> ## Documentation Index > Fetch the complete documentation index at: https://docs.neo.projectdiscovery.io/llms.txt > Use this file to discover all available pages before exploring further. # List supported models > Returns all models supported for tasks. Use this endpoint to discover available models and their capabilities. ## OpenAPI ````yaml /openapi/neo.public.openapi.json get /api/v1/models openapi: 3.1.0 info: contact: name: ProjectDiscovery url: https://neo.projectdiscovery.io description: Neo API Server - Security agent orchestration platform license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0 title: Neo API version: 1.0.0 servers: - description: Production url: https://neo.api.projectdiscovery.io - description: Development url: https://neo.api.dev.projectdiscovery.io - description: Local development url: http://localhost:8080 security: [] tags: - description: Task execution and management name: Tasks - description: Agent listing and management name: Agents - description: Public agent directory name: Agent Directory - description: User file storage management name: Files - description: User working memory management name: Memory - description: Scheduled and recurring task management name: Schedules - description: Knowledge base and semantic search name: Knowledge - description: Encrypted user credentials and API keys name: Secrets - description: Neo API key management for programmatic access name: API Keys - description: User profile and account information name: User - description: Task and LLM usage tracking name: Usage - description: Bring Your Own Key provider management name: BYOK - description: Connect personal AI provider accounts and select them as a model source name: AI Connections - description: Model discovery and capabilities name: Models - description: Third-party integrations name: Integrations - description: Skill knowledge documents for agent prompts name: Skills - description: User-authored tools and toolkit management name: Dynamic Tools - description: Team management and member invitations name: Teams - description: Prompt library management and discovery name: Prompts - description: Slack bot integration for workspace installation and OAuth name: Slack - description: GitHub integration for PR reviews and repository management name: GitHub - description: Vulnerability issue tracking and management name: Issues - description: Subscription billing and plans name: Billing - description: Project management and member assignments name: Projects - description: SSH key pair generation and management for remote server access name: SSH Keys - description: Codebase structural analysis and mapping name: Codemaps - description: AI-generated codebase documentation and security analysis name: CodeWiki - description: Captured HTTP traffic query and replay name: Network Events - description: User and team API activity metadata name: Audit Logs - description: Vulnerability triage for HackerOne, GitHub, and Security Inbox name: Triage paths: /api/v1/models: get: tags: - Models summary: List supported models description: | Returns all models supported for tasks. Use this endpoint to discover available models and their capabilities. operationId: get-v1-models responses: '200': content: application/json: schema: $ref: '#/components/schemas/ModelsResponse' description: List of supported models '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Internal server error security: - BearerAuth: [] - ApiKeyAuth: [] components: schemas: ModelsResponse: properties: model_source: description: > The model source the list belongs to. Present when the deployment lists provider-reported models for non-Neo accounts. enum: - neo - byok - ai_connections type: string models: description: > List of models the caller can select. For the `neo` model source this is Neo's catalog. For `byok` and `ai_connections` it is the set of models the account's own provider credentials can reach; each `id` is the provider's exact model ID and Neo premium gating does not apply. items: $ref: '#/components/schemas/ModelInfo' type: array required: - models type: object ErrorResponse: properties: code: description: > Stable machine-readable error code — branch on this rather than matching the human `error`/`message` strings. `access_restricted` (HTTP 403) denies hosted Neo access under the access policy. On team invitations, param=email identifies a restricted recipient rather than the caller; show the error without redirecting the caller. Domain codes include `user_spending_cap_reached`, `project_spending_cap_reached`, and `insufficient_neo_credits`; Free/usage codes include `free_grant_challenge_required`, `free_usage_exhausted`, `free_task_budget_exhausted`, `model_not_available_on_free`, `sandbox_not_available_on_free` (cloud sandbox surfaces are not available on the Free plan; task files remain available from the task), `free_cannot_continue_managed_task` (a task that ran on the standard cloud sandbox cannot be continued on the Free plan; start a new task), `free_origin_not_supported` (integration-originated tasks are not available on the Free plan), `weekly_usage_limit_reached`, `billing_period_usage_limit_reached`, `topup_required`, `subscription_required`, and `isolated_workspace_purged`. Otherwise it mirrors the error kind (e.g. `forbidden`, `invalid_request`, `not_exists`, `already_exists`). example: user_spending_cap_reached type: string error: example: Bad request type: string error_id: description: Correlation id for a specific error instance, when present. type: string kind: description: Coarse error category (e.g. "forbidden request", "invalid request"). example: forbidden request type: string message: description: | Human-readable detail (the kind prefixed to the error). For display, not for branching. type: string param: description: >- Field rejected by the policy; email for a restricted invite recipient. type: string turnstile_site_key: description: | Public Cloudflare Turnstile site key returned only with `free_grant_challenge_required`, so the client can complete the invisible verification before retrying the request. type: string required: - error type: object ModelInfo: properties: context_window: description: Maximum context window size in tokens type: integer credential_ref: description: >- The credential that serves this row on the byok source: a provider key ID or a custom endpoint ID. Pass it back as the task's `credential_ref` to run the model on that credential. Omitted on the Neo model source. type: string cyber_verified: description: >- Whether the model runs under a model provider's cyber verification grant (Anthropic's Cyber Verification Program), which relaxes the safeguards that block dual-use security work such as exploit development and penetration testing. Set only on the neo source, from Neo's grants with its model providers; a request that fails over to another route does not carry the grant. Omitted on byok and AI connections, where the grant belongs to the key's own organization. type: boolean data_regions: description: >- Regions the model's processing stays inside. On the neo source this is always us, under Neo's contracts with its model providers. On byok, only OpenRouter and Vercel AI Gateway report it, and a model outside every region is routed globally. Omitted when unknown. items: enum: - eu - us type: string x-enum-varnames: - ModelInfoDataRegionsEu - ModelInfoDataRegionsUs type: array default_reasoning_effort: description: Reasoning effort Neo applies when the request omits an override. enum: - none - minimal - low - medium - high - xhigh - max type: string x-enum-varnames: - ModelInfoDefaultReasoningEffortNone - ModelInfoDefaultReasoningEffortMinimal - ModelInfoDefaultReasoningEffortLow - ModelInfoDefaultReasoningEffortMedium - ModelInfoDefaultReasoningEffortHigh - ModelInfoDefaultReasoningEffortXhigh - ModelInfoDefaultReasoningEffortMax default_speed: description: Speed Neo applies when the request omits an override. enum: - standard - fast type: string x-enum-varnames: - ModelInfoDefaultSpeedStandard - ModelInfoDefaultSpeedFast description: description: Short description of the model's strengths type: string details: description: Model capability ratings and specialty info properties: cyber_security: description: Cyber-security capability rating (1-10) type: integer reasoning: description: Reasoning capability rating (1-10) type: integer specialty: description: Detailed description of the model's specialty type: string speed: description: Response speed rating (1-10) type: integer type: object id: description: | Model identifier (e.g., "sonnet-4.6"). Unique among the Neo and fixed-provider rows, but not across custom endpoints: two endpoints that serve one model ID are two rows with the same `id` and different `credential_ref` values. type: string is_premium: description: Whether the model requires premium/enterprise access type: boolean logo: description: Logo URL (string) or light/dark variant object oneOf: - type: string - properties: dark: type: string light: type: string required: - light - dark type: object max_output_tokens: description: Maximum output tokens type: integer name: description: Human-readable model name (e.g., "Claude Sonnet 4.6") type: string provider: description: >- Model provider (e.g., "anthropic", "openai", "google"), or "custom" for a custom OpenAI-compatible endpoint (its name is in `provider_label`). type: string provider_label: description: >- The provider as the user knows it: the product name of a fixed provider, or the name the user gave a custom endpoint. Omitted on the Neo model source. type: string reasoning_can_disable: description: >- Whether reasoning can be switched off for this model. False means it always reasons. Omitted when unknown. type: boolean reasoning_efforts: description: >- Exact reasoning effort overrides accepted for this Neo model. An empty array means the model uses its pinned/default reasoning behavior and accepts no override. items: enum: - none - minimal - low - medium - high - xhigh - max type: string x-enum-varnames: - ModelInfoReasoningEffortsNone - ModelInfoReasoningEffortsMinimal - ModelInfoReasoningEffortsLow - ModelInfoReasoningEffortsMedium - ModelInfoReasoningEffortsHigh - ModelInfoReasoningEffortsXhigh - ModelInfoReasoningEffortsMax type: array reasoning_style: description: >- How the model takes a reasoning option. Omitted when the provider did not say. enum: - adaptive - effort - max_tokens type: string x-enum-varnames: - ModelInfoReasoningStyleAdaptive - ModelInfoReasoningStyleEffort - ModelInfoReasoningStyleMaxTokens supported_input_modalities: description: >- Input types the provider reports for the model. Omitted when unknown. items: type: string type: array supported_output_modalities: description: >- Output types the provider reports for the model. Omitted when unknown. items: type: string type: array supports_reasoning: description: Whether the model supports reasoning/chain-of-thought type: boolean supports_speed: description: >- Whether the model accepts an explicit standard or fast speed selection. type: boolean supports_structured_output: description: >- Whether the provider reports that the model can return structured (JSON schema) output. Omitted when unknown. type: boolean supports_tools: description: >- Whether the provider reports that the model can call tools. Omitted when unknown. type: boolean zdr_available: description: >- Whether zero data retention is available. On the neo source it is always true and applies to every request, under Neo's contracts with its model providers. On byok, true means at least one route offers it; only OpenRouter and Vercel AI Gateway report it. Omitted when unknown. type: boolean required: - id - name - provider - context_window - supports_reasoning type: object securitySchemes: BearerAuth: bearerFormat: JWT description: JWT authentication token scheme: bearer type: http ApiKeyAuth: description: Neo API key (neo_sk_* prefix) in: header name: X-Api-Key type: apiKey ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.