1.05M | fp8 | 1s° | 76° tok/s | 4/5 | $0.158 elsewhere |
| GLM 5Z.ai | $1.00 | $3.20 | 203K | fp8 | ✕ | ✕ | — | $0.60 elsewhere |
| GLM 5.1Z.ai | $1.38 | $4.40 | 205K | fp8 | ✕ | ✕ | — | $0.966 elsewhere |
| Llama 3.1 Euryale 70B v2.2Sao10K | $1.45 | $1.45 | 8K | fp8 | 0.49s° | 45° tok/s | — | $0.85 elsewhere |
| DeepSeek V4 Pro 0423DeepSeek | $1.60 | $3.20 | 1.05M | fp8 | 1.6s° | 72° tok/s | — | $0.30 elsewhere |
| Qwen3.8 2.4T A95BQwenBEST PRICE | $2.00 | $6.00 | 1M | — | ✕ | ✕ | — | cheapest here |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for Novita’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page