Phala
Inference providerGlobalprices checked Oct 23, 06:00 UTC
Phala serves 22 models at a verified price. On the 21 it shares with other hosts, it is never the cheapest and charges a median 59% above it.
Models served2221 with open weights · +1 without a price
Cheapest input, per M$0.04gpt-oss-20b
Uptime, last 24 h98.7%average of its 21 OpenRouter endpoints
Sign-upCard requiredno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | not read: host terms | 1M | ✓ | $0.30 | $1.20 | $0.006 |
| Xing4.0 29B A4Bno verified price | — | 256K | — | — | — | — |
| DeepSeek V4.1 Flash | not read: host terms | 1M | ✓ | $0.21 | $0.84 | $0.0042 |
| GLM-5.3-Flash | nvfp4 | 1M | ✓ | $0.13 | $0.42 | $0.0255 |
| GLM-5.3 | not read: host terms | 1M | ✓ | $0.84 | $2.64 | $0.16 |
| Qwen3.8 27B | not read: host terms | under review | ✓ | $0.20 | $2.50 | $0.05 |
| DeepSeek V4 Pro 0813 | not read: host terms | 1M | ✓ | $1.45 | $4.36 | $0.15 |
| Nemotron 3.5 Lightning | not read: host terms | 256K | ✓ | $0.07 | $0.20 | $0.04 |
| DeepSeek V4 Flash 0731 | not read: host terms | 1M | ✓ | $0.44 | $1.32 | $0.028 |
| Kimi K3 | not read: host terms | 1M | ✓ | $2.55 | $12.75 | $0.26 |
| GLM 5.2 | fp8 | 1M | ✓ | $1.26 | $3.00 | $0.22 |
| Kimi K2.7 Code | not read: host terms | 256K | — | $0.95 | $4.00 | $0.19 |
| Qwen3.6 27B | not read: host terms | 256K | ✓ | $0.32 | $3.25 | $0.03 |
| Kimi K2.6 | not read: host terms | 256K | ✓ | $1.09 | $4.60 | $0.37 |
| Qwen3.6 35B A3B | not read: host terms | 256K | ✓ | $0.20 | $1.27 | $0.056 |
| GLM 5.1 | not read: host terms | 198K | ✓ | $1.21 | $4.20 | $0.60 |
| Qwen3.5-27B | not read: host terms | 256K | — | $0.30 | $2.40 | $0.03 |
| Qwen3.5 397B A17B | not read: host terms | 256K | ✓ | $0.55 | $3.50 | $0.23 |
| Kimi K2.5 | not read: host terms | 256K | — | $0.60 | $3.00 | $0.22 |
| DeepSeek V3.2 | not read: host terms | 160K | ✓ | $1.00 | $1.00 | $0.50 |
| gpt-oss-120b | not read: host terms | 128K | ✓ | $0.15 | $0.60 | — |
| gpt-oss-20b | not read: host terms | 128K | — | $0.04 | $0.15 | — |
| Qwen2.5 7B Instruct | — | 32K | ✓ | $0.10 | $0.20 | — |
10 of 23 models · prices per million tokens · precision and context: read at Phala's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Phala declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | Card required | docs.redpill.ai |
| Free credits | None stated | — |
| Headquarters region | Global | — |
| Price list | Where its per-token prices are published | redpill.ai |
| API documentation | Its own docs | docs.redpill.ai |
| Terms of service | Its terms | redpill.ai |
Links checked Oct 8.