> ## Documentation Index > Fetch the complete documentation index at: https://docs.deepinfra.com/llms.txt > Use this file to discover all available pages before exploring further. # Deploy Llm Presets > DeepInfra presets and mirrored vLLM recipes for ``hf_repo_id``, told apart by ``source``; empty when none. Filter by ``gpu``/``engine``/``source``. ## OpenAPI ````yaml https://api.deepinfra.com/openapi.json get /deploy/llm/presets openapi: 3.1.0 info: title: DeepInfra API description: >- The DeepInfra API provides serverless AI inference, custom model deployments, and GPU rentals. version: 1.0.0 servers: - url: https://api.deepinfra.com security: [] tags: - name: Chat Completions description: OpenAI and Anthropic-compatible chat completion endpoints for LLMs. - name: Text Completions description: OpenAI-compatible text completion endpoints. - name: Embeddings description: Generate text embeddings for search and RAG. - name: Image Generation description: Generate, edit, and create variations of images. - name: Audio description: OpenAI-compatible speech synthesis, transcription, and translation. - name: Text to Speech description: ElevenLabs-compatible TTS endpoints and voice management. - name: Inference description: Native DeepInfra inference API for models and deployments. - name: Dedicated Models description: Deploy and manage private model instances with autoscaling. - name: GPU Rentals description: Rent dedicated GPU containers. - name: Models description: Browse, search, and manage AI models. - name: Files & Batches description: File uploads and batch processing. - name: LoRA Adapters description: Create, manage, and query LoRA adapter models. - name: Agents description: Manage agent-framework instances (OpenClaw and friends). - name: Sandboxes description: Create and manage isolated sandbox environments. - name: Account description: User profile, team management, and rate limits. - name: Authentication description: API tokens, SSH keys, scoped JWTs, and login flows. - name: Billing description: Payment methods, usage tracking, and billing. - name: Logs & Metrics description: Query inference logs, deployment logs, and usage metrics. - name: Utilities description: Feedback submission and CLI version. paths: /deploy/llm/presets: get: tags: - Dedicated Models summary: Deploy Llm Presets description: >- DeepInfra presets and mirrored vLLM recipes for ``hf_repo_id``, told apart by ``source``; empty when none. Filter by ``gpu``/``engine``/``source``. operationId: deploy_llm_presets_deploy_llm_presets_get parameters: - name: hf_repo_id in: query required: true schema: type: string title: Hf Repo Id - name: gpu in: query required: false schema: anyOf: - $ref: '#/components/schemas/DeployGPUs' - type: 'null' title: Gpu - name: engine in: query required: false schema: anyOf: - type: string - type: 'null' title: Engine - name: source in: query required: false schema: anyOf: - type: string - type: 'null' title: Source - name: xi-api-key in: header required: false schema: anyOf: - type: string - type: 'null' title: Xi-Api-Key - name: x-api-key in: header required: false schema: anyOf: - type: string - type: 'null' title: X-Api-Key responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/PresetConfigOut' title: Response Deploy Llm Presets Deploy Llm Presets Get '422': content: application/json: schema: $ref: '#/components/schemas/DeepError' description: Unprocessable Entity security: - HTTPBearer: [] components: schemas: DeployGPUs: type: string enum: - L4-24GB - L40S-48GB - A100-80GB - H100-80GB - H200-141GB - B200-180GB - B300-270GB - RTXPRO6000-96GB - other title: DeployGPUs PresetConfigOut: properties: id: type: string title: Id description: Preset id. source: type: string title: Source description: Config source. default: deepinfra engine: type: string title: Engine description: Inference engine. default: vllm gpu_configs: items: type: string type: array title: Gpu Configs description: Allowed Nx configs. standard_args: properties: max_context_size: anyOf: - type: integer maximum: 10000000 minimum: 1 - type: 'null' title: Max Context Size description: Maximum total sequence length (prompt + generation). max_concurrent_requests: anyOf: - type: integer maximum: 1024 minimum: 1 - type: 'null' title: Max Concurrent Requests description: Max number of requests served concurrently. gpu_memory_fraction: anyOf: - type: number maximum: 0.97 minimum: 0.5 - type: 'null' title: Gpu Memory Fraction description: >- Fraction of GPU memory the engine may use for weights + KV cache. max_prefill_tokens: anyOf: - type: integer maximum: 131072 minimum: 512 - type: 'null' title: Max Prefill Tokens description: >- Max tokens processed per prefill/engine step (chunked prefill size). kv_cache_dtype: anyOf: - type: string enum: - auto - fp8 - type: 'null' title: Kv Cache Dtype description: >- KV cache precision. fp8 ~doubles KV capacity at <1% accuracy loss. enable_prefix_caching: anyOf: - type: boolean - type: 'null' title: Enable Prefix Caching description: Reuse KV cache for shared prompt prefixes. quantization: anyOf: - type: string enum: - fp8 - awq - gptq - awq_marlin - gptq_marlin - compressed-tensors - bitsandbytes - type: 'null' title: Quantization description: On-the-fly weight quantization method. additionalProperties: false type: object title: StandardArgs description: Engine tuning knobs. extra_args: anyOf: - items: type: string type: array - type: 'null' title: Extra Args description: Raw engine flags; vLLM recipes only. label: type: string title: Label description: Short display name (e.g. "Throughput-optimized"). default: '' type: object required: - id - gpu_configs title: PresetConfigOut description: One preset deploy config for an HF model on specific hardware. DeepError: properties: error: type: string title: Error description: Error examples: - Model not found type: object required: - error title: DeepError securitySchemes: HTTPBearer: type: http scheme: bearer ````