modelschemas
.com
models
schemas
changes
examples
docs
openapi.json
get an API key
GET
/v1/schemas
copy url
Accept:
readable
json
schemas
2521
providers
63
cache
swr
provider=any
provider=amazon-bedrock
provider=ant-ling
provider=anthropic
provider=assemblyai
provider=azure
provider=baseten
provider=bfl
provider=byteplus
provider=cartesia
provider=cerebras
provider=cloudflare-ai-gateway
provider=cloudflare-workers-ai
provider=cohere
provider=dashscope
provider=dashscope-cn
provider=deepgram
provider=deepseek
provider=elevenlabs
provider=fal
provider=fireworks
provider=fish-audio
provider=gemini
provider=google-vertex
provider=google-vertex-anthropic
provider=grok
provider=groq
provider=huggingface
provider=hyperbolic
provider=jina
provider=kimi-code-plan-cn
provider=kimi-code-plan-global
provider=kling
provider=llmgateway
provider=lovable
provider=meta
provider=minimax
provider=minimax-cn
provider=mistral
provider=moonshot
provider=moonshotai-cn
provider=neon
provider=novita
provider=nvidia
provider=ollama
provider=ollaya
provider=openai
provider=opencode
provider=opencode-go
provider=openrouter
provider=perplexity
provider=reactor
provider=replicate
provider=runway
provider=sambanova
provider=stability
provider=together
provider=typesafe
provider=vercel
provider=voyage
provider=worldlabs
provider=xiaomi
provider=zai
provider=zhipuai-coding-plan
activity=any
activity=chat
activity=image
activity=video
activity=audio
activity=embeddings
activity=moderation
50 of 2521 endpoints
endpoint
provider
activity
aisingapore/sea-lion-7b-instruct
nvidia
chat
input →
output →
bigcode/starcoder2-15b
nvidia
chat
input →
output →
deepseek-ai/deepseek-v4.1-flash
nvidia
chat
input →
output →
fastino/gliner2-pii
nvidia
chat
input →
output →
google/codegemma-7b
nvidia
chat
input →
output →
google/diffusiongemma-26b-a4b-it
nvidia
chat
input →
output →
google/gemma-4-31b-it
nvidia
chat
input →
output →
meta/codellama-70b
nvidia
chat
input →
output →
meta/llama-guard-4-12b
nvidia
chat
input →
output →
meta/llama2-70b
nvidia
chat
input →
output →
meta/muse-glimmer-30b
nvidia
chat
input →
output →
minimaxai/minimax-m3.1-flash
nvidia
chat
input →
output →
mistralai/mistral-7b-instruct-v0.3
nvidia
chat
input →
output →
mistralai/mistral-large-4-1t-a52b
nvidia
chat
input →
output →
moonshotai/kimi-k2.6
nvidia
chat
input →
output →
moonshotai/kimi-k3
nvidia
chat
input →
output →
moonshotai/kimi-k3.1-pro
nvidia
chat
input →
output →
nvidia/ising-calibration-1.5-31b
nvidia
chat
input →
output →
nvidia/llama-3.1-nemoguard-8b-content-safety
nvidia
chat
input →
output →
nvidia/llama-3.1-nemoguard-8b-topic-control
nvidia
chat
input →
output →
nvidia/llama-3.1-nemotron-70b-instruct
nvidia
chat
input →
output →
nvidia/llama-3.1-nemotron-safety-guard-8b-v3
nvidia
chat
input →
output →
nvidia/llama-3.1-nemotron-ultra-253b-v1
nvidia
chat
input →
output →
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
nvidia
chat
input →
output →
nvidia/nemotron-3-super-120b-a12b
nvidia
chat
input →
output →
nvidia/nemotron-3-ultra-550b-a55b
nvidia
chat
input →
output →
nvidia/nemotron-3.5-bolt-e4b
nvidia
chat
input →
output →
nvidia/nemotron-3.5-content-safety
nvidia
chat
input →
output →
nvidia/nemotron-3.5-lightning-30b-a3b
nvidia
chat
input →
output →
nvidia/nemotron-3.5-super-vl-120b-a12b
nvidia
chat
input →
output →
nvidia/nemotron-4-340b-reward
nvidia
chat
input →
output →
nvidia/nemotron-parse
nvidia
chat
input →
output →
nvidia/nemotron-parse-2.0
nvidia
chat
input →
output →
nvidia/riva-translate-4b-instruct
nvidia
chat
input →
output →
nvidia/riva-translate-4b-instruct-v2
nvidia
chat
input →
output →
openai/gpt-oss-20b
nvidia
chat
input →
output →
poolside/laguna-xs-2.1
nvidia
chat
input →
output →
stepfun-ai/step-5-preview
nvidia
chat
input →
output →
z-ai/glm-5.3
nvidia
chat
input →
output →
z-ai/glm-5.3-flash
nvidia
chat
input →
output →
nvidia/embed-qa-4
nvidia
embeddings
input →
output →
nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1
nvidia
embeddings
input →
output →
nvidia/llama-3.2-nv-embedqa-1b-v1
nvidia
embeddings
input →
output →
nvidia/llama-nemotron-embed-vl-1b-v2
nvidia
embeddings
input →
output →
nvidia/nemotron-3-embed-1b
nvidia
embeddings
input →
output →
nvidia/nemotron-3.5-embed-1b
nvidia
embeddings
input →
output →
nvidia/nemotron-3.5-embed-8b
nvidia
embeddings
input →
output →
nvidia/nv-embedqa-mistral-7b-v2
nvidia
embeddings
input →
output →
nvidia/nvclip
nvidia
embeddings
input →
output →
snowflake/arctic-embed-l
nvidia
embeddings
input →
output →