{"id":102528,"name":"Synap by Linkrra","description":"OpenAI-compatible inference on open-weight models, served on hardware Linkrra owns and operates. Send it a prompt and it answers with a model completion; ask it to list models or to estimate the cost of a job and it answers from the live price list. Zero data retention: prompts and completions are not stored, and a finished task cannot be read back.","card_url":"https://pool.linkrra.com/.well-known/agent-card.json","endpoint":"https://pool.linkrra.com/a2a/v1","protocol_version":"1.0","first_seen":"2026-10-14T11:57:27.730064+00:00","last_verified":"2026-10-14T11:57:27.730064+00:00","card":{"name":"Synap by Linkrra","skills":[{"id":"chat-completion","name":"Chat completion","tags":["llm","inference","chat","code-generation","openai-compatible"],"examples":["Write a Python function that parses an ISO 8601 duration.","Explain the difference between a mutex and a semaphore in two sentences."],"inputModes":["text/plain"],"description":"Answers a prompt with a completion from an open-weight model — prose, analysis or code. Billed per prompt and completion token to the Synap key on the request; with no key it returns a task in TASK_STATE_AUTH_REQUIRED and spends nothing. Name a model by putting its id in metadata.model, or leave it out and Synap routes to the cheapest model that can do the job. Stateless: send the whole conversation in the message, because nothing is remembered between calls.","outputModes":["text/plain"]},{"id":"list-models","name":"List models","tags":["catalogue","models","pricing","discovery"],"examples":["list models","models","list models coder"],"inputModes":["text/plain"],"description":"Returns the models Synap serves right now, with each one's context window, maximum output length and per-million-token price, as JSON text. Read-only, free, and needs no key. Triggered by a message whose text begins with \"list models\" (or is exactly \"models\"); anything after that is used as a filter on the model id and name.","outputModes":["text/plain"]},{"id":"estimate-cost","name":"Estimate cost","tags":["pricing","cost","estimate","budget"],"examples":["estimate cost qwen3-coder-30b 4000 1000","estimate cost gpt-oss-20b 12000"],"inputModes":["text/plain"],"description":"Prices a job before it is run: given a model id and a token count, returns the prompt, completion and total USD from the live price list, as JSON text. Read-only, free, and needs no key. Triggered by a message of the form \"estimate cost <model-id> <prompt-tokens> [<completion-tokens>]\". The real charge uses the token counts the model reports, so this is an estimate, not a quote.","outputModes":["text/plain"]}],"version":"1.0.0","provider":{"url":"https://linkrra.com","organization":"Linkrra"},"description":"OpenAI-compatible inference on open-weight models, served on hardware Linkrra owns and operates. Send it a prompt and it answers with a model completion; ask it to list models or to estimate the cost of a job and it answers from the live price list. Zero data retention: prompts and completions are not stored, and a finished task cannot be read back.","capabilities":{"streaming":false,"extendedAgentCard":false,"pushNotifications":false},"securitySchemes":{"bearer":{"httpAuthSecurityScheme":{"scheme":"Bearer","description":"A Synap API key, as \"Authorization: Bearer sk-pool-…\". Required for the chat-completion skill, which is billed per token. list-models and estimate-cost need no key. Keys are issued at https://synap.linkrra.com."}}},"documentationUrl":"https://synap.linkrra.com/docs","defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"supportedInterfaces":[{"url":"https://pool.linkrra.com/a2a/v1","protocolBinding":"HTTP+JSON","protocolVersion":"1.0"}],"securityRequirements":[{"schemes":{"bearer":{"list":[]}}}]},"signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-14T11:57:27.730064+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Global A2A Registry","source_url":"https://api.a2a-registry.org/public/agents","last_check":{"checked_at":"2026-10-14T11:57:27.730064+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://pool.linkrra.com/.well-known/agent-card.json"],"also_observed_in":[{"source_name":"A2A Registry","source_url":"https://a2aregistry.org/api/agents","last_seen":"2026-10-14T11:55:21.238732+00:00"},{"source_name":"Global A2A Registry","source_url":"https://api.a2a-registry.org/public/agents","last_seen":"2026-10-14T11:55:21.238732+00:00"}],"skills":[{"skill_id":"chat-completion","name":"Chat completion","description":"Answers a prompt with a completion from an open-weight model — prose, analysis or code. Billed per prompt and completion token to the Synap key on the request; with no key it returns a task in TASK_STATE_AUTH_REQUIRED and spends nothing. Name a model by putting its id in metadata.model, or leave it out and Synap routes to the cheapest model that can do the job. Stateless: send the whole conversation in the message, because nothing is remembered between calls.","tags":["llm","inference","chat","code-generation","openai-compatible"],"quality_warning":false},{"skill_id":"estimate-cost","name":"Estimate cost","description":"Prices a job before it is run: given a model id and a token count, returns the prompt, completion and total USD from the live price list, as JSON text. Read-only, free, and needs no key. Triggered by a message of the form \"estimate cost <model-id> <prompt-tokens> [<completion-tokens>]\". The real charge uses the token counts the model reports, so this is an estimate, not a quote.","tags":["pricing","cost","estimate","budget"],"quality_warning":false},{"skill_id":"list-models","name":"List models","description":"Returns the models Synap serves right now, with each one's context window, maximum output length and per-million-token price, as JSON text. Read-only, free, and needs no key. Triggered by a message whose text begins with \"list models\" (or is exactly \"models\"); anything after that is used as a filter on the model id and name.","tags":["catalogue","models","pricing","discovery"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://pool.linkrra.com/.well-known/agent-card.json","checked_at":"2026-10-14T11:57:27.730064+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":null,"protocol_check":{"checked_at":"2026-10-14T11:57:27.730064+00:00","state":"unconfirmed","http_status":404,"detail":"Endpoint returned a generic not-found response"},"x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://pool.linkrra.com/.well-known/agent-card.json","last_successful_card_check":"2026-10-14T11:57:27.730064+00:00","latest_card_check":{"checked_at":"2026-10-14T11:57:27.730064+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-14T11:57:27.730064+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":null,"endpoint_tls_reachable":null,"protocol_check_state":"unconfirmed","protocol_checked_at":"2026-10-14T11:57:27.730064+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null}}