Skip to main content

Model Catalog

AINative Studio provides access to 47 models across text, code, reasoning, image, video, audio, and embedding categories. Models are organized into four access tiers:

TierAccess
FreeAvailable to all users, no subscription required
BasicRequires Basic plan ($9/mo)
ProfessionalRequires Professional plan ($29/mo)
EnterpriseRequires Enterprise plan ($99/mo)

All models are accessible through the unified /v1/chat/completions endpoint (text/code/reasoning) or their respective modality endpoints (image, video, audio, embeddings).

Text / Chat Models​

General-purpose language models for conversation, content generation, and tool calling.

Model IDLabelProviderTierTags
llama-3.3-8b-instructLlama 3.3 8BMetaFreetext, fast
llama-3.3-70b-instructLlama 3.3 70BMetaFreetext
llama-4-maverick-17b-128eLlama 4 Maverick 17BMetaFreetext, multimodal
llama-4-scoutLlama 4 ScoutMetaFreetext, fast
gpt-oss-120bGPT OSS 120BCerebrasFreecoding, tools, text, fast
zai-glm-4.7GLM-4.7 (Preview)CerebrasFreecoding, text, fast
qwen-7bQwen 7BHuggingFaceBasictext, fast
claude-3-5-haikuClaude 3.5 HaikuAnthropicBasictext, coding, fast
claude-sonnet-4.5Claude Sonnet 4.5AnthropicProfessionaltext, coding, tools
claude-opus-4Claude Opus 4AnthropicEnterprisetext, coding, tools

Code Models​

Specialized for code generation, completion, and software engineering tasks.

Model IDLabelProviderTierTags
qwen-coder-7bQwen Coder 7BHuggingFaceBasiccoding
qwen-coder-32bQwen Coder 32BHuggingFaceProfessionalcoding, tools
nouscoder-14bNousCoder 14BNousCoderProfessionalcoding
minimax-m2.7MiniMax M2.7NVIDIA NIMProfessionalcoding, reasoning
devstralDevstralNVIDIA NIMProfessionalcoding
qwen3-coder-flashQwen3 Coder FlashDigitalOceanProfessionalcoding, tools, fast
qwen3.5-397bQwen3.5 397B MoEDigitalOceanProfessionalcoding, tools, reasoning, fast
deepseek-4-flashDeepSeek 4 FlashDigitalOceanProfessionalcoding, tools, reasoning
kimi-k2Kimi K2DigitalOceanProfessionalcoding, tools, reasoning

Reasoning Models​

Deep reasoning and chain-of-thought models for complex problem solving.

Model IDLabelProviderTierTags
deepseek-v3DeepSeek V3NVIDIA NIMProfessionalreasoning, text
deepseek-r1-distill-qwen-7bDeepSeek R1 Distill 7BHuggingFaceProfessionalreasoning
deepseek-r1-distill-llama-8bDeepSeek R1 Llama 8BHuggingFaceProfessionalreasoning
deepseek-r1DeepSeek R1HuggingFaceEnterprisereasoning

Image Models​

Text-to-image and image editing models.

Model IDLabelProviderTierTags
flux-schnellFLUX SchnellHuggingFaceProfessionalimage
flux-1-devFLUX 1 DevHuggingFaceProfessionalimage
flux-2Flux 2fal.aiProfessionalimage
seedream-5Seedream 5fal.aiProfessionalimage
nano-banana-2Nano Banana 2fal.aiProfessionalimage
grok-imagineGrok Imaginefal.aiProfessionalimage
happy-horseHappy Horsefal.aiProfessionalimage
sdxlStable Diffusion XLHuggingFaceProfessionalimage
qwen-image-edit-2511-loraQwen Image EditRunPodProfessionalimage, edit
sd-3.5-largeStable Diffusion 3.5HuggingFaceEnterpriseimage

Video Models​

Text-to-video and image-to-video generation models.

Model IDLabelProviderTierTags
kling-3-proKling 3 Profal.aiEnterprisevideo
veo-3Veo 3fal.aiEnterprisevideo
runway-gen-4.5Runway Gen 4.5RunPodEnterprisevideo, premium
hunyuanvideo-1.5HunyuanVideo 1.5HuggingFaceEnterprisevideo
cogvideox-2bCogVideoX 2BHuggingFaceEnterprisevideo
seedance-v1-5-pro-i2vSeedance Pro i2vRunPodEnterprisevideo
sora-2-i2vSora 2 i2vRunPodEnterprisevideo
wan-2-6-t2vWan 2.6 T2VRunPodEnterprisevideo

Audio / TTS Models​

Speech-to-text (transcription) and text-to-speech models.

Model IDLabelProviderTierTags
whisper-smallWhisper SmallHuggingFaceBasicaudio, transcription
whisper-large-v3-turboWhisper Large v3 TurboHuggingFaceBasicaudio, transcription
minimax-speech-02-hdMiniMax Speech 02 HDRunPodProfessionalaudio, tts
elevenlabs-ttsElevenLabs TTSElevenLabsProfessionalaudio, tts, voice-clone

Embedding Models​

Vector embedding models for semantic search and RAG pipelines.

Model IDLabelProviderTierTags
all-minilm-l6-v2All MiniLM L6 v2HuggingFaceFreeembeddings
bge-large-enBGE Large ENHuggingFaceBasicembeddings

Programmatic Access​

Retrieve the full model catalog programmatically:

curl -X GET https://api.ainative.studio/v1/public/models \
  -H "X-API-Key: your-api-key"

To get only models available for your current subscription tier:

curl -X GET https://api.ainative.studio/v1/public/models/available \
  -H "X-API-Key: your-api-key"

Both endpoints return JSON with the following structure:

{
  "ok": true,
  "models": [
    {
      "id": "llama-3.3-8b-instruct",
      "provider": "meta",
      "label": "Llama 3.3 8B",
      "capabilities": {
        "intelligence": 3,
        "speed": 5,
        "cost": 5
      },
      "context_window": 131072,
      "tags": ["text", "fast"],
      "tier": "free",
      "pricing": {
        "input": 0.0,
        "output": 0.0,
        "cache_read": 0.0
      }
    }
  ]
}

The response includes ETag and Last-Modified headers for cache validation.

Pricing​

Pricing is per 1M tokens (input/output) for text models, or per generation for image/video/audio models. Free-tier models have zero cost. See the Billing documentation for details on credit consumption.

Refs #3797