openPangu 2.0 Flash
by Huawei Cloud MAAS · family pangu · listed Jun 2026RTW
Huawei's 92B MoE lightweight (6B active) for fast agents and 512K context work, Ascend-native with slow/fast thinking
Current rates USD per 1M tokens
Input$0.12
Output$0.24
Cache read$0.03
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
openpangu-2.0-flash- Context window
- 524K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jun 2026
- Released
- 2026-06-30
- Last updated
- 2026-06-30
← All Huawei Cloud MAAS listings