{"type":"post","id":"ember-1-is-on-ai-gateway-analysis-577d5d","slug":"ember-1-is-on-ai-gateway-analysis-577d5d","title":"Ember-1 is on AI Gateway.","description":"Ember-1’s arrival on Vercel AI Gateway turns a model-efficiency claim into an operational choice for teams running coding agents.","retrieval_nugget":"Ember-1’s arrival on Vercel AI Gateway turns a model-efficiency claim into an operational choice for teams running coding agents.","published_at":"2026-09-28","updated_at":"2026-09-28","record_date":"2026-09-28","date_kind":"published_at","topics":["coding-agents"],"source_urls":["https://vercel.com/changelog/ember-1-from-fireworks-now-available-on-ai-gateway"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:ember-1-is-on-ai-gateway-analysis-577d5d","status":"published","visuals":[],"editorial_provenance":{"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:287c53246c5a949fef9d2077edce7803b6198f9f49e545db699a86d6aa22118e","reviewed_at":"2026-09-28T05:00:50.691Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":2,"related_record_count":0},"analysis":{"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Ember-1’s arrival on Vercel AI Gateway turns a model-efficiency claim into an operational choice for teams running coding agents.","observed_facts":[{"text":"Vercel says Ember-1 from Fireworks is available on AI Gateway under the identifier `fireworks/ember-1` as an initial two-week research preview.","source_urls":["https://vercel.com/changelog/ember-1-from-fireworks-now-available-on-ai-gateway"]},{"text":"Vercel states that Ember-1 supports a 1M-token context window, text and image input, tool calling, and implicit prompt caching.","source_urls":["https://vercel.com/changelog/ember-1-from-fireworks-now-available-on-ai-gateway"]},{"text":"Fireworks reports approximately 40% fewer generated tokens than Kimi K3 at comparable quality across its evaluations.","source_urls":["https://vercel.com/changelog/ember-1-from-fireworks-now-available-on-ai-gateway"]}],"mechanism":"The mechanism is that lower token generation can reduce both output spend and the reasoning trace that a repeatedly calling agent carries into later steps.","why_now":"Why now is that the model is newly accessible through Vercel’s gateway, while the initial preview window makes the decision time-sensitive for evaluators.","implications":["For agent builders, the first implication is that a long-context, tool-capable coding model can be trialed alongside existing gateway-routed models without creating a separate provider integration.","Claimed token efficiency matters most where workflows make many sequential calls, rather than in a single isolated prompt."],"evidence_boundary":"The evidence boundary is that the 40% token reduction and comparable-quality claim comes from Fireworks’ own evaluations, and the announcement does not provide the underlying benchmark tasks, pricing, latency figures, or independent replication.","watch_conditions":["The first watch condition is whether Vercel or Fireworks publishes pricing, rate limits, benchmark methodology, and production-availability terms after the two-week preview.","Whether real coding-agent evaluations preserve quality while reducing total workflow cost, rather than merely reducing tokens in a narrow test."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied with enough content to establish a continuing analytical thread; this availability event starts its own record."},"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/ember-1-is-on-ai-gateway-analysis-577d5d/","markdown":"https://newruntime.com/posts/ember-1-is-on-ai-gateway-analysis-577d5d.md","json":"https://newruntime.com/posts/ember-1-is-on-ai-gateway-analysis-577d5d.json"},"next_reads":[{"type":"topic","path":"/topics/coding-agents/","url":"https://newruntime.com/topics/coding-agents/","title":"Coding Agents","reason":"Explore the coding-agents topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/coding-agents.md","json_url":"https://newruntime.com/topics/coding-agents.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}