{"id":"sid-2-swarm","slug":"sid-2-swarm","name":"SID-2 Swarm","orgId":"sid-ai","family":"sid-2-swarm","releaseDate":null,"availability":"ga","openWeights":false,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://www.sid.ai/research/sid-2-technical-report","hfRepo":null,"modalities":["text"],"aliases":["SID-2 Swarm","sid-2-swarm","SID-2-Swarm","SID 2 Swarm"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-18","announced":"2026-11-07","blurb":"SID AI's multi-agent search model, kept separate from SID-2. Official docs: a root agent forks into a team that searches in parallel, messages other agents, and reports ranked document IDs, on the first-party SID API over a WebSocket (model SID-2-Swarm). Official models page: reasoning is fixed at high, context is described as effectively infinite, and list pricing is $0.50 input, $0.05 cached input, and $2.00 output per 1M tokens. Official technical report dated November 7, 2026, describes SID-2 Swarm as trained as a team of agents. Not an LLM for general chat.","api":"live","apiModelId":"SID-2-Swarm","openWeights":"no","facts":[{"label":"Task","value":"Multi-agent agentic search: a team of agents returns document IDs in relevance order that the caller can fuse, for example with RRF (official Swarm docs)"},{"label":"Context","value":"Official models page: effectively infinite. Official Swarm docs: each agent can have its own context after a fork"},{"label":"Reasoning","value":"Fixed at high; official request docs say any other effort value is refused"},{"label":"Agents","value":"Official request docs: multi_agent.max_agents from 1 to 24, default 6, and not more than the account's agent quota (12 by default)"},{"label":"Availability","value":"Public first-party SID API at wss://api.sid-1.com/v1/responses, model SID-2-Swarm, with the same self-serve SID API key as SID-2 (official Swarm docs). Official overview says it is currently only available via SID's first-party API"},{"label":"Price","value":"$0.50 input, $0.05 cached input, and $2.00 output per 1M tokens (official SID models page)"},{"label":"Related","value":"A separately trained multi-agent model related to SID-2, not only a SID-2 mode (official technical report and models page)"},{"label":"Weights","value":"Not released"}],"claims":["Lab claim: on SID's self-reported 506-question benchmark across 19 corpora, SID-2 Swarm with 12 agents scored 0.720 NDCG, and with 6 agents scored 0.701 NDCG with an estimated 17.7 seconds of model inference per query (official technical report, Tables 2 and 4). The same official tables list GPT-6 Astra at maximum effort at 0.704 NDCG and 135 seconds."],"sources":[{"kind":"lab","title":"SID-2 Technical Report: Scaling Search Swarms","url":"https://www.sid.ai/research/sid-2-technical-report","date":"2026-11-07"},{"kind":"lab","title":"SID models: SID-2, SID-2 Swarm and SID-1","url":"https://www.sid.ai/models"},{"kind":"lab","title":"SID-2 Swarm overview (official docs)","url":"https://platform.sid.ai/docs/sid-2-swarm"},{"kind":"lab","title":"SID-2 Swarm making a request (official docs)","url":"https://platform.sid.ai/docs/sid-2-swarm/making-a-request"}],"firstBenchmark":null},"organization":{"id":"sid-ai","name":"SID AI","slug":"sid-ai","country":null,"url":"https://www.sid.ai","color":"#11110F","mark":"S"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Nov 7, 2026; no independent results yet.","lead":"As of Nov 22, 2026, SID-2 Swarm is pending benchmarks on isitsota: announced Nov 7, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}