# sference model cards

> One card per live model: pricing, specs, portfolio comparison, quickstart, and curated positioning. Index page: https://sference.com/models

- [Kimi K3](https://sference.com/models/moonshotai/Kimi-K3) — `moonshotai/Kimi-K3`: $3.00 in / $15.00 out / $0.45 cached input, per 1M tokens, 1M context
- [GLM 5.3](https://sference.com/models/zai-org/GLM-5.3) — `zai-org/GLM-5.3`: $1.20 in / $4.20 out / $0.26 cached input, per 1M tokens, 1M context
- [DeepSeek V4.1 Flash](https://sference.com/models/deepseek-ai/DeepSeek-V4.1-Flash) — `deepseek-ai/DeepSeek-V4.1-Flash`: $0.50 in / $1.50 out / $0.05 cached input, per 1M tokens, 1M context
- [GLM 5.3 Flash](https://sference.com/models/zai-org/GLM-5.3-Flash) — `zai-org/GLM-5.3-Flash`: $0.20 in / $0.60 out / $0.07 cached input, per 1M tokens, 1M context
- [DeepSeek V4 Flash (0731)](https://sference.com/models/deepseek-ai/DeepSeek-V4-Flash-0731) — `deepseek-ai/DeepSeek-V4-Flash-0731`: $0.28 in / $0.56 out / $0.07 cached input, per 1M tokens, 1M context
- [Clef 27B](https://sference.com/models/Cloudflare/clef) — `Cloudflare/clef`: billed on input tokens only: $0.24 per 1M input tokens, 64K context