Novita AI
Inference platform with language models and image, video, text-to-speech and voice-cloning APIs.
Models on Novita AI 11
A curated selection, with links to other providers for the same model.
Explore imported models by type. Image and video categories refer to generation; image understanding is available under Vision.
Artificial Analysis Intelligence Index ↗ · Higher is better · Checked 2026-10-02
Rank among verified models in this catalog. Best published configuration per model; equal scores share a rank. Scores are rounded by the source. Unverified and non-language models appear last without a rank. Methodology ↗11 models
| Rank | Model | Intelligence | Best price | Input → output | Providers |
|---|---|---|---|---|---|
| #13 |  Kimi K3Moonshot AI | 44max | $2.7 in / $13.5 outUSD / 1M tokensOpenRouter Router catalog · Lowest listed input price; output is from the same tariff. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Compare prices → | text, image, video → text | DeepInfraFireworks AINovita AIOpenRouterTogether AI |
| #23 |  DeepSeek V4 Pro 0813Deepseek | 36max | $0.66 in / $1.98 outUSD / 1M tokensDeepSeek Off-peak · Lowest listed input price; output is from the same tariff. Time-of-day tariff; consult official source for UTC peak/off-peak windows and alias behavior. Compare prices → | text → text | DeepSeekNovita AIOpenRouter |
| #31 |  MiniMax M3MiniMax | 29Published configuration | $0.3 in / $1.2 outUSD / 1M tokensOpenRouter Router catalog · Lowest listed input price; output is from the same tariff. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Compare prices → | text, image, video → text | Novita AIOpenRouter |
| — |  Fish Audio TTSFish Audio | —Not comparable | Price not collected | text → audio | Novita AI |
| — |  GLM 5.2Z Ai | —Not verified | $0.41 in / $3.99 outUSD / 1M tokensOpenRouter Router catalog · Lowest listed input price; output is from the same tariff. OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Compare prices → | text → text | Novita AIOpenRouter |
| — |  Hailuo 2.3MiniMax | —Not comparable | From $0.35USD / generationSegmind Resolution=768p / Duration=6 · Starting tariff; final cost depends on the selected settings. Total listed price per generation for exactly these parameters. Compare prices → | text, image → video | Novita AISegmind |
| — | Hailuo 2.3 FastMiniMax | —Not comparable | Price not collected | text, image → video | Novita AI |
| — | MiniMax Voice CloningMiniMax | —Not comparable | Price not collected | audio → voice profile | Novita AI |
| — |  Qwen-ImageAlibaba / Qwen | —Not comparable | Price not collected | text → image | Novita AI |
| — | Qwen-Image EditAlibaba / Qwen | —Not comparable | From $0.0043USD / gpu secondSegmind Serverless · Starting tariff; final cost depends on the selected settings. Billed per GPU compute second, not generated media duration. Runtime varies. Compare prices → | text, image → image | Novita AISegmind |
| — | Qwen3.8 FlashAlibaba / Qwen | —Not verified | $0.15 in / $0.47 outUSD / 1M tokensNovita AI Standard · Lowest listed input price; output is from the same tariff. Decimal USD per million fields from the provider; tiered entries require separate mapping. Compare prices → | text, image, video → text | Novita AIOpenRouter |
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Benchmark scores are a dated snapshot, not a live feed or a universal measure of quality. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.