Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Deepseek-R1-Distill-Qwen-32b deepseek/deepseek-r1-distill-qwen-32b | Uform-Gen2-Qwen-500m unum/uform-gen2-qwen-500m | |
|---|---|---|
| Provider | DeepSeek | Unum |
| Family | Qwen | Qwen |
| Modality | reasoning | vision |
| Context window | 80,000 tok | 4,096 tok |
| Max output | 4,096 tok | 4,096 tok |
| Released | 2025-01-22 | 2024-02-27 |
| Input price | $0.500 /1M | $0.0000 /img |
| Output price | $4.88 /1M | — |
| Cache read | — | — |
| Tools | — | — |
| Streaming | yes | yes |
| Vision | — | yes |
| JSON mode | yes | — |
| Reasoning | yes | — |
| Prompt caching | — | — |
DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Deepseek-R1-Distill-Qwen-32b
client.chat.completions.create(
model="deepseek/deepseek-r1-distill-qwen-32b",
messages=[{"role":"user","content":"hello"}],
)
# Try Uform-Gen2-Qwen-500m — same client, same key
client.chat.completions.create(
model="unum/uform-gen2-qwen-500m",
messages=[{"role":"user","content":"hello"}],
)