Approved models
19
Records published from this collection
Provider information
inference host
Review approach
Verify each model’s source, terms, capabilities, and current availability
Deepinfra via Requesty is a routing collection created from Requesty’s public model catalogue. It groups the model IDs that Requesty currently exposes through the deepinfra 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 deepinfra 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 |
|---|---|---|---|---|---|
| Qwen3.5 2B Deepinfra via Requesty | 55.2 | 262.1K | $0.02 | $0.10 | — |
| Seed 1.8 Deepinfra via Requesty | 55.1 | 256K | $0.25 | $2.00 | — |
| Seed 2.0 Mini Deepinfra via Requesty | 55.1 | 256K | $0.10 | $0.40 | — |
| Seed 2.0 Pro Deepinfra via Requesty | 55.1 | 256K | $0.50 | $3.00 | — |
| Qwen3 235B A22B Thinking 2507 Deepinfra via Requesty | 50.2 | 262.1K | $0.23 | $2.30 | — |
| Seed 2.0 Code Deepinfra via Requesty | 50.1 | 256K | $0.50 | $3.00 | — |
| Qwen3 235B A22B Instruct 2507 Deepinfra via Requesty | 35.2 | 262.1K | $0.07 | $0.10 | — |
| Qwen3 Coder 480B A35B Instruct Turbo Deepinfra via Requesty | 35.2 | 262.1K | $0.30 | $1.00 | — |
| DeepSeek V3 Deepinfra via Requesty | 34.8 | 128K | $0.85 | $0.90 | — |
| DeepSeek V3.1 Deepinfra via Requesty | 32.9 | 163.8K | $0.30 | $1.00 | — |
| Llama 3.3 70B Instruct Turbo Deepinfra via Requesty | 31.8 | 131.1K | $0.12 | $0.30 | — |
| Meta Llama 3.1 70B Instruct Deepinfra via Requesty | 31.8 | 130.8K | $0.23 | $0.40 | — |
| Meta Llama 3.1 8B Instruct Turbo Deepinfra via Requesty | 31.8 | 131.1K | $0.02 | $0.05 | — |
| Qwen2.5 72B Instruct Deepinfra via Requesty | 31.8 | 131.1K | $0.23 | $0.40 | — |
| Llama 3.2 90B Vision Instruct Deepinfra via Requesty | 23.4 | 131.1K | $0.35 | $0.40 | — |
| Qwen2.5 Coder 32B Instruct Deepinfra via Requesty | 23.4 | 16.4K | $0.07 | $0.16 | — |
| Meta Llama 3.1 405B Instruct Deepinfra via Requesty | 21.8 | 130.8K | $0.80 | $0.80 | — |
| DeepSeek R1 Distill Llama 70B Deepinfra via Requesty | 16.4 | 64K | $0.23 | $0.69 | — |
| Phi 4 Deepinfra via Requesty | 11.8 | 16.4K | $0.07 | $0.14 | — |
19 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.