MagmaRouter

Models.

Our signature line of Xploded models are normal open weight models with the refusals taken out. Prices are what you pay, per million tokens.

The line

The models MagmaRouter sells under its own name. Each one is a real frontier model with the refusal training taken off it.

1.05M ctx · $2.00 in · $5.00 outCached reads $1.00 per MtokGLM 5.3 Xplodedglm-5.3-xplodedIntelligence 100View the model

1.05M ctx · $0.30 in · $1.00 outCached reads $0.20 per MtokGLM 5.3 Flash Xplodedglm-5.3-flash-xplodedIntelligence 93View the model

1.05M ctx · $1.25 in · $2.50 outCached reads $0.30 per MtokDeepSeek V4.1 Flash 1017 Xplodeddeepseek-v4.1-flash-1017-xplodedIntelligence 87View the model

512k ctx · $0.36 in · $1.44 outCached reads $0.03 per MtokDeepSeek Flash Lite Xplodeddeepseek-v4.1-flash-lite-1017-xplodedIntelligence 87View the model

1.05M ctx · $1.00 in · $2.00 outCached reads $0.50 per MtokMiMo V2.6 Flash Xplodedmimo-v2.6-flash-xplodedIntelligence 84View the model

1.05M ctx · $1.50 in · $5.00 outCached reads $0.50 per MtokQwen3.8 27B Xplodedqwen3.8-27b-xplodedIntelligence 76View the model

524k ctx · $1.75 in · $5.50 outCached reads $0.50 per MtokQwen3.8 27B Ultrafast Xplodedqwen3.8-27b-fast-xplodedIntelligence 76View the model

Loading the catalogue...

* Intelligence is the Artificial Analysis Intelligence Index of the model each one is built on, scaled so the strongest in the line reads 100. Removing refusals does not change what a model knows.

Looking for an uncensored GPT, Claude, Gemini or Grok?

Most frontier models have no uncensored version you can buy. Each page below says what exists for that model and which Xploded model is the closest match.

Uncensored families on sale: GLM · Qwen · MiMo · DeepSeek

Claude Opus 5.5 uncensoredAnthropic, scores 58 Claude Sonnet 5.5 uncensoredAnthropic, scores 56 Gemini 4 Argon uncensoredGoogle, scores 53 GPT-6 Astra uncensoredOpenAI, scores 53 Claude Fable 5.1 uncensoredAnthropic, scores 53 GPT-6.1 Sol uncensoredOpenAI, scores 52 GPT-6 Sol uncensoredOpenAI, scores 48 K2 Horizon 375B A23B uncensoredK2, scores 47 Mistral Large 4 uncensoredMistral, scores 38 Muse Spark 1.3 uncensoredMeta, scores 48 Kimi K3.1 Pro uncensoredMoonshot AI, scores 55 MiMo V2.6 Pro uncensoredXiaomi, scores 46 Grok 4.7 uncensoredxAI, scores 46 GLM 5.3 uncensoredZ.ai, scores 45 Qwen3.8 Max uncensoredAlibaba, scores 45 Step 5 uncensoredStepFun, scores 44 Kimi K3 uncensoredMoonshot AI, scores 44 GPT-5.6 Terra uncensoredOpenAI, scores 42 GLM 5.3 Flash uncensoredZ.ai, scores 42 Ling 3.1 Flash uncensoredInclusionAI, scores 41 Gemini 3.8 Flash uncensoredGoogle, scores 41 Qwen3.8 2.4T A95B uncensoredAlibaba, scores 40 Qwen3.8 Flash Next uncensoredAlibaba, scores 40 DeepSeek V4.1 Flash uncensoredDeepSeek, scores 39 MiMo V2.6 Flash uncensoredXiaomi, scores 38 GPT-6 Luna uncensoredOpenAI, scores 38 DeepSeek V4 Pro uncensoredDeepSeek, scores 36 DeepSeek V4 Flash Vision uncensoredDeepSeek, scores 35 Qwen3.8 27B uncensoredAlibaba, scores 34 K2 Horizon uncensoredK2, scores 31 Gemini 3.1 Pro uncensoredGoogle, scores 30 MiniMax M3 uncensoredMiniMax, scores 29 GPT-5.5 Instant uncensoredOpenAI, scores 26 Kimi K2.7 Code uncensoredMoonshot AI, scores 26 Inkling Small uncensoredThinking Machines, scores 26 Inkling uncensoredThinking Machines, scores 25 Hy3 uncensoredTencent, scores 25 Qwen3.7 Plus uncensoredAlibaba, scores 25 K2 Horizon MoVA 36B uncensoredK2, scores 25 Solar Mini 4 uncensoredUpstage, scores 24 Nemotron 3 Ultra uncensoredNVIDIA, scores 23 Gemini 3.5 Flash-Lite uncensoredGoogle, scores 22 Ling 3.0 Flash uncensoredInclusionAI, scores 20 LongCat 2.0 uncensoredLongCat, scores 19 Qwen3.5 397B A17B uncensoredAlibaba, scores 18 Qwen3.6 35B A3B uncensoredAlibaba, scores 18 Muse Glimmer uncensoredMeta, scores 17 Ring 2.6 1T uncensoredInclusionAI, scores 17 Claude Haiku 4.5 uncensoredAnthropic, scores 17 Qwen3.5 122B A10B uncensoredAlibaba, scores 16 Gemma 4 31B uncensoredGoogle, scores 15 Mistral Medium 3.5 uncensoredMistral, scores 14 Nemotron 3 Super 120B uncensoredNVIDIA, scores 13 Command A+ uncensoredCohere, scores 13