DeepInfra
aggregator · deepinfra.com
About
DeepInfra is an aggregator — it resells other companies' work, 378 models and two tools on offer from 64 companies.
Its price list runs to 378 models and two tools, none of it its own work. What it sells was built by 64 different companies, so buying here is one account instead of 64.
Every current figure
- Kind
- aggregator
- On its price list
- 380
- Companies behind it
- 64
- Home
- https://deepinfra.com
Resells · 380
- Audio8-TTS-Preview-0.6b model
- Bria-3.2 model
- Bria-3.2-vector model
- Claude 3.7 Sonnet model
- Claude Fable 5 model
- Claude Haiku 4.5 model
- Claude Opus 4 model
- Claude Opus 4.7 model
- Claude Opus 4.8 model
- Claude Opus 5 model
- Claude Opus 5.5 model
- Claude Sonnet 4 model
- Claude Sonnet 4.6 model
- Claude Sonnet 5 model
- Claude Sonnet 5.5 model
- DeepSeek Prover V2 671B model
- DeepSeek R1 (Turbo) model
- DeepSeek R1 Distill QWEN 32B model
- DeepSeek V3.1 Terminus model
- DeepSeek V3.2 Exp model
- DeepSeek V4 Flash model
- DeepSeek V4 Flash (0731) model
- DeepSeek V4 Flash Vision model
- DeepSeek V4 Pro model
- DeepSeek V4 Pro 0813 model
- DeepSeek V4.1 Flash model
- DeepSeek V4.1 Flash 1017 model
- DeepSeek v3.2 model
- DeepSeek-OCR model
- DeepSeek-R1 model
- DeepSeek-R1 (0528) model
- DeepSeek-R1-0528-Turbo model
- DeepSeek-V3 model
- DeepSeek-V3 0324 model
- DeepSeek-V3-0324-Turbo model
- DeepSeek-V3.1 model
- Deliberate model
- Devstral-Small-2505 model
- Devstral-Small-2507 model
- Doubao-Seedream-5.0-pro model
- FLUX model
- FLUX-1-Redux-dev model
- FLUX.1 [dev] model
- FLUX.1 [schnell] (Turbo) model
- FLUX.1-Kontext-dev model
- FLUX.2 [dev] model
- FLUX.2 [klein] 4B model
- FLUX.2 [klein] 9B model
- FLUX.2 [max] model
- FLUX.2 [pro] model
- FLUX1.1 [pro] model
- FastWan-QAD-FP8-1.3B model
- Fibo-1.5 model
- Fibo-2.0 model
- GLM 5.1 model
- GLM 5.2 model
- GLM 5.3 Flash model
- GLM-4.5 model
- GLM-4.5-Air model
- GLM-4.6 model
- GLM-4.6V model
- GLM-4.7 model
- GLM-4.7 Flash model
- GLM-5 model
- GLM-5.3 model
- GPT OSS 120B model
- GPT OSS 20B model
- GPT-oss-120b-Turbo model
- GPT-oss-120b-Ultra model
- Gemini 2.5 Flash model
- Gemini 2.5 Pro model
- Gemini 3 Pro Image (Nano Banana Pro) model
- Gemini 3.1 Flash-Lite model
- Gemini 3.1 Pro Preview model
- Gemini 3.5 Flash model
- Gemini 3.7 Flash model
- Gemma 2 27B model
- Gemma 3 12B model
- Gemma 3 27B model
- Gemma 3 4B model
- Gemma 4 26B A4B model
- Gemma 4 31B model
- Gemma-4-31B-it-Ultra model
- Gemma-4-31B-it-turbo model
- Gemma-4-E4B-it model
- Gen Fill tool
- Granite 4.2 8B model
- Hermes 3 405B Instruct model
- Hermes 3 70B Instruct model
- HiggsAudioV2.5 model
- Hy3 model
- Hy4-preview model
- Inkling model
- Inkling Small model
- Janus-Pro-1B model
- Janus-Pro-7B model
- Juggernaut Lightning Flux model
- Juggernaut-Flux model
- Kimi K2 0905 model
- Kimi K2 Instruct model
- Kimi K2 Thinking model
- Kimi K2.5 model
- Kimi K2.6 model
- Kimi K2.7 Code model
- Kimi K3 model
- Kimi-K2.5-Turbo model
- Kokoro model
- L3 70B Euryale V2.1 model
- L3-8B-Lunaris-v1 model
- L3-8B-Lunaris-v1-Turbo model
- L3.3-70B-Euryale-v2.3 model
- L31 70B Euryale V2.2 model
- LTX2-Distilled-Diffusers model
- Ling 3.0 Flash Fin model
- Ling-3.0-flash model
- Ling-3.0-flash-VL model
- Llama 3 8B Instruct model
- Llama 3.1 8B Instruct model
- Llama 3.2 11B Vision Instruct model
- Llama 3.2 1B Instruct model
- Llama 3.2 3B Instruct model
- Llama 3.3 70B Instruct model
- Llama 4 Maverick 17B model
- Llama 4 Maverick Instruct model
- Llama 4 Scout 17B model
- Llama 4 Scout Instruct model
- Llama Guard 4 12B model
- Llama-2-13b-chat-hf model
- Llama-2-70b-chat-hf model
- Llama-3.1-Nemotron-70B-Instruct model
- Llama-3.2-90B-Vision-Instruct model
- Llama-3.3-70B-Instruct-Turbo model
- Llama-3.3-Nemotron-Super-49B-v1.5 model
- Llama-4-Maverick-17B-128E-Instruct-Turbo model
- Llama-Guard-3-8B model
- Llama2-13B-Tiefighter model
- Meta-Llama-3-70B-Instruct model
- Meta-Llama-3.1-405B-Instruct model
- Meta-Llama-3.1-70B-Instruct model
- Meta-Llama-3.1-70B-Instruct-Turbo model
- Meta-Llama-3.1-8B-Instruct-Turbo model
- MiMo V2.6 Flash model
- MiMo V2.6 Pro model
- MiMo-V2.5 model
- MiMo-V2.5-Pro model
- Ming-Image-0.1-Design model
- MiniCPM-Llama3-V-2_5 model
- MiniMax M2.1 model
- MiniMax M2.5 model
- MiniMax M2.7 model
- MiniMax M3 model
- MiniMax-M2 model
- MiniMax-M2.7-Turbo model
- Mistral Nemo model
- Mistral Small 3 model
- Mistral Small 3.1 24B Instruct 2503 model
- Mistral-7B-Instruct-v0.1 model
- Mistral-7B-Instruct-v0.2 model
- Mistral-7B-Instruct-v0.3 model
- Mistral-Small-3.2-24B-Instruct-2506 model
- Mixtral-8x22B-Instruct-v0.1 model
- Mixtral-8x7B-Instruct-v0.1 model
- Multilingual-e5-large-instruct model
- Muse Glimmer 30B model
- MythoMax 13B model
- MythoMax-L2-13b-turbo model
- NVIDIA Nemotron 3.5 Super VL model
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B model
- Nemotron 3 Nano 30B A3B model
- Nemotron 3 Super model
- Nemotron 3 Super 120B A12B model
- Nemotron 3 Ultra model
- Nemotron 3.5 Lightning model
- Nemotron Nano 12B V2 VL model
- Nemotron Nano 9B V2 model
- Nemotron-3-Embed-1B-BF16 model
- Nemotron-3-Embed-1B-NVFP4 model
- Nemotron-3-Embed-8B model
- Nemotron-3-Nano-Omni-30B-A3B-Reasoning model
- Nemotron-3.5-ASR-Streaming-Multilingual-0.6b model
- Nemotron-4-340B-Instruct model
- Nemotron-Content-Safety-3.5 model
- Olmo-3.1-32B-Instruct model
- Ornith-1.0-35B model
- Orpheus 3B model
- PaddleOCR-VL-0.9B model
- Phi-3-medium-4k-instruct model
- Phi-4 model
- Phi-4-multimodal-instruct model
- Phind-CodeLlama-34B-v2 model
- PixVerse-6-I2V model
- PixVerse-6-T2V model
- PixVerse-T2V model
- PixVerse-T2V-HD model
- QVQ-72B-Preview model
- QwQ-32B model
- QwQ-32B-Preview model
- Qwen 2 7B Instruct model
- Qwen 3.8 Max model
- Qwen-Image-Edit model
- Qwen-Image-Edit-Max model
- Qwen-Image-Max model
- Qwen2-72B-Instruct model
- Qwen2.5 72B Instruct model
- Qwen2.5 7B Instruct model
- Qwen2.5 Coder 32B Instruct model
- Qwen2.5-Coder-7B model
- Qwen2.5-VL-32B-Instruct model
- Qwen3 14B model
- Qwen3 235B A22B model
- Qwen3 235B A22B Thinking 2507 model
- Qwen3 30B A3B model
- Qwen3 32B model
- Qwen3 8B (embeddings) model
- Qwen3 Coder 30B A3B Instruct model
- Qwen3 Max model
- Qwen3 Max Thinking model
- Qwen3 Next 80B A3B Instruct model
- Qwen3 VL 235B A22B Instruct model
- Qwen3 VL 235B A22B Thinking model
- Qwen3 VL 30B A3B Instruct model
- Qwen3 VL 30B A3B Thinking model
- Qwen3 VL 8B Instruct model
- Qwen3 VL 8B Thinking model
- Qwen3-235B-A22B-Instruct-2507 model
- Qwen3-ASR-0.6B model
- Qwen3-ASR-1.7B model
- Qwen3-Coder-480B-A35B-Instruct model
- Qwen3-Coder-480B-A35B-Instruct-Turbo model
- Qwen3-Embedding-0.6B model
- Qwen3-Embedding-0.6B-batch model
- Qwen3-Embedding-4B model
- Qwen3-Embedding-4B-batch model
- Qwen3-Embedding-8B-batch model
- Qwen3-Reranker-0.6B model
- Qwen3-Reranker-4B model
- Qwen3-Reranker-8B model
- Qwen3-TTS model
- Qwen3-TTS-VoiceDesign model
- Qwen3-VL-4B-Instruct model
- Qwen3-VL-4B-Thinking model
- Qwen3.5 397B A17B model
- Qwen3.5 9B model
- Qwen3.5-0.8B model
- Qwen3.5-122B-A10B model
- Qwen3.5-27B model
- Qwen3.5-2B model
- Qwen3.5-35B-A3B model
- Qwen3.5-4B model
- Qwen3.6 27B model
- Qwen3.6 35B A3B model
- Qwen3.7 Max model
- Qwen3.8 27B model
- Qwen3.8 Flash model
- Qwen3.8-2.4T-A95B model
- R1 Distill Llama 70B model
- Realtime TTS-2 model
- Reflection-Llama-3.1-70B model
- Remove Background tool
- Seed-1.8 model
- Seed-2.0-Code model
- Seed-2.0-Mini model
- Seed-2.0-pro model
- Seedance-1.5-Pro model
- Seedance-2.0 model
- Seedream 4.0 model
- Seedream-4.5 model
- Sky-T1-32B-Preview model
- Stable Diffusion 3.5 Medium model
- Step 3.5 Flash model
- Step 3.7 Flash model
- Step 5 model
- Veo 3 Fast model
- Veo 3.1 Fast model
- Veo 3.1 Standard model
- Voxtral Small 24B 2507 model
- Voxtral-Mini-3B-2507 model
- Wan 3.0 model
- Wan2.1-T2V-1.3B model
- Wan2.1-T2V-14B model
- Wan2.2-T2V-A14B model
- Wan2.6-I2V model
- Wan2.6-Image-Edit model
- Wan2.6-T2I model
- Wan2.6-T2V model
- Wan2.7-I2V model
- Wan2.7-Image-Edit model
- Wan2.7-R2V model
- Whisper Large V3 Turbo model
- Whisper Large v3 model
- WizardLM-2 8x22B model
- WizardLM-2-7B model
- Zonos-v0.1-hybrid model
- Zonos-v0.1-transformer model
- acestep-v15-xl-sft model
- airoboros-70b model
- all-MiniLM-L12-v2 model
- all-MiniLM-L6-v2 model
- all-mpnet-base-v2 model
- bge-base-en-v1.5 model
- bge-en-icl model
- bge-large-en-v1.5 model
- bge-m3 model
- bge-m3-multi model
- blur_background model
- chatterbox model
- chatterbox-multilingual model
- chatterbox-turbo model
- chronos-hermes-13b-v2 model
- clip-ViT-B-32 model
- clip-ViT-B-32-multilingual-v1 model
- clip-vit-base-patch32 model
- clip-vit-large-patch14-336 model
- codegemma-7b-it model
- creative model
- crystal model
- csm-1b model
- dolphin-2.6-mixtral-8x7b model
- dolphin-2.9.1-llama-3-70b model
- e5-base-v2 model
- e5-large-v2 model
- embeddinggemma-2 model
- embeddinggemma-300m model
- enhance model
- erase model
- erase_foreground model
- expand model
- fibo model
- fibo_edit model
- gemini-2.0-flash-001 model
- gemma-1.1-7b-it model
- gemma-2-9b-it model
- gte-base model
- gte-large model
- inworld-tts-1.5-max model
- inworld-tts-1.5-mini model
- llama-nemotron-embed-vl-1b-v2 model
- llama-nemotron-rerank-vl-1b-v2 model
- lzlv_70b_fp16_hf model
- multi-qa-mpnet-base-dot-v1 model
- nano-banana-2 model
- nano-banana-2-lite model
- nano-banana-pro model
- olmOCR-2 model
- olmOCR-2-7B-1025 model
- olmOCR-7B-0725-FP8 model
- olmOCR-7B-0825 model
- olmOCR-7B-1025 model
- openchat-3.6-8b model
- openchat_3.5 model
- p-image model
- p-image-Edit model
- p-video model
- p-video-avatar model
- paraphrase-MiniLM-L6-v2 model
- phi-4-reasoning-plus model
- realtime-tts-1.5-max model
- realtime-tts-1.5-mini model
- replace_background model
- sd3.5 model
- sdxl-turbo model
- stable-diffusion-2-1 model
- stable-diffusion-v1-4 model
- stable-diffusion-v1-5 model
- starcoder2-15b-instruct-v0.1 model
- text2vec-base-chinese model
- veo-3.0 model
- video_eraser model
- video_foreground_mask model
- video_increase_resolution model
- video_mask_by_key_points model
- video_mask_by_prompt model
- video_remove_background model
- whisper-base model
- whisper-base.en model
- whisper-medium.en model
- whisper-small.en model
- whisper-timestamped-medium model
- whisper-timestamped-medium.en model
- whisper-tiny.en model