> ## 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 - OpenAI Format > The MessariAI API's Chat Completion endpoint is used for generating contextual crypto responses using Messari's knowledge graph and specialized tools. It follows OpenAI's chat completions API specification for easy integration with libraries like [OpenAI's official python SDK](https://github.com/openai/openai-python). 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/openai/chat/completions openapi: 3.0.0 info: description: OpenAPI specification for the entire Messari API title: Messari API - Ai Openai version: 1.0.0 servers: - description: Messari API url: https://api.messari.io security: [] paths: /ai/openai/chat/completions: post: summary: Generate chat completions in OpenAI format description: >- Processes a conversation and returns an AI-generated response in OpenAI-compatible format. Consumes 5 credits per request. operationId: postChatCompletionOpenAI requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequestOpenAI' example: model: messari messages: - role: user content: What is Solana? required: true responses: '200': content: application/json: schema: properties: choices: description: Array of completion choices items: $ref: '#/components/schemas/ChatCompletionResponseChoiceOpenAI' type: array created: description: Unix timestamp when the completion was created format: int64 type: integer id: description: Unique identifier for the completion request type: string metadata: allOf: - $ref: >- #/components/schemas/ChatCompletionResponseMetadataOpenAI - description: Additional metadata about the completion model: description: Model used for the completion type: string object: description: Type of object returned, always 'chat.completion' type: string required: - choices - created - id - model - object type: object example: id: b72679d2-2144-41f1-9a15-252df2f264b3 object: chat.completion created: 1762276239 model: messari-ai choices: - index: 0 message: role: assistant content: >- # Solana Overview Solana is a Layer-1 blockchain network designed to provide a highly scalable infrastructure for decentralized applications (dapps). Its primary goal is to minimize performance constraints, such as transaction throughput limitations and high costs, typically faced by developers on other networks. ## Core Features and Technology Solana is optimized for speed and efficiency, aiming to achieve high throughput without relying on second-layer or off-chain technologies. * **Scalability and Throughput:** Solana uses a Proof of Stake (PoS) consensus mechanism combined with a unique innovation called Tower Consensus. This design allows the network to handle a high volume of transactions, with the capacity to process up to 710,000 transactions per second (TPS) at peak load. * **Developer Support:** The network supports all LLVM-compatible smart contract languages, offering flexibility for developers. * **Transaction Efficiency:** Solana is designed for sub-second settlement times and low transaction costs. * **Token Extensions:** Developers launching SPL tokens on Solana can utilize various token extensions, such as Confidential Transfers, which hides transaction amounts to protect user balance confidentiality during transfers. ## The SOL Token The native token of the Solana network is **SOL**, which was launched alongside the Mainnet Beta in March 2020. * **Transaction Fees:** Users pay fees in SOL for sending transactions and executing smart contracts. These fees include a static base fee plus a variable fee based on the computational resources used. Users can also include an optional "prioritization fee" to expedite transaction processing. * **Staking and Governance:** SOL is also used for staking to secure the network and for on-chain governance. ## Ecosystem and Use Cases Solana's infrastructure supports various applications and services, including: * **Decentralized Finance (DeFi):** Projects like Ellipsis Labs' Phoenix, a spot limit order book implementation, are built on Solana to create efficient and scalable DeFi liquidity primitives. * **Payments (Solana Pay):** Solana Pay is a protocol for payments that uses the blockchain to create new commerce rails for merchants, enabling secure payments without intermediaries. * **Gaming and Customer Engagement:** Services like GameShift streamline the integration of Web3 features into games, handling interactions with Solana for self-custodied game assets and abstracted transaction fees. Bond is another platform powered by Solana designed to boost customer engagement for brands through digital collectibles, authentication, and loyalty programs. ## Recent Market Sentiment Recent market activity suggests a strong institutional interest in Solana, contrasting with other major cryptocurrencies: * **ETF Inflows:** In early November 2025, Solana ETFs attracted significant investment, totaling **$421 million in inflows** for the week. This was driven by the successful launch of new U.S.-based funds, such as Bitwise's Solana ETF, which reached $105 million in assets under management in its first week. * **Market Divergence:** This surge in Solana investment occurred while Bitcoin and Ethereum products experienced significant outflows, indicating a divergence in institutional capital allocation. Solana's year-to-date inflows reached $3.3 billion. ## Company Background Solana was founded in **2017** and is headquartered in San Francisco, CA. The company has raised a total of **$335 million** in funding. finish_reason: stop metadata: status: Completed trace_id: b72679d2-2144-41f1-9a15-252df2f264b3 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: trending_topic title: Warden Protocol's $900K Mindshare Leaderboard Launch url: https://messari.io/topics - domain: trending_topic title: >- Wintermute Denies Binance Lawsuit Rumors Amid CZ's ASTER Investment url: https://messari.io/topics - domain: trending_topic title: Wallchain's Quack Reward System and Project Campaigns url: https://messari.io/topics - domain: trending_topic title: Billion-Dollar Liquidation Cascade url: https://messari.io/topics - domain: trending_topic title: 'ETF Flow Divergence: Bitcoin Outflows vs Solana Surge' url: https://messari.io/topics - 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: ChatCompletionRequestOpenAI: 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: 0 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: 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 type: array default: - role: user content: What is Solana? 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 ChatCompletionResponseChoiceOpenAI: properties: finish_reason: description: Reason the model stopped generating (e.g., 'stop') type: string index: description: Index of the choice in the array format: int64 type: integer message: type: object description: The message output by the model properties: role: type: string description: The role of the message author example: assistant content: type: string description: The content of the message required: - role - content required: - finish_reason - index - message type: object ChatCompletionResponseMetadataOpenAI: properties: charts: description: Chart data referenced in the response items: $ref: '#/components/schemas/ChartSource' type: array related_questions: description: Follow-up questions related to the original query items: type: string type: array sources: description: >- Sources used to construct the response content. If using inline citations, sources will include citationIds associated with the response citations. items: $ref: '#/components/schemas/StandardSource' 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 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 ````