Phala
19 modelsProvider docs
As of Nov 22, 2026, Phala lists 19 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash 1017, GLM-5.3-Flash, GLM-5.3, Qwen3.8 27B and DeepSeek V4 Flash 0731 across the deepseek-flash, glm-flash, glm, qwen, kimi and gemma families. The cheapest rate in the table is Qwen2.5 7B Instruct at $0.2 per 1M output tokens, the priciest Kimi K3 at $15. On a 3:1 input:output blend the metered rates span $0.125–$6 per 1M tokens, and every price is Phala's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
19 of 19 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.75 | $1.6 | $0.15 | 1.0M | Oct 17, 2026 |
| GLM-5.3-Flash | $0.15 | $0.5 | $0.03 | 1.0M | Aug 26, 2026 |
| GLM-5.3 | $1.4 | $4.4 | $0.26 | 1.0M | Aug 14, 2026 |
| Qwen3.8 27B | $0.2 | $2.5 | $0.05 | 1.0M | Aug 14, 2026 |
| DeepSeek V4 Flash 0731 | $0.44 | $1.32 | $0.028 | 1.0M | Jul 31, 2026 |
| Kimi K3 | $3 | $15 | $0.3 | 1.0M | Jul 16, 2026 |
| GLM-5.2 | $1.26 | $3 | $0.22 | 1.0M | Jun 13, 2026 |
| Qwen3.6 27B | $0.32 | $3.25 | $0.03 | 262k | Apr 22, 2026 |
| Kimi K2.6 | $1.09 | $4.6 | $0.37 | 262k | Apr 20, 2026 |
| Qwen3.6 35B-A3B | $0.2 | $1.27 | $0.056 | 262k | Apr 17, 2026 |
| GLM-5.1 | $1.21 | $4.2 | $0.6 | 203k | Apr 7, 2026 |
| Gemma 4 31B IT | $0.15 | $0.46 | $0.075 | 262k | Apr 2, 2026 |
| Qwen3.5 27B | $0.3 | $2.4 | $0.03 | 262k | Feb 23, 2026 |
| Qwen3.5 397B-A17B | $0.55 | $3.5 | $0.225 | 262k | Feb 15, 2026 |
| DeepSeek V3.2 | $1 | $1 | $0.5 | 164k | Dec 1, 2025 |
| Qwen3 VL 30B A3B Instruct | $0.2 | $0.7 | $0.03 | 128k | Oct 4, 2025 |
| GPT OSS 120B | $0.15 | $0.6 | — | 131k | Aug 5, 2025 |
| Llama-3.3-70B-Instruct | $2 | $2 | — | 131k | Dec 6, 2024 |
| Qwen2.5 7B Instruct | $0.1 | $0.2 | — | 33k | Sep 19, 2024 |