> ## Documentation Index > Fetch the complete documentation index at: https://docs.messari.io/llms.txt > Use this file to discover all available pages before exploring further. # Chat Completion - Messari Format > The MessariAI API's Chat Completion endpoint is used for generating contextual crypto responses using Messari's knowledge graph and specialized tools. If you'd like to play around with the responses feel free to try on the [Messari web-app](https://messari.io/copilot), it uses the same underlying endpoint implementation. The chat completion endpoint leverages a graph architecture with agents to: * Access Messari's real-time quantitative (compute) dataset which includes but is not limited to: Market data, Asset metrics, Fundraising, Token unlocks * Access Messari's qualitative (search) dataset which includes but is not limited to: News, Blogs, Youtube transcriptions, RSS-feeds, Twitter, Webcrawl documents, Proprietary datasets of: Research, Quarterlies, Diligence Reports * Generate market insights and analysis * Process natural language queries about crypto assets, protocols and projects For a more interactive experience trying out the API, [here is our Replit in Typescript](https://replit.com/@malcolm22/MessariAI-API-Examples#index.ts). Simply populate the `API_KEY` field with your Enterprise API key generated in the [Messari Account > API page](https://messari.io/account/api) of our webapp and you're off! ### Request Params #### verbosity The `verbosity` parameter controls the level of detail in the model's response. When set to `"verbose"`, the model provides more comprehensive and detailed explanations, including additional context, examples, and supporting information. Other possible values might include `"balanced"` or `"succinct"` for shorter responses. Example usage: ```json theme={null} { "verbosity": "verbose" } ``` #### response\_format The `response_format` parameter specifies the desired formatting style for the model's response. When set to `"markdown"`, the output will be formatted using Markdown syntax, allowing for structured text with headings, lists, code blocks, and other formatting elements. Other common option might include `"text"`. **Example usage:** ```json theme={null} { "response_format": "markdown" } ``` #### inline\_citations The `inline_citations` parameter determines whether the response metadata should include citations within its response text. When set to `true`, the model will reference sources directly in the text where information is being drawn from. This is particularly useful for academic, research, or factual content where attribution is important. **Example usage:** ```json theme={null} { "inline_citations": true } ``` #### stream The `stream` parameter controls whether the API response is delivered as a complete response or as a stream of partial responses. When set to `false`, the API will wait until the entire response is generated and then deliver it in one piece. When set to `true`, the API would begin sending partial responses as they are generated, useful for implementing real-time typing effects or processing responses incrementally. **Example usage:** ```json theme={null} { "stream": false } ``` #### generate\_related\_questions The `generate_related_questions` parameter determines whether the response metadata should include AI-generated related questions to the user query. This feature is useful for receiving follow up questions as part of the API response payload to prompt the user with potential next questions. Note: A maximum of 5 is allowed. **Example usage:** ```json theme={null} { "generate_related_questions": 2 } ``` ## OpenAPI ````yaml POST /ai/v1/chat/completions openapi: 3.0.0 info: description: OpenAPI specification for the entire Messari API title: Messari API - Ai V1 version: 1.0.0 servers: - description: Messari API url: https://api.messari.io security: [] paths: /ai/v1/chat/completions: post: summary: Generate chat completions with Messari AI description: >- Processes a conversation and returns an AI-generated response with Messari's standard format. Consumes 5 credits per request. operationId: postChatCompletion requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' example: messages: - role: user content: What is Solana? required: true responses: '200': content: application/json: schema: properties: data: $ref: '#/components/schemas/ChatCompletionResponse' error: type: string metadata: $ref: '#/components/schemas/ChatCompletionResponseMetadata' required: - data type: object example: error: null data: messages: - role: assistant content: >- # Solana Overview Solana is a Layer-1 blockchain network optimized for **scalability** and designed to provide infrastructure for decentralized applications (dapps). Its primary goal is to offer a platform where developers can build applications without encountering common performance bottlenecks, such as high transaction fees and throughput limitations. ## Key Features and Design Goals Solana's design emphasizes high performance and efficiency, aiming to minimize constraints typically faced by developers: * **High Throughput:** The network is designed to handle a high volume of transactions, with the capacity to process up to 710,000 transactions per second (TPS) at peak load. * **Low Costs:** It aims for low transaction costs and sub-second settlement times. * **Scalability:** Solana achieves scalability without relying on second-layer or off-chain technologies. * **Smart Contract Support:** It supports all LLVM-compatible smart contract languages, which is a collection of modular compiler and toolchain technologies. The network utilizes a Proof of Stake (PoS) consensus mechanism combined with a unique component called Tower Consensus to achieve its high throughput. ## The SOL Token The native token of the Solana network is **SOL**, which was launched alongside the Mainnet Beta in March 2020. SOL serves several essential functions within the ecosystem: * **Transaction Fees:** Users pay fees in SOL for sending transactions and executing smart contracts. These fees include a static base fee per signature and a variable fee based on the computational resources used. Transactions can also include an optional "prioritization fee" for faster processing. * **Staking:** SOL is used for staking to secure the network. * **Governance:** The token is used for on-chain governance. ## Ecosystem and Applications Solana provides a robust environment for various decentralized applications and services: * **Decentralized Finance (DeFi):** Projects like Phoenix, a spot limit order book implementation by Ellipsis Labs, are built on Solana to create efficient and scalable DeFi infrastructure. * **Payments:** Solana Pay is a protocol for payments on Solana, designed to build new payment and commerce rails for merchants that utilize the blockchain for secure transactions without intermediaries. * **Gaming and NFTs:** Solana offers tools like GameShift, an API that streamlines integration with Web3 features for development studios, handling interactions with Solana for self-custodied game assets and abstracted transaction fees. * **Customer Engagement:** Platforms like Bond utilize Solana to drive customer engagement for brands through digital collectibles, luxury-good authentication, verified digital identities, and loyalty programs. ## Company Background Solana was founded in 2017 and is headquartered in San Francisco, CA. It is a private company that has raised a total of $335 million in funding. metadata: status: Completed trace_id: 63c56f80-4ac7-4e24-8fb7-a896e8bc5100 cited_sources: - domain: asset_profile url: https://messari.io/asset/solana - domain: diligence title: 'Diligence Report: General Information' url: >- https://messari.io/asset/solana/diligence-report#general_information - domain: diligence title: 'Diligence Report: Token Economics' url: >- https://messari.io/asset/solana/diligence-report#token_usage_and_economics - domain: research_image title: Solana Ecosystem Overview url: >- https://cdn.sanity.io/images/2bt0j8lu/production/10299763330e60bae0a812764da7cbd1c3e3d153-1940x976.png?w=800 - domain: research_image title: 'Solana Deep Dive: Reframing The Narrative' url: >- https://cdn.sanity.io/images/2bt0j8lu/production/7a725362c19ddb5f7b089a68dcc13d416fa6726d-2782x1508.png?w=800 - domain: news title: >- What Is Solana? A Scalable, Decentralized Network for Dapps url: >- https://decrypt.co/resources/what-is-solana-a-scalable-decentralized-network-for-dapps - domain: webcrawl url: https://www.kraken.com/prices/solana - domain: webcrawl title: >- Solana Company Profile 2025: Valuation, Funding & Investors | PitchBook url: https://pitchbook.com/profiles/company/227820-52 - domain: webcrawl title: >- Solana - Products, Competitors, Financials, Employees, Headquarters Locations url: https://www.cbinsights.com/company/solana-labs - domain: webcrawl title: >- There are no bad questions about... blockchain payments | Solana url: https://solana.com/learn/payments description: Default response '400': content: application/json: schema: properties: data: {} error: type: string required: - data type: object description: Bad Request '401': content: application/json: schema: properties: data: {} error: type: string required: - data type: object description: Unauthorized '500': content: application/json: schema: properties: data: {} error: type: string required: - data type: object description: Internal Server Error security: - apiKey: [] components: schemas: ChatCompletionRequest: properties: allow_clarification_query: description: Whether the AI can ask for clarification when the query is ambiguous type: boolean default: true generate_related_questions: description: Adds AI generated related questions to use as follow up questions format: int64 type: integer default: 2 inline_citations: description: Adds inline citation document references in the payload metadata type: boolean default: true messages: description: Array of messages in the conversation history items: $ref: '#/components/schemas/ChatCompletionMessage' type: array response_format: description: >- Text format for the response. Values accepted are 'markdown' and 'plaintext'. type: string default: markdown stream: description: Stream the response through the API type: boolean default: false verbosity: description: >- Controls the length and detail level of the AI-generated response. Values accepted are 'succinct', 'balanced', and 'verbose'. type: string default: balanced required: - messages type: object ChatCompletionResponse: properties: messages: description: Array of response messages from the assistant items: $ref: '#/components/schemas/ChatCompletionResponseMessage' type: array required: - messages type: object ChatCompletionResponseMetadata: properties: charts: description: Chart data referenced in the response items: $ref: '#/components/schemas/ChartSource' type: array cited_sources: description: Sources cited in the response content items: $ref: '#/components/schemas/StandardSource' type: array related_questions: description: Follow-up questions related to the original query items: type: string type: array status: description: Current status of the completion request type: string trace_id: description: Unique identifier for tracing the request format: byte type: string required: - status - trace_id type: object ChatCompletionMessage: type: object properties: role: type: string enum: - user - assistant - system default: user description: The role of the message author content: type: string default: What is Solana? description: The content of the message required: - role - content ChatCompletionResponseMessage: type: object description: Schema for ChatCompletionResponseMessage properties: {} additionalProperties: true ChartSource: type: object description: Schema for ChartSource properties: {} additionalProperties: true StandardSource: type: object description: Schema for StandardSource properties: {} additionalProperties: true securitySchemes: apiKey: in: header name: X-Messari-API-Key type: apiKey ````