{"api_name":"xAI","docs_url":"https://docs.x.ai/developers/quickstart.md","domain":"docs.x.ai","generated_at":"2026-10-25T22:00:56.835292+00:00","agent_readiness_score":65,"certification_level":"Agent-Compatible With Gaps","agent_commerce_score":30,"agent_commerce_level":"Agent Commerce Emerging","agent_commerce":{"generated_at":"2026-10-25T22:00:56.715910+00:00","agent_commerce_score":30,"agent_commerce_level":"Agent Commerce Emerging","payment_protocol_detected":false,"machine_payment_capable":false,"detected_protocols":[],"category_scores":{"mcp_support":0,"agent_identity_auth":0,"machine_payments":0,"machine_pricing":10,"budget_controls":0,"agent_rate_controls":0,"deterministic_errors":10,"auditability":5,"agent_security":0,"agent_observability":5},"strengths":["Machine-readable consumption pricing","Deterministic machine-readable errors"],"gaps":["MCP support","Agent identity / scoped authorization","Machine-native payments","Budget / spend controls","Agent rate and quota controls","Least-privilege agent security"],"matched_signals":{"mcp_support":{"score":0,"matched_terms":["mcp server","mcp tools","mcp","tool server"],"lexical_score_before_guardrails":10,"guardrail_note":"MCP keywords alone do not prove an operational API integration. Reviewed pages document a search/lookup MCP server or lack a concrete MCP API-operation claim."},"agent_identity_auth":{"score":0,"matched_terms":["authorization"]},"machine_payments":{"score":0,"matched_terms":[]},"machine_pricing":{"score":10,"matched_terms":["per request","pricing"]},"budget_controls":{"score":0,"matched_terms":["spend","limit"],"lexical_score_before_guardrails":5,"guardrail_note":"No affirmative agent/API-key spending cap in reviewed pages; keyword matches such as pagination 'limit' or 'spend' warnings do not establish budget controls."},"agent_rate_controls":{"score":0,"matched_terms":["rate limit","rate limits","limits"],"lexical_score_before_guardrails":10,"guardrail_note":"No concrete API request rate-control evidence in reviewed pages; GPU scheduling 'quota' and pagination 'limits' are out of scope."},"deterministic_errors":{"score":10,"matched_terms":["idempotency","errors"]},"auditability":{"score":5,"matched_terms":["logs","history"]},"agent_security":{"score":0,"matched_terms":[]},"agent_observability":{"score":5,"matched_terms":["metrics","usage","dashboard"]}},"evidence_signals":{"machine_pricing":[{"source_url":"https://docs.x.ai/developers/quickstart.md","matched_terms":["pricing"],"snippet":"iew) - Web search, X search, code execution, and function calling * [Models](/developers/models) - Compare available models and their capabilities * [Pricing](/developers/pricing) - Tools, batch API, and other platform pricing * [Grok Bot](/grok-bot/overview) - AI teammates on a persistent cloud computer * [Grok..."},{"source_url":"https://docs.x.ai/developers/pricing.md","matched_terms":["per request","pricing"],"snippet":"eneration of the request. For violations that are caught before generation in the Responses API, we will charge a $0.05 usage guideline violation fee per request. Billing and Availability Your model access might vary depending on various factors such as geographical location, account limitations, etc. For how the..."}],"deterministic_errors":[{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["idempotency","errors"],"snippet":"rtant when you're processing hundreds or thousands of items. If you don't provide an ID, we generate a UUID for you. Using your own IDs is useful for idempotency (ensuring a request is only processed once) and for linking batch requests to records in your own system. ```bash curl -X POST https://api.x.ai/v1/batches/..."}],"auditability":[{"source_url":"https://docs.x.ai/developers/pricing.md","matched_terms":["history"],"snippet":"query complexity. Token Costs All standard token types are billed for the model used in the request: * **Input tokens**: Your query and conversation history * **Reasoning tokens**: Agent's internal thinking and planning * **Completion tokens**: The final response * **Image tokens**: Visual content analysis (when..."},{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["logs"],"snippet":"**Processing large datasets** - Analyze customer feedback, classify support tickets, extract entities * **Content moderation at scale** - Review backlogs of user-generated content * **Document summarization** - Process reports, research papers, or legal documents in bulk * **Data enrichment pipelines** - Add..."}],"agent_observability":[{"source_url":"https://docs.x.ai/developers/pricing.md","matched_terms":["usage"],"snippet":"ools Pricing Requests which make use of SpaceXSI provided [server-side tools](/developers/tools/overview) are priced based on two components: **token usage** and **server-side tool invocations**. Since the agent autonomously decides how many tools to call, costs scale with query complexity. Token Costs All standard..."},{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["usage","dashboard"],"snippet":"Advanced API Usage # Batch API The Batch API lets you process large volumes of requests asynchronously with reduced pricing and higher rate limits. For pricing details, see [Batch API Pric"}]},"category_review_notes":{"mcp_support":"MCP keywords alone do not prove an operational API integration. Reviewed pages document a search/lookup MCP server or lack a concrete MCP API-operation claim.","budget_controls":"No affirmative agent/API-key spending cap in reviewed pages; keyword matches such as pagination 'limit' or 'spend' warnings do not establish budget controls.","agent_rate_controls":"No concrete API request rate-control evidence in reviewed pages; GPU scheduling 'quota' and pagination 'limits' are out of scope."},"claim_limitations":[],"scoring_signals":{"docs_fetched":true,"pages_fetched":6,"candidate_pages":6,"fetched_urls":["https://docs.x.ai/developers/quickstart.md","https://docs.x.ai/developers/pricing.md","https://docs.x.ai/developers/advanced-api-usage/batch-api.md","https://docs.x.ai/developers/rest-api-reference/inference/batches.md","https://docs.x.ai/developers/advanced-api-usage/priority-processing.md","https://docs.x.ai/developers/model-capabilities/text/structured-outputs.md"],"scoring_source":"YoofoozBot bounded crawl"},"methodology":{"separate_from_agent_readiness":true,"category_count":10,"category_scale":[0,5,10],"max_score":100,"evidence_required_for_public_claims":true}},"category_scores":{"documentation_clarity":10,"machine_readable_spec":10,"authentication_clarity":5,"error_handling":10,"rate_limit_clarity":10,"agent_safe_workflow_support":10,"sandbox_availability":0,"webhook_event_support":0,"commercial_trust":0,"developer_experience":10},"strengths":["Documentation clarity","Machine-readable specification (OpenAPI/GraphQL/etc.)","Error handling and status codes","Rate-limit / quota behavior","Agent-safe workflow primitives (idempotency, retries)","Developer experience (SDKs, quickstart, CLI)"],"risks":["Authentication model clarity signal is partial; clearer documentation recommended.","Sandbox / test-mode availability signal not detected in docs.","Webhook / event support signal not detected in docs.","Commercial trust (status, SLA, compliance) signal not detected in docs."],"recommended_next_steps":["Strengthen: Document authentication clearly (API keys, OAuth scopes, bearer tokens, secret/publishable key handling).","Provide a sandbox / test mode with test API keys for safe agent testing.","Expose webhook/event docs including event types, signature verification, and retry delivery.","Publish status page, SLA, and security/compliance posture (SOC 2, GDPR, PCI as applicable)."],"scoring_signals":{"docs_fetched":true,"docs_chars_used":75917,"pages_fetched":6,"candidate_pages":6,"fetched_urls":["https://docs.x.ai/developers/quickstart.md","https://docs.x.ai/developers/pricing.md","https://docs.x.ai/developers/advanced-api-usage/batch-api.md","https://docs.x.ai/developers/rest-api-reference/inference/batches.md","https://docs.x.ai/developers/advanced-api-usage/priority-processing.md","https://docs.x.ai/developers/model-capabilities/text/structured-outputs.md"],"scoring_source":"yoofoozbot_crawl_documents"},"matched_signals":{"documentation_clarity":{"score":10,"matched_terms":["quickstart","parameters","request","response","docs","guide","reference","overview"]},"machine_readable_spec":{"score":10,"matched_terms":["json schema","endpoints","schema"]},"authentication_clarity":{"score":5,"matched_terms":["authorization","api key","keys"]},"error_handling":{"score":10,"matched_terms":["idempotency","400","500","errors"]},"rate_limit_clarity":{"score":10,"matched_terms":["rate limit","rate limits","limits"]},"agent_safe_workflow_support":{"score":10,"matched_terms":["idempotency","test mode"]},"sandbox_availability":{"score":0,"matched_terms":[]},"webhook_event_support":{"score":0,"matched_terms":["events"]},"commercial_trust":{"score":0,"matched_terms":["support"]},"developer_experience":{"score":10,"matched_terms":["quickstart","sdk","cli","dashboard"]}},"evidence_signals":{"documentation_clarity":[{"source_url":"https://docs.x.ai/developers/quickstart.md","matched_terms":["quickstart","request","response","docs","guide","overview"],"snippet":"quickstart # quickstart welcome! in this guide, we'll walk you through the basics of using the spacexsi api, from creating an account to making your first..."},{"source_url":"https://docs.x.ai/developers/model-capabilities/text/structured-outputs.md","matched_terms":["parameters","request","response","reference","overview"],"snippet":"...and report generation. > [!tip] > > when using supported schema features, the response is guaranteed to match your schema. there are two ways to request structured outputs from the model. the primary and most flexible method is to use the `response_format` parameter. by setting `response_format.type`..."}],"machine_readable_spec":[{"source_url":"https://docs.x.ai/developers/model-capabilities/text/structured-outputs.md","matched_terms":["json schema","schema"],"snippet":"...is through tool calling. when you define tools, spacexsi models will always generate tool call arguments that strictly conform to the tool’s input json schema (the `strict` flag is implicitly always `true`). > [!note] > > tool schemas follow the same json schema support rules described on this page. see..."},{"source_url":"https://docs.x.ai/developers/pricing.md","matched_terms":["endpoints"],"snippet":"...is served at the default tier instead, standard rates apply. > [!note] > > priority processing is available for chat completions and responses endpoints only. it is not supported for image generation, video generation, or [batch api](/developers/advanced-api-usage/batch-api) requests. see [priority..."}],"authentication_clarity":[{"source_url":"https://docs.x.ai/developers/quickstart.md","matched_terms":["authorization","api key","keys"],"snippet":"...this function and explain the bug: function median(a) \", ) print(response.output_text) ``` ```bash curl https://api.x.ai/v1/responses \\ -h \"authorization: bearer $xai_api_key\" \\ -h \"content-type: application/json\" \\ -d ' ' ``` ```javascript customlanguage=\"javascriptopenaisdk\" import openai from..."},{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["authorization"],"snippet":"...that you'll use to add requests and retrieve results. ```bash curl -x post https://api.x.ai/v1/batches \\\\ -h \"content-type: application/json\" \\\\ -h \"authorization: bearer $xai_api_key\" \\\\ -d ' ' ``` ```javascriptwithoutsdk // create a batch with a descriptive name const response = await..."}],"error_handling":[{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["idempotency","500","errors"],"snippet":"...when you're processing hundreds or thousands of items. if you don't provide an id, we generate a uuid for you. using your own ids is useful for idempotency (ensuring a request is only processed once) and for linking batch requests to records in your own system. ```bash curl -x post..."},{"source_url":"https://docs.x.ai/developers/model-capabilities/text/structured-outputs.md","matched_terms":["400"],"snippet":"...values not listed under [string formats](#string-formats) * constraints exceeding the limits above rejected schemas the following will return a `400` error: * `enum` or `anyof` with zero variants * properties with a schema of `true` or `false` * `maxcontains` / `mincontains` * `items` as an array..."}],"rate_limit_clarity":[{"source_url":"https://docs.x.ai/developers/pricing.md","matched_terms":["rate limit","rate limits","limits"],"snippet":"...| token pricing | standard rates | discounted rates (varies by model) | | response time | immediate (seconds) | typically within 24 hours | | rate limits | per-minute limits apply | requests don't count towards rate limits | the batch discount applies to all token types — input tokens, output tokens,..."},{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["rate limit","rate limits","limits"],"snippet":"advanced api usage # batch api the batch api lets you process large volumes of requests asynchronously with reduced pricing and higher rate limits. for pricing details, see [batch api pricing](/developers/pricing#batch-api-pricing). if you need lower latency on real-time requests instead, see..."}],"agent_safe_workflow_support":[{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["idempotency","test mode"],"snippet":"...when you're processing hundreds or thousands of items. if you don't provide an id, we generate a uuid for you. using your own ids is useful for idempotency (ensuring a request is only processed once) and for linking batch requests to records in your own system. ```bash curl -x post..."}],"commercial_trust":[{"source_url":"https://docs.x.ai/developers/pricing.md","matched_terms":["support"],"snippet":"...servers | token-based | † all tool names work in the responses api. in the grpc api (python xai sdk), `code_interpreter` and `file_search` are not supported. \\* only applies to images and videos found by search tools — not to images passed directly in messages. x search is billed per item fetched..."},{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["support"],"snippet":"...need lower latency on real-time requests instead, see [priority processing](/developers/advanced-api-usage/priority-processing). > [!note] > model support > > not every model accepts batch api requests. see details on each [model page](/developers/models). unsupported models reject batch requests. what..."}],"developer_experience":[{"source_url":"https://docs.x.ai/developers/quickstart.md","matched_terms":["quickstart","sdk","cli"],"snippet":"quickstart # quickstart welcome! in this guide, we'll walk you through the basics of using the spacexsi api, from creating an account to making your first..."},{"source_url":"https://docs.x.ai/developers/advanced-api-usage/batch-api.md","matched_terms":["sdk","cli","dashboard"],"snippet":"...post https://api.x.ai/v1/batches \\\\ -h \"content-type: application/json\" \\\\ -h \"authorization: bearer $xai_api_key\" \\\\ -d ' ' ``` ```javascriptwithoutsdk // create a batch with a descriptive name const response = await fetch(\"https://api.x.ai/v1/batches\", ); const batch = await response.json();..."}]},"evidence_quality":{"raw_pages_fetched":6,"scoring_pages":6,"index_pages_excluded":[],"protocol_responses_excluded":[],"html_navigation_trimmed":[],"security_quarantined_pages_excluded":[],"security_quarantine_requires_review":false,"scoring_coverage_incomplete":false,"index_pages_are_discovery_only":true,"source_crawl_unchanged":true,"runtime_capabilities_not_tested":true,"no_trusted_documentation":false,"robots_access_deferred":false},"assessment_status":"documentation_only_preliminary","publication_eligible":true,"score_qualification":"Preliminary documentation-only scores; runtime not verified.","documentation_only":true,"runtime_capabilities_verified":false,"yoofoozbot":{"run_id":"20261025T220049Z_xai_600e64c1","user_agent":"YoofoozBot/1.12 (+https://yoofooz.com/yoofoozbot; contact: submit@yoofooz.com)","pages_fetched":6,"total_bytes":116356,"robots_respected":true,"crawl_record_path":"outputs/yoofoozbot/20261025T220049Z_xai_600e64c1.json","spec_candidates":[],"official_sibling_openapi_probes":[],"signal_summary":{"openapi":{"detected":true,"matched_terms":["json schema"]},"authentication":{"detected":true,"matched_terms":["api key"]},"errors":{"detected":false,"matched_terms":[]},"rate_limits":{"detected":true,"matched_terms":["rate limit"]},"webhooks":{"detected":false,"matched_terms":[]},"sandbox":{"detected":true,"matched_terms":["sandbox","test mode"]},"agent_workflows":{"detected":true,"matched_terms":["mcp","agent","idempotency"]},"developer_experience":{"detected":true,"matched_terms":["sdk","quickstart","cli"]},"commercial_trust":{"detected":true,"matched_terms":["sla"]},"mcp_support":{"detected":true,"matched_terms":["mcp server","mcp tools"]},"machine_payments":{"detected":false,"matched_terms":[]},"machine_pricing":{"detected":true,"matched_terms":["per request"]},"budget_controls":{"detected":false,"matched_terms":[]},"agent_identity":{"detected":false,"matched_terms":[]},"auditability":{"detected":false,"matched_terms":[]},"agent_observability":{"detected":false,"matched_terms":[]}},"readiness_scoring_pages":6,"readiness_scoring_source":"yoofoozbot_crawl_documents","scoring_evidence_quality":{"raw_pages_fetched":6,"scoring_pages":6,"index_pages_excluded":[],"protocol_responses_excluded":[],"html_navigation_trimmed":[],"security_quarantined_pages_excluded":[],"security_quarantine_requires_review":false,"scoring_coverage_incomplete":false,"index_pages_are_discovery_only":true,"source_crawl_unchanged":true,"runtime_capabilities_not_tested":true,"no_trusted_documentation":false,"robots_access_deferred":false},"agent_commerce_probe":{"score":30,"level":"Agent Commerce Emerging","machine_payment_capable":false,"detected_protocols":[],"evidence_categories":["agent_observability","auditability","deterministic_errors","machine_pricing"]}},"ai_analysis":{"provider":"nvidia","enabled":true,"model":"nvidia/nemotron-3.5-super-vl-120b-a12b","summary":"xAI API scores 65/100 and is Agent-Compatible With Gaps, with strong documentation, specs, error handling, rate limits, agent-safe workflows, and developer experience, but lacks sandbox, webhooks, and commercial trust signals.","credibility_notes":["Agent-compatible with a mid-tier readiness score of 65/100.","Core technical foundations like specs and error handling are solid.","Trust and integration signals including SLA, sandbox, and webhooks are missing."],"next_actions":["Document authentication clearly including API keys, OAuth scopes, and bearer token handling.","Provide a sandbox or test mode with test API keys for safe agent testing.","Publish status page, SLA, and security or compliance posture such as SOC 2 and GDPR."],"error":null}}