Qiniu serves 22 of the models we track. We do not support bring-your-own-key for this provider yet.
| Model | Made by | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| MiMo V2 Flash | Xiaomi | $0.1 | $0.3 | 256K |
| Qwen3-Next 80B-A3B Instruct | Alibaba | — | — | 131K |
| Gemini 2.0 Flash | — | — | 1.0M | |
| Claude 3.5 Sonnet | Anthropic | — | — | 200K |
| Qwen Turbo | Alibaba | — | — | 1.0M |
| Gemini 2.5 Flash Lite | — | — | 1.0M | |
| GPT-OSS 20B | OpenAI | — | — | 128K |
| Qwen3.5 397B-A17B | Alibaba | — | — | 256K |
| DeepSeek R1 | DeepSeek | — | — | 128K |
| DeepSeek R1 0528 | DeepSeek | — | — | 128K |
| GLM-4.5 | Zhipu AI | — | — | 131K |
| Claude 3.5 Haiku | Anthropic | — | — | 200K |
| Claude 3.7 Sonnet | Anthropic | — | — | 200K |
| Qwen3 235B-A22B Instruct 2507 | Amazon Bedrock | — | — | 262K |
| GPT-OSS 120B | OpenAI | — | — | 128K |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | — | — | 262K |
| Gemini 2.5 Pro | — | — | 1.0M | |
| Gemini 2.5 Flash | — | — | 1.0M | |
| DeepSeek V3.1 | DeepSeek | — | — | 128K |
| Kimi K2 0905 | NVIDIA | — | — | 256K |
| GLM-4.5-Air | Zhipu AI | — | — | 131K |
| Kimi K2 Thinking | Vertex | — | — | 256K |
Qiniu serves 22 of the models we track, across 1 model type.
MiMo V2 Flash at $0.1 per million input tokens.
Not yet — Qiniu is not currently one of the providers Serenities supports for bring-your-own-key.
