Approved models
21
Records published from this collection
Provider information
inference host
Review approach
Verify each model’s source, terms, capabilities, and current availability
Novita via Requesty is a routing collection created from Requesty’s public model catalogue. It groups the model IDs that Requesty currently exposes through the novita route so readers can inspect the exact identifier, documented context window, pricing metadata, and capability flags recorded by the catalogue.
A routing collection is not a statement that novita developed every underlying model, nor does it guarantee a particular region, uptime, support plan, price, or data policy. Those details can vary by route and model version. This page preserves the catalogue source so every record can be verified before publication.
Each linked model remains an editorial draft until its facts and source are reviewed. Approval is separate from catalogue membership: only explicitly approved pages may be visible publicly or enter the sitemap.
Review each record individually; collection membership does not imply a recommendation or guarantee of availability.
| Model | Capability▼ | Context | Input $/1M | Output $/1M | Speed |
|---|---|---|---|---|---|
| Deepseek V3.2 Novita via Requesty | 50.5 | 163.8K | $0.27 | $0.40 | — |
| Ring 2.6 1t Novita via Requesty | 45.2 | 262.1K | $0.30 | $2.50 | — |
| Llama 4 Maverick 17b 128e Instruct Fp8 Novita via Requesty | 36.9 | 1.0M | $0.20 | $0.85 | — |
| Ling 2.6 1t Novita via Requesty | 30.2 | 262.1K | $0.30 | $2.50 | — |
| Ling 2.6 Flash Novita via Requesty | 30.2 | 262.1K | $0.10 | $0.30 | — |
| Kat Coder Pro Novita via Requesty | 30.1 | 256K | $0.30 | $1.20 | — |
| Kimi K2 Instruct Novita via Requesty | 26.8 | 131.1K | $0.57 | $2.30 | — |
| Deepseek V3 0324 Novita via Requesty | 26.7 | 128K | $0.40 | $1.30 | — |
| Deepseek V3 Turbo Novita via Requesty | 26.7 | 128K | $0.40 | $1.30 | — |
| Deepseek R1 Turbo Novita via Requesty | 23.4 | 64K | $0.70 | $2.50 | — |
| Deepseek V3 Novita via Requesty | 23.4 | 64K | $0.89 | $0.89 | — |
| Qwen 2.5 72b Instruct Novita via Requesty | 20.0 | 32K | $0.38 | $0.40 | — |
| Baichuan M2 32b Novita via Requesty | 16.8 | 131.1K | $0.07 | $0.07 | — |
| Qwen3 235b A22b Fp8 Novita via Requesty | 16.7 | 128K | $0.20 | $0.80 | — |
| Wizardlm 2 8x22b Novita via Requesty | 13.5 | 65.5K | $0.62 | $0.62 | — |
| Mythomax L2 13b Novita via Requesty | 10.1 | 4.1K | $0.09 | $0.09 | — |
| Deepseek R1 Distill Llama 70b Novita via Requesty | 10.0 | 32K | $0.80 | $0.80 | — |
| Llama 3.1 8b Instruct Novita via Requesty | 6.8 | 16.4K | $0.05 | $0.05 | — |
| L31 70b Euryale V2.2 Novita via Requesty | 6.7 | 16K | $1.48 | $1.48 | — |
| L3 8b Lunaris Novita via Requesty | 3.5 | 8.2K | $0.05 | $0.05 | — |
| L3 8b Stheno V3.2 Novita via Requesty | 3.5 | 8.2K | $0.05 | $0.05 | — |
21 models · click a column to sort
About the capability score: a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.