Cached input $1.00 / MtokGLM 5.3 Xplodedglm-5.3-xplodedView modelModels.
The Xploded lineup consists of open-weight models with refusal training removed: uncensored and served through one endpoint, compatible with both OpenAI and Anthropic clients. Prices below are the actual settlement rates per million tokens.
The line · Model lineup
9 uncensored models, one unified endpoint. Pick the model that fits, copy its ID and start calling.
Cached input $1.00 / MtokGLM 5.3 Xplodedglm-5.3-xplodedView model
Cached input $0.20 / MtokGLM 5.3 Flash Xplodedglm-5.3-flash-xplodedView model
Cached input $0.80 / MtokKimi K3.1 Pro Xploded NEWkimi-k3.1-pro-xplodedView model
Cached input $0.60 / MtokTencent Hy4 Xploded NEWhy4-xplodedView model
Cached input $0.30 / MtokDeepSeek V4.1 Flash 1017 Xplodeddeepseek-v4.1-flash-1017-xplodedView model
Cached input $0.03 / MtokDeepSeek V4.1 Flash Lite 1017 Xploded NEWdeepseek-v4.1-flash-lite-1017-xplodedView model
Cached input $0.50 / MtokMiMo V2.6 Flash Xplodedmimo-v2.6-flash-xplodedView model
Cached input $0.50 / MtokQwen3.8 27B Xplodedqwen3.8-27b-xplodedView modelCached input $0.50 / MtokQwen3.8 27B Ultrafast Xplodedqwen3.8-27b-fast-xplodedView model| Details | ||||||||
|---|---|---|---|---|---|---|---|---|
GLM 5.3 Xplodedglm-5.3-xploded | Text only | $1.00 | $2.00 | $5.00 | 1.05M | ✓ | Online | → |
GLM 5.3 Flash Xplodedglm-5.3-flash-xploded | Text + vision | $0.20 | $0.30 | $1.00 | 1.05M | ✓ | Online | → |
Kimi K3.1 Pro Xploded NEWkimi-k3.1-pro-xploded | Text + vision | $0.80 | $7.50 | $37.50 | 1.05M | ✓ | Online | → |
Tencent Hy4 Xploded NEWhy4-xploded | Text + vision | $0.60 | $3.20 | $6.40 | 1.05M | ✓ | Online | → |
DeepSeek V4.1 Flash 1017 Xplodeddeepseek-v4.1-flash-1017-xploded | Text + vision | $0.30 | $1.25 | $2.50 | 1.05M | ✓ | Online | → |
DeepSeek V4.1 Flash Lite 1017 Xploded NEWdeepseek-v4.1-flash-lite-1017-xploded | Text + vision | $0.03 | $0.36 | $1.44 | 512K | ✓ | Online | → |
MiMo V2.6 Flash Xplodedmimo-v2.6-flash-xploded | Text + vision | $0.50 | $1.00 | $2.00 | 1.05M | ✓ | Online | → |
Qwen3.8 27B Xplodedqwen3.8-27b-xploded | Text + vision | $0.50 | $1.50 | $5.00 | 1.05M | ✓ | Online | → |
Qwen3.8 27B Ultrafast Xplodedqwen3.8-27b-fast-xploded | Text + vision | $0.50 | $1.75 | $5.50 | 524K | ✓ | Online | → |
Which model should I use?
I need the smartestKimi K3.1 Pro$7.50 in · $37.50 out / MtokThe strongest reasoner in the lineup — for hard analysis, long agentic tasks and code.I need the cheapestDeepSeek V4.1 Flash Lite 1017$0.36 in · $1.44 out / MtokThe cheapest model — the default pick for everyday chat and bulk workloads.I want a balanced all-rounderGLM 5.3 Flash$0.30 in · $1.00 out / MtokFast, inexpensive and vision-capable — quality at a low cost.
Kimi K3.1 Pro$7.50 in · $37.50 out / MtokThe strongest reasoner in the lineup — for hard analysis, long agentic tasks and code.I need the cheapestDeepSeek V4.1 Flash Lite 1017$0.36 in · $1.44 out / MtokThe cheapest model — the default pick for everyday chat and bulk workloads.I want a balanced all-rounderGLM 5.3 Flash$0.30 in · $1.00 out / MtokFast, inexpensive and vision-capable — quality at a low cost.Prices are in USD per million tokens, matching billing settlement. Context length and available capabilities follow the model provider's actual responses.