LLM gateway
OpenAI-compatible pay-per-call inference over x402 - flat quality tiers and a metered tier, plus embeddings and image generation, model-optional auto-routing, streaming, and a default-on prompt cache. See /v1 in the OpenAPI spec for the full wire format.
Chat completions - metered (pay what the call costs)
POST /v1/metered/chat/completionsOpenAI-compatible chat completions priced per request from the request itself.
try in playground →Chat completions - nano tier
POST /v1/nano/chat/completionsOpenAI-compatible chat completions, nano tier: gpt-6-luna (the default), gpt-5.6-luna, gpt-5-nano, gemini flash-lite.
try in playground →Chat completions - auto tier (eval-ranked routing)
POST /v1/auto/chat/completionsOpenAI-compatible chat completions with server-side model choice: omit "model" (or send "auto") and the gateway routes.
try in playground →Grounded chat (web search, OpenAI-compatible)
POST /v1/grounded/chat/completionsOpenAI-compatible chat completions GROUNDED in a live web search on every call: the gateway runs a live web search (up.
try in playground →Chat completions (OpenAI-compatible)
POST /v1/chat/completionsOpenAI-compatible chat completions, base tier: point any OpenAI SDK at base_url https://agent402.tools/v1 and pay per.
try in playground →Chat completions - pro tier
POST /v1/pro/chat/completionsOpenAI-compatible chat completions, pro tier: gpt-4o, gpt-4.1, gpt-6 sol, claude sonnet, gemini pro, grok - paid per.
try in playground →Chat completions - premium tier
POST /v1/premium/chat/completionsOpenAI-compatible chat completions, premium tier: gpt-5, gpt-6 astra, o3, claude opus, claude fable 5.1 - paid per call.
try in playground →Embeddings (OpenAI-compatible)
POST /v1/embeddingsOpenAI-compatible text embeddings over x402 - point any OpenAI SDK at base_url https://agent402.tools/v1 and pay $0.002.
try in playground →Rerank (Cohere-compatible)
POST /v1/rerankRerank documents against a query over x402 - the Cohere /rerank wire ({query, documents[], top_n} -> results.
try in playground →Image generation (OpenAI-compatible)
POST /v1/images/generationsOpenAI-compatible image generation over x402 - point any OpenAI SDK's images.generate() at base_url.
try in playground →Text-to-speech (OpenAI-compatible)
POST /v1/audio/speechOpenAI-compatible text-to-speech over x402 - point any OpenAI SDK's audio.speech.create() at base_url.
try in playground →Messages nano (Anthropic-compatible)
POST /v1/nano/messagesAnthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url.
try in playground →Messages auto (Anthropic-compatible)
POST /v1/auto/messagesAnthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url.
try in playground →Messages base (Anthropic-compatible)
POST /v1/messagesAnthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url.
try in playground →Messages pro (Anthropic-compatible)
POST /v1/pro/messagesAnthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url.
try in playground →Messages premium (Anthropic-compatible)
POST /v1/premium/messagesAnthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url.
try in playground →Messages metered (Anthropic-compatible)
POST /v1/metered/messagesAnthropic Messages API priced per request from the request itself.
try in playground →Gemini generateContent (nano tier)
POST /v1/nano/geminiGoogle's native generateContent wire on the nano tier.
try in playground →Gemini generateContent (auto tier)
POST /v1/auto/geminiGoogle's native generateContent wire on the auto tier.
try in playground →Gemini generateContent (base tier)
POST /v1/geminiGoogle's native generateContent wire on the base tier.
try in playground →Gemini generateContent (pro tier)
POST /v1/pro/geminiGoogle's native generateContent wire on the pro tier.
try in playground →Gemini generateContent (premium tier)
POST /v1/premium/geminiGoogle's native generateContent wire on the premium tier.
try in playground →Gemini generateContent (metered tier)
POST /v1/metered/geminiGoogle's native generateContent wire on the metered tier.
try in playground →Responses nano (OpenAI Responses API)
POST /v1/nano/responsesOpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url.
try in playground →Responses auto (OpenAI Responses API)
POST /v1/auto/responsesOpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url.
try in playground →Responses base (OpenAI Responses API)
POST /v1/responsesOpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url.
try in playground →Responses pro (OpenAI Responses API)
POST /v1/pro/responsesOpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url.
try in playground →Responses premium (OpenAI Responses API)
POST /v1/premium/responsesOpenAI Responses API over x402 - point the OpenAI SDK's responses.create() (or the OpenAI Agents SDK) at base_url.
try in playground →Responses metered (OpenAI Responses API)
POST /v1/metered/responsesOpenAI Responses API priced per request from the request itself.
try in playground →Deep research report (grounded, cited)
POST /v1/researchHand over a whole research question and get one cited report back.
try in playground →Deep research report - PRO (premium synthesis)
POST /v1/research/proThe deeper research tier: more sub-questions, more grounded searches, wider reranked source set, and a premium (Claude.
try in playground →Deep research report - MAX (exhaustive)
POST /v1/research/maxThe exhaustive tier: up to a dozen sub-questions and grounded searches, the widest reranked source set, premium.
try in playground →Market / competitor brief (grounded)
POST /v1/research/market-briefName a market, category or company and get one cited MARKET / COMPETITOR BRIEF: how the market is defined and sized.
try in playground →Company due-diligence dossier (grounded, cited)
POST /v1/dossierHand over a ticker and get one due-diligence dossier back.
try in playground →Company due-diligence dossier - MAX (exhaustive)
POST /v1/dossier/maxThe exhaustive due-diligence tier: more filings, a full year of Form 4 insider activity, wider web research (up to 8.
try in playground →Fund portfolio report (13F, grounded)
POST /v1/fundHand over an institutional manager (a fund name like "Berkshire Hathaway", a ticker, or a SEC CIK) and get one cited.
try in playground →Fund portfolio report - MAX (deep)
POST /v1/fund/maxThe deep tier: the full holdings table, wider quarter-over-quarter change analysis, more grounded web research.
try in playground →Domain security & deliverability audit (graded)
POST /v1/domain-auditHand over a domain and get one graded security & email-deliverability audit: SPF, DMARC, DKIM and MX (why your mail.
try in playground →Domain security audit - PRO (attack surface + stack)
POST /v1/domain-audit/proThe deeper tier: everything in the standard audit plus the attack surface from Certificate Transparency logs.
try in playground →FDA recall report (drug, food, device)
POST /v1/recall-reportName a drug, food, ingredient, brand or medical device and get one cited FDA recall report: every matching enforcement.
try in playground →Insider flow report (Form 4 transactions)
POST /v1/insider-reportName a US ticker and get one cited insider-flow report: every Form 4 against the company in the window with the actual.
try in playground →Token & contract risk report (on-chain evidence)
POST /v1/token-riskHand over a token contract address (and chain) and get one evidence-based on-chain risk report: whether the source is.
try in playground →Token & contract risk report - PRO (static scan + reputation)
POST /v1/token-risk/proThe deeper tier: everything in the standard report plus a deterministic static-pattern scan of the verified source.
try in playground →Fast image generation (OpenAI-compatible, budget)
POST /v1/images/fastBudget text-to-image over x402 - OpenAI images wire (prompt in, inline base64 out) at $0.02 per picture, a quarter.
try in playground →Pro image generation (OpenAI-compatible)
POST /v1/images/proHigher-fidelity text-to-image over x402 - OpenAI images wire (prompt in, inline base64 out) at $0.05 per picture.
try in playground →Image edit (OpenAI-compatible)
POST /v1/images/editsEdit an image with a prompt over x402 - OpenAI images.edit wire (reference images and a prompt in, inline base64 out).
try in playground →Video generation (4-second clip)
POST /v1/videos/generationsText-to-video over x402 - one silent 4-second 720p clip (MP4, inline base64) for a flat $0.20, served by Veo 3.1 Lite.
try in playground →Solana token due-diligence brief
POST /v1/token-briefHand over a Solana SPL mint address and get one cited due-diligence brief: what the token is, whether the mint.
try in playground →Ticker pack: dossier, insider flow and institutional holders
POST /v1/ticker-packOne ticker, one purchase, the full picture.
try in playground →SEC filing report (what the company just filed)
POST /v1/filing-reportName a US ticker and get one cited report on what the company just filed with the SEC: every filing in EDGAR's index.
try in playground →LinkedIn article, ready to publish (research + copy + sized images)
POST /v1/linkedin-articleHand over a topic and get a publish-ready LinkedIn article back: grounded web research with cited sources, three.
try in playground →