p2d
> text · images · video · voice_

Every model in one window P2D AI aggregator: 683 models for text, images, video and voice

GPT, Claude, Gemini, Nano Banana, Seedance, Veo and hundreds more — in one account. No subscription: pay only for what you generate.

● Seedance 2.5● Nano Banana Pro● Veo 3.1● Claude Opus 5.5+679
> ls ./models | wc -l  →  683

Model catalog: 683 models from 80 developers

Find a model by name, or pick what you want to make.

List updated 20 October 2026

Showing: 683

AionLabs 6

  • Aion 3.5Text
  • Aion 3.5 MiniText
  • Aion-2.0Text
  • Aion-3.0Text
  • Aion-3.0-MiniText
  • Aion-RP 1.0 (8B)Text

Alibaba 6

  • HappyHorse 1.0Video
  • HappyHorse 1.1Video
  • Wan 2.6Video
  • Wan 2.7Video
  • Wan 3.0Video
  • Wan 3.0 PrimeVideo

Amazon 5

  • Nova 2 LiteText
  • Nova Lite 1.0Text
  • Nova Micro 1.0Text
  • Nova Premier 1.0Text
  • Nova Pro 1.0Text

Anthropic 34

  • Claude Fable 5Text
  • Claude Fable 5batchText
  • Claude Fable 5.1Text
  • Claude Fable 5.1batchText
  • Claude Fable LatestText
  • Claude Haiku 4.5Text
  • Claude Haiku 4.5batchText
  • Claude Haiku 5.5Text
  • Claude Haiku 5.5batchText
  • Claude Haiku LatestText
  • Claude Opus 4.1Text
  • Claude Opus 4.1batchText
  • Claude Opus 4.5Text
  • Claude Opus 4.5batchText
  • Claude Opus 4.6Text
  • Claude Opus 4.6batchText
  • Claude Opus 4.7Text
  • Claude Opus 4.7batchText
  • Claude Opus 4.8Text
  • Claude Opus 4.8batchText
  • Claude Opus 5Text
  • Claude Opus 5batchText
  • Claude Opus 5.5Text
  • Claude Opus 5.5batchText
  • Claude Opus LatestText
  • Claude Sonnet 4.5Text
  • Claude Sonnet 4.5batchText
  • Claude Sonnet 4.6Text
  • Claude Sonnet 4.6batchText
  • Claude Sonnet 5Text
  • Claude Sonnet 5batchText
  • Claude Sonnet 5.5Text
  • Claude Sonnet 5.5batchText
  • Claude Sonnet LatestText

Arcee AI 1

  • Trinity Large ThinkingText

AssemblyAI 2

  • Universal-3.5 ProSpeech recognition
  • Universal-3.6 ProSpeech recognition

BAAI 3

  • bge-base-en-v1.5Embeddings
  • bge-large-en-v1.5Embeddings
  • bge-m3Embeddings

Black Forest Labs 9

  • FLUX 3 ImageImages
  • FLUX 3 Image KleinImages
  • FLUX 3 VideoVideo
  • FLUX Video EditVideo
  • FLUX Video UpscaleVideo
  • FLUX.2 FlexImages
  • FLUX.2 Klein 4BImages
  • FLUX.2 MaxImages
  • FLUX.2 ProImages

ByteDance 6

  • Seedance 1.5 ProVideo
  • Seedance 2.0Video
  • Seedance 2.0 FastVideo
  • Seedance 2.0 MiniVideo
  • Seedance 2.5Video
  • UI-TARS 7BText

ByteDance Seed 11

  • Seed 1.6Text
  • Seed 1.6 FlashText
  • Seed 2.1 TurboText
  • Seed Audio 1.0Speech
  • Seed-2.0-CodeText
  • Seed-2.0-LiteText
  • Seed-2.0-MiniText
  • Seedream 4.5Images
  • Seedream 5.0 FlashImages
  • Seedream 5.0 LiteImages
  • Seedream 5.0 ProImages

Canopy Labs 1

  • Orpheus 3BSpeech

Cloudflare 3

  • ClefDecisions
  • Clef FlashDecisions
  • Clef OmniDecisions

Cohere 9

  • Command AText
  • Command A+Text
  • Command R (08-2024)Text
  • Command R+ (08-2024)Text
  • Command R7B (12-2024)Text
  • North Mini CodefreeText
  • Rerank 4 FastReranking
  • Rerank 4 ProReranking
  • Rerank v3.5Reranking

Deepgram 3

  • Aura-2Speech
  • Flux TTSSpeech
  • Nova-3Speech recognition

DeepSeek 18

  • DeepSeek Flash LatestText
  • DeepSeek Pro LatestText
  • DeepSeek V3Text
  • DeepSeek V3 0324Text
  • DeepSeek V3.1Text
  • DeepSeek V3.1 TerminusText
  • DeepSeek V3.2Text
  • DeepSeek V3.2 ExpText
  • DeepSeek V4 Flash 0423Text
  • DeepSeek V4 Flash 0731Text
  • DeepSeek V4 Flash LatestText
  • DeepSeek V4 Flash Vision ExpText
  • DeepSeek V4 Pro 0423Text
  • DeepSeek V4 Pro 0813Text
  • DeepSeek V4.1 FlashText
  • DeepSeek V4.1 FlashbatchText
  • DeepSeek V4.1 Flash 1017Text
  • R1 0528Text

Dots Studio 1

  • Dots3-Note PreviewfreeText

ElevenLabs 11

  • Eleven Flash v2Speech
  • Eleven Flash v2.5Speech
  • Eleven Multilingual v2Speech
  • Eleven Turbo v2Speech
  • Eleven Turbo v2.5Speech
  • Eleven v3Speech
  • Eleven v3 ConversationalSpeech
  • Eleven v4Speech
  • Eleven v4 TurboSpeech
  • Scribe v2Speech recognition
  • Scribe v2 MedicalSpeech recognition

Elorian 1

  • GlimpseText

Fireworks 1

  • Ember-1Text

Fish Audio 7

  • Drama 3Speech
  • S1Speech
  • S2 ProSpeech
  • S2.1 ProSpeech
  • S2.1 Pro FreefreeSpeech
  • Transcribe 1Speech recognition
  • Transcribe 1 ProSpeech recognition

Google 56

  • Chirp 3Speech recognition
  • Gemini 2.5 FlashText
  • Gemini 2.5 Flash LiteText
  • Gemini 2.5 Flash LitebatchText
  • Gemini 2.5 ProText
  • Gemini 2.5 Pro Preview 06-05Text
  • Gemini 3 Flash PreviewText
  • Gemini 3 Flash PreviewbatchText
  • Gemini 3.1 Flash LiteText
  • Gemini 3.1 Flash LitebatchText
  • Gemini 3.1 Flash Lite PreviewText
  • Gemini 3.1 Flash TTS PreviewSpeech
  • Gemini 3.1 Pro PreviewText
  • Gemini 3.1 Pro PreviewbatchText
  • Gemini 3.1 Pro Preview Custom ToolsText
  • Gemini 3.5 FlashText
  • Gemini 3.5 FlashbatchText
  • Gemini 3.5 Flash LiteText
  • Gemini 3.5 Flash LitebatchText
  • Gemini 3.5 TranscribeSpeech recognition
  • Gemini 3.6 FlashText
  • Gemini 3.6 FlashbatchText
  • Gemini 3.7 FlashText
  • Gemini 3.7 FlashbatchText
  • Gemini 3.8 FlashText
  • Gemini 3.8 FlashbatchText
  • Gemini 3.8 Flash Lite TTSSpeech
  • Gemini 3.8 Flash TTSSpeech
  • Gemini 4 ArgonText
  • Gemini 4 ArgonbatchText
  • Gemini Embedding 001Embeddings
  • Gemini Embedding 2Embeddings
  • Gemini Embedding 2batchEmbeddings
  • Gemini Embedding 2 PreviewEmbeddings
  • Gemini Flash LatestText
  • Gemini Pro LatestText
  • Gemma 2 27BText
  • Gemma 3 12BText
  • Gemma 3 27BText
  • Gemma 3 4BText
  • Gemma 4 26B A4BText
  • Gemma 4 26B A4BfreeText
  • Gemma 4 31BText
  • Gemma 4 31BfreeText
  • Lyria 3 Clip PreviewMusic and sound
  • Lyria 3 Pro PreviewMusic and sound
  • Nano Banana (Gemini 2.5 Flash Image)Images
  • Nano Banana 2 (Gemini 3.1 Flash Image Preview)Images
  • Nano Banana 2 (Gemini 3.1 Flash Image)Images
  • Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Images
  • Nano Banana 2.1Images
  • Nano Banana Pro (Gemini 3 Pro Image Preview)Images
  • Nano Banana Pro (Gemini 3 Pro Image)Images
  • Veo 3.1Video
  • Veo 3.1 FastVideo
  • Veo 3.1 LiteVideo

hexgrad 1

  • Kokoro 82MSpeech

HeyGen 4

  • Avatar IVVideo
  • HeyGen VideoVideo
  • HeyGen VoiceSpeech
  • HeyGen Voice TurboSpeech

IBM 2

  • Granite 4.0 MicroText
  • Granite 4.2 8BText

Inception 5

  • Mercury 2Text
  • Mercury 2.5Text
  • Mercury 3Text
  • Mercury DecideDecisions
  • Mercury DecidefreeDecisions

inclusionAI 3

  • Ling 3.0 FlashText
  • Ling 3.0 Flash VLText
  • Ling 3.1 FlashText

Inference.net 2

  • Schematron V2 SmallText
  • Schematron V2 TurboText

Intfloat 3

  • E5-Base-v2Embeddings
  • E5-Large-v2Embeddings
  • Multilingual-E5-LargeEmbeddings

Jared Palmer 1

  • Kev 4BDecisions

Kling 3

  • Video O1Video
  • Video v3.0 ProVideo
  • Video v3.0 StandardVideo

Krea 4

  • K3 EditImages
  • Krea 2 LargeImages
  • Krea 2 MediumImages
  • Krea 2 Medium TurboImages

LiquidAI 5

  • d1Decisions
  • d1-ultraDecisions
  • LFM2.5-2.6BfreeText
  • LFM2.5-24B-A2BText
  • LFM2.5-Embedding-350MfreeEmbeddings

Mancer 1

  • Weaver (alpha)Text

Meituan 1

  • LongCat 2.0Text

Meta 18

  • Llama 3.1 70B InstructText
  • Llama 3.1 8B InstructText
  • Llama 3.2 1B InstructText
  • Llama 3.2 3B InstructText
  • Llama 3.3 70B InstructText
  • Llama 4 MaverickText
  • Llama 4 ScoutText
  • Llama Guard 4 12BText
  • Muse Glimmer 30BText
  • Muse ImageImages
  • Muse Spark 1.1Text
  • Muse Spark 1.2Text
  • Muse Spark 1.2 ContributorText
  • Muse Spark 1.3Text
  • Muse Spark 1.3 ContributorText
  • Muse Spark OpenText
  • Muse Voice Transcribe 1.0Speech recognition
  • Muse WonderText

Microsoft 2

  • Microsoft-Decision-1Decisions
  • Phi 4Text

Microsoft AI 10

  • MAI-Image-2.5Images
  • MAI-Image-2.5 ProImages
  • MAI-Image-2.6Images
  • MAI-Image-2.6 FlashImages
  • MAI-Transcribe 1.5Speech recognition
  • MAI-Transcribe 2Speech recognition
  • MAI-Voice-2Speech
  • MAI-Voice-2-FlashSpeech
  • MAI-Voice-2.1Speech
  • MAI-Voice-2.1-FlashSpeech

MiniMax 14

  • H3Video
  • H3 MaxVideo
  • Hailuo 2.3Video
  • MiniMax M1Text
  • MiniMax M2Text
  • MiniMax M2-herText
  • MiniMax M2.1Text
  • MiniMax M2.5Text
  • MiniMax M2.7Text
  • MiniMax M3Text
  • MiniMax M3.1 FlashfreeText
  • MiniMax-01Text
  • Speech 2.8 HDSpeech
  • Speech 2.8 TurboSpeech

Mistral 30

  • Codestral 2508Text
  • Codestral 2508batchText
  • Codestral Embed 2505Embeddings
  • Devstral 2 2512Text
  • Ministral 3 14B 2512Text
  • Ministral 3 3B 2512Text
  • Ministral 3 8B 2512Text
  • Ministral 3 8B 2512batchText
  • Mistral Embed 2312Embeddings
  • Mistral Large 3 2512Text
  • Mistral Large 3 2512batchText
  • Mistral Large 4Text
  • Mistral Medium 3Text
  • Mistral Medium 3.1Text
  • Mistral Medium 3.1batchText
  • Mistral Medium 3.5Text
  • Mistral Medium 3.5batchText
  • Mistral NemoText
  • Mistral Small 3Text
  • Mistral Small 3.1 24BText
  • Mistral Small 3.2 24BText
  • Mistral Small 4Text
  • Mistral Small 4batchText
  • Mixtral 8x22B InstructText
  • SabaText
  • Voxtral Mini 3B 2507Speech recognition
  • Voxtral Mini TranscribeSpeech recognition
  • Voxtral Mini TTSSpeech
  • Voxtral Small 24B 2507Text
  • Voxtral Small 24B 2507 STTSpeech recognition

Moondream 2

  • Moondream 3 PreviewText
  • Moondream 3.1Text

MoonshotAI 9

  • Kimi K2 0711Text
  • Kimi K2 0905Text
  • Kimi K2 ThinkingText
  • Kimi K2.5Text
  • Kimi K2.6Text
  • Kimi K2.7 CodeText
  • Kimi K3Text
  • Kimi K3batchText
  • Kimi LatestText

Morph 2

  • Morph V3 FastText
  • Morph V3 LargeText

Nace.AI 2

  • Drex v1.5Decisions
  • Drex v2.0Decisions

Nex AGI 2

  • Nex-N2.5-MiniText
  • Nex-N2.5-ProText

Nous 3

  • Hermes 3 405B InstructText
  • Hermes 3 70B InstructText
  • Hermes 4 405BText

NVIDIA 18

  • Llama Nemotron Embed VL 1B V2freeEmbeddings
  • Llama Nemotron Rerank VL 1B V2freeReranking
  • Nemotron 3 Embed 1BfreeEmbeddings
  • Nemotron 3 Nano 30B A3BText
  • Nemotron 3 Nano OmnifreeText
  • Nemotron 3 SuperText
  • Nemotron 3 SuperfreeText
  • Nemotron 3 UltraText
  • Nemotron 3 UltrafreeText
  • Nemotron 3.5 ASR Streaming Multilingual 0.6BSpeech recognition
  • Nemotron 3.5 Content SafetyText
  • Nemotron 3.5 Content SafetyfreeText
  • Nemotron 3.5 LightningText
  • Nemotron 3.5 LightningfreeText
  • Nemotron 3.5 Super VLText
  • Nemotron 3.5 Super VLfreeText
  • Parakeet TDT 0.6B v3Speech recognition
  • SwitchyardText

OpenAI 127

  • GPT Astra LatestText
  • GPT AudioMusic and sound
  • GPT Audio MiniMusic and sound
  • GPT Chat LatestText
  • GPT Image 1Images
  • GPT Image 1 MiniImages
  • GPT Image 2Images
  • GPT Image 2.5 FlareImages
  • GPT Image 2.5 SunburstImages
  • GPT Luna LatestText
  • GPT Mini LatestText
  • GPT Sol LatestText
  • GPT Terra LatestText
  • GPT TranscribeSpeech recognition
  • GPT-3.5 TurboText
  • GPT-3.5 TurbobatchText
  • GPT-3.5 Turbo (older v0613)Text
  • GPT-3.5 Turbo 16kText
  • GPT-3.5 Turbo InstructText
  • GPT-4Text
  • GPT-4 TurboText
  • GPT-4 TurbobatchText
  • GPT-4.1Text
  • GPT-4.1batchText
  • GPT-4.1 MiniText
  • GPT-4.1 MinibatchText
  • GPT-4.1 NanoText
  • GPT-4.1 NanobatchText
  • GPT-4oText
  • GPT-4o (2024-05-13)Text
  • GPT-4o (2024-08-06)Text
  • GPT-4o (2024-11-20)Text
  • GPT-4obatchText
  • GPT-4o Mini TranscribeSpeech recognition
  • GPT-4o TranscribeSpeech recognition
  • GPT-4o-miniText
  • GPT-4o-mini (2024-07-18)Text
  • GPT-4o-minibatchText
  • GPT-5Text
  • GPT-5batchText
  • GPT-5 ImageImages
  • GPT-5 Image MiniImages
  • GPT-5 MiniText
  • GPT-5 MinibatchText
  • GPT-5 NanoText
  • GPT-5 NanobatchText
  • GPT-5 ProText
  • GPT-5 ProbatchText
  • GPT-5.1Text
  • GPT-5.1batchText
  • GPT-5.1-CodexText
  • GPT-5.1-Codex-MaxText
  • GPT-5.1-Codex-MiniText
  • GPT-5.2Text
  • GPT-5.2batchText
  • GPT-5.2 ChatText
  • GPT-5.2 ProText
  • GPT-5.2 ProbatchText
  • GPT-5.2-CodexText
  • GPT-5.3-CodexText
  • GPT-5.4Text
  • GPT-5.4batchText
  • GPT-5.4 Image 2Images
  • GPT-5.4 MiniText
  • GPT-5.4 MinibatchText
  • GPT-5.4 NanoText
  • GPT-5.4 NanobatchText
  • GPT-5.4 ProText
  • GPT-5.4 ProbatchText
  • GPT-5.5Text
  • GPT-5.5batchText
  • GPT-5.5 ProText
  • GPT-5.5 ProbatchText
  • GPT-5.6 LunaText
  • GPT-5.6 LunabatchText
  • GPT-5.6 Luna ProText
  • GPT-5.6 Luna ProbatchText
  • GPT-5.6 SolText
  • GPT-5.6 SolbatchText
  • GPT-5.6 Sol ProText
  • GPT-5.6 Sol ProbatchText
  • GPT-5.6 TerraText
  • GPT-5.6 TerrabatchText
  • GPT-5.6 Terra ProText
  • GPT-5.6 Terra ProbatchText
  • GPT-6 AstraText
  • GPT-6 AstrabatchText
  • GPT-6 Astra ProText
  • GPT-6 Astra ProbatchText
  • GPT-6 LunaText
  • GPT-6 LunabatchText
  • GPT-6 Luna DecisionsDecisions
  • GPT-6 Luna ProText
  • GPT-6 Luna ProbatchText
  • GPT-6 SolText
  • GPT-6 SolbatchText
  • GPT-6 Sol ProText
  • GPT-6 Sol ProbatchText
  • GPT-6.1 SolText
  • GPT-6.1 SolbatchText
  • GPT-6.1 Sol ProText
  • GPT-6.1 Sol ProbatchText
  • gpt-oss-120bText
  • gpt-oss-120bbatchText
  • gpt-oss-20bText
  • gpt-oss-20bbatchText
  • gpt-oss-safeguard-20bText
  • o1Text
  • o1-proText
  • o3Text
  • o3batchText
  • o3 MiniText
  • o3 MinibatchText
  • o3 Mini HighText
  • o3 ProText
  • o4 MiniText
  • o4 MinibatchText
  • o4 Mini HighText
  • Text Embedding 3 LargeEmbeddings
  • Text Embedding 3 LargebatchEmbeddings
  • Text Embedding 3 SmallEmbeddings
  • Text Embedding 3 SmallbatchEmbeddings
  • Text Embedding Ada 002Embeddings
  • Text Embedding Ada 002batchEmbeddings
  • Whisper 1Speech recognition
  • Whisper Large V3Speech recognition
  • Whisper Large V3 TurboSpeech recognition

OpenRouter 1

  • FusionText

Perceptron 2

  • Perceptron Mk1Text
  • Perceptron Mk1.5Text

Perplexity 11

  • Decider Flash LatestDecisions
  • Decider Flash V1.2Decisions
  • Decider LatestDecisions
  • Decider V1.2Decisions
  • Embed V1 0.6BEmbeddings
  • Embed V1 4BEmbeddings
  • SonarText
  • Sonar Deep ResearchText
  • Sonar ProText
  • Sonar Pro SearchText
  • Sonar Reasoning ProText

Poolside 4

  • Laguna S 2.1Text
  • Laguna S 2.1freeText
  • Laguna XS 2.1Text
  • Laguna XS 2.1freeText

PrismML 1

  • Ternary Bonsai 2 27BText

Qwen 51

  • Qwen Image 2.1 ProImages
  • Qwen Image 2.1 TurboImages
  • Qwen Image 3Images
  • Qwen Image 3 ProImages
  • Qwen-Audio-3.0-TTS FlashSpeech
  • Qwen-Audio-3.0-TTS PlusSpeech
  • Qwen-PlusText
  • Qwen2.5 7B InstructText
  • Qwen2.5 VL 72B InstructText
  • Qwen3 14BText
  • Qwen3 235B A22B Instruct 2507Text
  • Qwen3 235B A22B Thinking 2507Text
  • Qwen3 30B A3BText
  • Qwen3 30B A3B Instruct 2507Text
  • Qwen3 32BText
  • Qwen3 ASR 0.6BSpeech recognition
  • Qwen3 ASR 1.7BSpeech recognition
  • Qwen3 Coder 30B A3B InstructText
  • Qwen3 Coder 480B A35BText
  • Qwen3 Coder FlashText
  • Qwen3 Coder NextText
  • Qwen3 Embedding 4BEmbeddings
  • Qwen3 Embedding 8BEmbeddings
  • Qwen3 Next 80B A3B InstructText
  • Qwen3 Next 80B A3B ThinkingText
  • Qwen3 VL 235B A22B InstructText
  • Qwen3 VL 30B A3B InstructText
  • Qwen3 VL 30B A3B ThinkingText
  • Qwen3 VL 8B InstructText
  • Qwen3.5 397B A17BText
  • Qwen3.5 Plus 2026-02-15Text
  • Qwen3.5 Plus 2026-04-20Text
  • Qwen3.5-122B-A10BText
  • Qwen3.5-27BText
  • Qwen3.5-35B-A3BText
  • Qwen3.5-9BText
  • Qwen3.5-FlashText
  • Qwen3.6 27BText
  • Qwen3.6 35B A3BText
  • Qwen3.6 FlashText
  • Qwen3.6 PlusText
  • Qwen3.7 FlashText
  • Qwen3.7 MaxText
  • Qwen3.7 PlusText
  • Qwen3.7 PlusbatchText
  • Qwen3.8 2.4T A95BText
  • Qwen3.8 27BText
  • Qwen3.8 FlashText
  • Qwen3.8 Max (0902)Text
  • Qwen3.8 Max PrimeText
  • Qwen3.8 Omni FlashText

Recraft 16

  • Recraft V3Images
  • Recraft V4Images
  • Recraft V4 ProImages
  • Recraft V4 Pro VectorImages
  • Recraft V4 StylesImages
  • Recraft V4 Styles ProImages
  • Recraft V4 Styles Pro VectorImages
  • Recraft V4 Styles VectorImages
  • Recraft V4 VectorImages
  • Recraft V4.1Images
  • Recraft V4.1 FlashImages
  • Recraft V4.1 ProImages
  • Recraft V4.1 Pro VectorImages
  • Recraft V4.1 UtilityImages
  • Recraft V4.1 Utility ProImages
  • Recraft V4.1 VectorImages

Reflection 1

  • Beam 1.0 501B A23BText

Relace 2

  • Relace Apply 3Text
  • Relace SearchText

Respan 4

  • Span-01Decisions
  • Span-01 LiteDecisions
  • Span-01 LitefreeDecisions
  • Span-02Decisions

Runway 2

  • Aleph 2.0Video
  • Gen-4.5Video

Sakana 4

  • Fugu MaxText
  • Fugu UltraText
  • Fugu Ultra v2Text
  • Sakana NamazuText

Sao10K 2

  • Llama 3 8B LunarisText
  • Llama 3.1 Euryale 70B v2.2Text

ScaleDown 3

  • Classify-1Decisions
  • ExtractText
  • SummarizeText

Sentence Transformers 5

  • all-MiniLM-L12-v2Embeddings
  • all-MiniLM-L6-v2Embeddings
  • all-mpnet-base-v2Embeddings
  • multi-qa-mpnet-base-dot-v1Embeddings
  • paraphrase-MiniLM-L6-v2Embeddings

Sesame 1

  • CSM 1BSpeech

Sourceful 4

  • Riverflow V2 FastImages
  • Riverflow V2 ProImages
  • Riverflow V2.5 FastImages
  • Riverflow V2.5 ProImages

SpaceXAI 14

  • Grok 4.20Text
  • Grok 4.20 Multi-AgentText
  • Grok 4.3Text
  • Grok 4.3batchText
  • Grok 4.5Text
  • Grok 4.6Text
  • Grok 4.7Text
  • Grok Build 0.1Text
  • Grok Imagine Image QualityImages
  • Grok Imagine VideoVideo
  • Grok Imagine Video 1.5Video
  • Grok Imagine Video 1.5 LiteVideo
  • Grok STT 1.0Speech recognition
  • Grok Voice TTS 1.0Speech

StepFun 3

  • Step 3.5 FlashText
  • Step 3.7 FlashText
  • Step 5 PreviewText

Tencent 8

  • Hunyuan A13B InstructText
  • Hy Image 3.5 PreviewImages
  • Hy-MT2-1.8BText
  • Hy-MT2-30B-A3BText
  • Hy-MT2-7BText
  • Hy3Text
  • Hy3 previewText
  • Hy4 previewText

TheDrummer 3

  • Cydonia 24B V4.1Text
  • Skyfall 36B V2Text
  • UnslopNemo 12BText

Thenlper 2

  • GTE-BaseEmbeddings
  • GTE-LargeEmbeddings

Thinking Machines 4

  • InklingText
  • InklingfreeText
  • Inkling SmallText
  • Inkling SmallfreeText

Together 1

  • Tev1 4B ExperimentalDecisions

TypeSafe 4

  • Jev 1.13Decisions
  • Jev 1.14Decisions
  • Jev LatestDecisions
  • Jev RouterText

Upstage 5

  • Solar DecideDecisions
  • Solar Decide FlashDecisions
  • Solar Mini 4Text
  • Solar Pro 3Text
  • Solar Pro 4Text

Venice 1

  • UncensoredText

VoyageAI by MongoDB 9

  • rerank-2.5Reranking
  • rerank-2.5-liteReranking
  • rerank-3Reranking
  • rerank-3-liteReranking
  • voyage-4Embeddings
  • voyage-4-largeEmbeddings
  • voyage-4-liteEmbeddings
  • voyage-code-4Embeddings
  • voyage-multimodal-3.5Embeddings

Writer 1

  • Palmyra X5Text

xAI 2

  • Grok Imagine Image 2.0Images
  • Grok LatestText

Xiaomi 5

  • MiMo-V2.5Text
  • MiMo-V2.5-ProText
  • MiMo-V2.6-FlashText
  • MiMo-V2.6-ProText
  • MiMo-V2.6-Pro-UltraSpeedText

XingChen 1

  • Xing4.0 29B A4BfreeText

Z.ai 20

  • GLM 4.5Text
  • GLM 4.5 AirText
  • GLM 4.5VText
  • GLM 4.6Text
  • GLM 4.6VText
  • GLM 4.7Text
  • GLM 4.7 FlashText
  • GLM 5Text
  • GLM 5 TurboText
  • GLM 5.1Text
  • GLM 5.2Text
  • GLM 5.3Text
  • GLM 5.3batchText
  • GLM 5.3 FlashText
  • GLM 5.3 FlashbatchText
  • GLM 5.3 FlashXText
  • GLM 5.3 PrimeText
  • GLM 5V TurboText
  • GLM Flash LatestText
  • GLM LatestText

Other 18

  • Auto RouterImages
  • Auto Router (Beta)Images
  • Body Builder (beta)Text
  • Free Models RouterText
  • Magnum v4 72BText
  • Mistral LargeText
  • Mistral Large 2407Text
  • MythoMax 13BText
  • Pareto 26.10Text
  • Pareto 26.9Text
  • Pareto Code RouterText
  • Pareto LatestText
  • Qwen2.5 72B InstructText
  • Qwen2.5 Coder 32B InstructText
  • Qwen3 Reranker 8BReranking
  • Reka EdgeText
  • Reka Flash 3Text
  • ReMM SLERP 13BText
> ls ./capabilities

Models for text, images, video and voice

Text models

Posts, emails, scripts, code, translations and answers — in a regular chat.

452 models
  • Claude Opus 5.5
  • GPT-6 Sol
  • Gemini 4 Argon
  • DeepSeek V4.1 Flash
  • Grok 4.7
  • Qwen3.8 Max Prime

Image generation

Illustrations, banners, covers, product photos and vector art from a description.

63 models
  • Nano Banana Pro
  • GPT Image 2.5 Sunburst
  • FLUX.2 Max
  • Seedream 5.0 Pro
  • Recraft V4.1 Pro
  • Qwen Image 3 Pro

Video generation

Clips from text or an image — for reels, ads and presentations.

30 models
  • Seedance 2.5
  • Veo 3.1
  • Kling Video v3.0 Pro
  • Wan 3.0 Prime
  • Runway Gen-4.5
  • Hailuo 2.3

Voice and speech recognition

Turn text into natural voices, plus audio transcription and music.

65 models
  • ElevenLabs Eleven v4
  • MiniMax Speech 2.8 HD
  • Gemini 3.8 Flash TTS
  • Fish Audio S2.1 Pro
  • Whisper Large V3
  • Lyria 3 Pro Preview
> cat ./why.txt

Why use an AI aggregator

01

One account instead of dozens

No need to sign up for every service — 683 models are available from one P2D account.

02

Text, images, video and voice together

Write a script, make the picture, turn it into video and add a voice — without jumping between sites.

03

Pay only for the result

No subscription: top up a dollar balance and spend it on any model as you generate.

> price --beta 1.0

Model prices: pay only for the result

No subscription and no monthly fee. Top up a dollar balance and spend it on any model — you are charged only for what you generate.

Beta 1.0 prices may change

What do you need
Answer length

Estimated total$0
Per answer
—
$10 covers
—
Lowest price
—
Top up and start →
A model answer$0.0001 – $1.14a typical answer, 371 models
Image 1024×1024$0.013 – $0.6061 models
Minute of speech$0.0012 – $0.3035 models
Minute of transcription$0.0004 – $0.03226 models
Videoactualprice is calculated after generation

An estimate. An answer’s cost depends on how long your prompt and the model’s reply are; an image is priced at 1024×1024; a minute of speech is about 1,000 characters. You are charged the actual generation cost. Some models cost more for very long prompts or at peak times.

FAQ

How many models are in the aggregator?

683 models from 80 developers: 452 for text, 63 for images, 30 for video, 35 for speech, 26 for speech recognition, plus models for music, search and classification.

Which models make video?

Seedance 2.5, Veo 3.1, Kling Video v3.0 Pro, Wan 3.0, Runway Gen-4.5, Hailuo 2.3 and others — 30 models in total.

Which models make images?

Nano Banana Pro, GPT Image 2.5, FLUX.2 Max, Seedream 5.0 Pro, Recraft V4.1, Qwen Image 3 and others — 63 models in total.

Do I need an account for every model?

No. One P2D account is enough — every model is available in the same window.

How do I pay?

Top up a dollar balance and spend it on any model — you are charged only for what you generate. You can top up via SBP.

How much does a generation cost?

It depends on the model: a typical answer starts at a fraction of a cent, an image from $0.01, and a minute of speech from $0.001. The calculator in Prices shows the exact cost for any model.

> start --all-models

Try every model in one window

Start generating →