SiliconFlow models, one API key

74 models served by SiliconFlow are available through FastInfra's OpenAI-compatible endpoint — 15 of them route here by default because it is the cheapest option. Pin it explicitly with the :siliconflow suffix.

Read the docs
FLUX 1 Dev black-forest-labs/FLUX-1-dev input · output / 1M tokens FLUX 1 Schnell black-forest-labs/FLUX-1-schnell input · output / 1M tokens FLUX 1.1 Pro black-forest-labs/FLUX-1.1-pro input · output / 1M tokens FLUX 1.1 Pro Ultra black-forest-labs/FLUX-1.1-pro-Ultra input · output / 1M tokens FLUX 2 Pro black-forest-labs/FLUX-2-pro input · output / 1M tokens FLUX.1 Kontext Dev black-forest-labs/FLUX.1-Kontext-dev input · output / 1M tokens FLUX.1 Kontext Max black-forest-labs/FLUX.1-kontext-max input · output / 1M tokens FLUX.1 Kontext Pro black-forest-labs/FLUX.1-kontext-pro input · output / 1M tokens FLUX.2 Flex black-forest-labs/FLUX.2-flex input · output / 1M tokens Seed OSS 36B Instruct ByteDance-Seed/Seed-OSS-36B-Instruct input · output / 1M tokens DeepSeek V3 deepseek-ai/DeepSeek-V3 $0.34 input · $0.93 output / 1M tokens DeepSeek V3.1 DeepSeek-V3.1 $0.26 input · $1.00 output / 1M tokens DeepSeek V3.2 DeepSeek-V3.2 $0.27 input · $0.40 output / 1M tokens Deepseek r1 deepseek/deepseek-r1 $0.74 input · $2.63 output / 1M tokens Deepseek V3.1 Terminus deepseek/deepseek-v3.1-terminus $0.28 input · $1.00 output / 1M tokens Deepseek V3.2 Exp deepseek/deepseek-v3.2-exp $0.28 input · $0.43 output / 1M tokens Deepseek v4 Flash deepseek/deepseek-v4-flash $0.09 input · $0.19 output / 1M tokens Deepseek v4 Flash 0731 deepseek/deepseek-v4-flash-0731 $0.08 input · $0.19 output / 1M tokens Deepseek v4 Pro deepseek/deepseek-v4-pro $1.23 input · $2.45 output / 1M tokens Fish Speech 1.5 fishaudio/fish-speech-1.5 input · output / 1M tokens CosyVoice2 0.5B FunAudioLLM/CosyVoice2-0.5B input · output / 1M tokens Gemma 4 31B It gemma-4-31B-it $0.11 input · $0.36 output / 1M tokens Glm 4.5 Air glm-4.5-air $0.14 input · $0.89 output / 1M tokens Glm 5 glm-5 $0.63 input · $2.18 output / 1M tokens Glm 5 2 glm-5-2 $0.66 input · $2.08 output / 1M tokens Glm 5.1 glm-5.1 $1.10 input · $3.68 output / 1M tokens Gemma 4 12B It google/gemma-4-12B-it input · output / 1M tokens Gemma 4 26b a4b It google/gemma-4-26b-a4b-it $0.07 input · $0.36 output / 1M tokens Gpt Oss 120b gpt-oss-120b $0.03 input · $0.18 output / 1M tokens Ling Flash 2.0 inclusionAI/Ling-flash-2.0 input · output / 1M tokens IndexTTS 2 IndexTeam/IndexTTS-2 input · output / 1M tokens Longcat 2.0 meituan/longcat-2.0 $0.32 input · $1.26 output / 1M tokens Minimax M2.5 minimax/minimax-m2.5 $0.23 input · $0.95 output / 1M tokens Minimax m3 minimax/minimax-m3 $0.16 input · $0.63 output / 1M tokens Kimi K2.5 moonshotai/kimi-k2.5 $0.47 input · $2.36 output / 1M tokens Kimi K2.6 moonshotai/kimi-k2.6 $0.79 input · $3.68 output / 1M tokens Kimi K2.7 Code moonshotai/kimi-k2.7-code $0.50 input · $2.10 output / 1M tokens Kimi k3 moonshotai/kimi-k3 $2.99 input · $14.96 output / 1M tokens Nex n2 Pro nex-agi/nex-n2-pro $0.26 input · $1.05 output / 1M tokens Gpt Oss 20b openai/gpt-oss-20b $0.03 input · $0.14 output / 1M tokens Qwen Image Qwen/Qwen-Image input · output / 1M tokens Qwen Image Edit Qwen/Qwen-Image-Edit input · output / 1M tokens Qwen2.5 72B Instruct Qwen/Qwen2.5-72B-Instruct $0.38 input · $0.42 output / 1M tokens Qwen2.5 7B Instruct Qwen/Qwen2.5-7B-Instruct $0.11 input · $0.21 output / 1M tokens Qwen3 14b qwen/qwen3-14b $0.13 input · $0.25 output / 1M tokens Qwen3 30b a3b Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 $0.05 input · $0.20 output / 1M tokens Qwen3 32b qwen/qwen3-32b $0.08 input · $0.29 output / 1M tokens Qwen3 8b qwen/qwen3-8b $0.12 input · $0.48 output / 1M tokens Qwen3 Coder 30b a3b Instruct qwen/qwen3-coder-30b-a3b-instruct $0.07 input · $0.29 output / 1M tokens Qwen3 Embedding 0.6B Qwen/Qwen3-Embedding-0.6B $0.01 input · output / 1M tokens Qwen3 Embedding 4B Qwen/Qwen3-Embedding-4B $0.02 input · output / 1M tokens Qwen3 Embedding 8B Qwen/Qwen3-Embedding-8B $0.01 input · output / 1M tokens Qwen3 Reranker 0.6B Qwen/Qwen3-Reranker-0.6B input · output / 1M tokens Qwen3 Reranker 8B Qwen/Qwen3-Reranker-8B input · output / 1M tokens Qwen3 Vl 30b a3b Instruct qwen/qwen3-vl-30b-a3b-instruct $0.16 input · $0.63 output / 1M tokens Qwen3 Vl 30b a3b Thinking qwen/qwen3-vl-30b-a3b-thinking $0.21 input · $2.52 output / 1M tokens Qwen3 Vl 32b Instruct qwen/qwen3-vl-32b-instruct $0.11 input · $0.44 output / 1M tokens Qwen3 VL 32B Thinking Qwen/Qwen3-VL-32B-Thinking input · output / 1M tokens Qwen3 Vl 8b Instruct qwen/qwen3-vl-8b-instruct $0.12 input · $0.48 output / 1M tokens Qwen3.5 122b A10b qwen/qwen3.5-122b-a10b $0.30 input · $2.52 output / 1M tokens Qwen3.5 27b qwen/qwen3.5-27b $0.20 input · $1.64 output / 1M tokens Qwen3.5 35b a3b qwen/qwen3.5-35b-a3b $0.15 input · $1.05 output / 1M tokens Qwen3.5 397b A17b qwen/qwen3.5-397b-a17b $0.47 input · $3.15 output / 1M tokens Qwen3.5 9b qwen/qwen3.5-9b $0.11 input · $0.16 output / 1M tokens Qwen3.6 27b qwen/qwen3.6-27b $0.34 input · $3.36 output / 1M tokens Qwen3.6 35b a3b qwen/qwen3.6-35b-a3b $0.11 input · $1.00 output / 1M tokens Qwen3.8 2.4t A95b qwen/qwen3.8-2.4t-a95b $2.10 input · $6.30 output / 1M tokens Step 3.5 Flash stepfun/step-3.5-flash $0.11 input · $0.32 output / 1M tokens Hunyuan A13b Instruct tencent/hunyuan-a13b-instruct $0.15 input · $0.60 output / 1M tokens hy3 tencent/hy3 $0.14 input · $0.55 output / 1M tokens Z Image Turbo Tongyi-MAI/Z-Image-Turbo input · output / 1M tokens Wan2.2 I2V A14B Wan-AI/Wan2.2-I2V-A14B input · output / 1M tokens Wan2.2 T2V A14B Wan-AI/Wan2.2-T2V-A14B input · output / 1M tokens Glm 5v Turbo z-ai/glm-5v-turbo $1.26 input · $4.20 output / 1M tokens