Wally model pricing
As of November 7, 2026, 9 Wally models are available through LiteLLM. The most recently added are DeepSeek V4 Pro Fast, DeepSeek V4.1 Flash F2, DeepSeek V4.1 Flash Fast. Prices below are Wally's list prices.
Cheapest chat models on Wally
Sorted by Wally's own prices, blended at 3 input tokens per output token. Active chat models only.
| # | Model | Blended per 1M | Input / output per 1M | Context |
|---|---|---|---|---|
| 1 | GLM 5.3 Flash | $0.3665 | $0.272 / $0.65 | 1M |
| 2 | DeepSeek V4.1 Flash | $0.525 | $0.30 / $1.20 | 1M |
| 3 | DeepSeek V4.1 Flash F2 | $0.525 | $0.30 / $1.20 | 1M |
| 4 | MiniMax M3 | $0.5775 | $0.33 / $1.32 | 524K |
| 5 | DeepSeek V4 Flash | $0.66 | $0.44 / $1.32 | 1M |
| 6 | DeepSeek V4.1 Flash Fast | $1.05 | $0.60 / $2.40 | 1M |
| 7 | DeepSeek V4 Pro Fast | $2.39 | $1.91 / $3.83 | 1M |
| 8 | GLM 5.3 Fast | $3.225 | $2.10 / $6.60 | 1M |
| 9 | Kimi K3 | $6.00 | $3.00 / $15.00 | 1M |
Wally models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| DeepSeek V4 Pro Fast | DeepSeek | $1.91 / $3.83 per 1M tokens | 1M | 1 | Nov 2026 |
| DeepSeek V4.1 Flash F2 | DeepSeek | $0.30 / $1.20 per 1M tokens | 1M | 1 | Nov 2026 |
| DeepSeek V4.1 Flash Fast | DeepSeek | $0.60 / $2.40 per 1M tokens | 1M | 4 | Sep 2026 |
| GLM 5.3 Fast | Z.ai | $2.10 / $6.60 per 1M tokens | 1M | 4 | Sep 2026 |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 / $1.20 per 1M tokens | 1M | 25 | Sep 2026 |
| GLM 5.3 Flash | Z.ai | $0.272 / $0.65 per 1M tokens | 1M | 24 | Aug 2026 |
| Kimi K3 | Moonshot AI | $3 / $15 per 1M tokens | 1M | 21 | Aug 2026 |
| DeepSeek V4 Flash | DeepSeek | $0.44 / $1.32 per 1M tokens | 1M | 30 | Jun 2026 |
| MiniMax M3 | MiniMax | $0.33 / $1.32 per 1M tokens | 524K | 16 | Jun 2026 |