{
 "_comment": "Two model tiers. standard: the models a buyer meets on a free plan, twelve from twelve labs; the public index runs on them from the October 2026 reset. expanded: the flagship set the September 2026 Edition ran on; it runs per category for subscribers. Version strings were verified against each lab live model list on 2026-09-08 (expanded) and 2026-09-14 (free, direct models); gateway model ids and hosts were confirmed by a smoke through the gateway on 2026-09-14. A change to any string is a new Models row and triggers noise floor recalibration for that model. transport direct calls the lab; transport gateway calls Vercel AI Gateway with the provider pinned and the gateway search tool, because those labs offer no search tool of their own.",
 "judge": {
  "model": "claude-opus-5",
  "note": "It runs with reasoning effort set to low and a fixed output schema, so the same answer text produces the same labels every time.",
  "input_price_per_m": 5,
  "output_price_per_m": 25,
  "cost_per_answer_measured": 0.027,
  "cost_note": "Measured over the September 2026 Edition: about 2.7 cents an answer at low effort, 3,200 input and 500 output tokens on average, whatever model wrote the answer. Re-judged on 2026-09-14 against Sonnet 5 (72% first-choice set agreement) and Haiku 4.5 (65%) with Opus 5 reproducing itself at 93%: the judge stays Opus 5."
 },
 "models": [
  {
   "model_key": "anthropic-current",
   "lab": "anthropic",
   "model": "claude-opus-5",
   "generation": "current",
   "endpoint": "https://api.anthropic.com/v1/messages",
   "search": "web_search_20260209",
   "input_price_per_m": 5,
   "output_price_per_m": 25,
   "search_price_per_call": 0.01,
   "tier": "expanded",
   "transport": "direct"
  },
  {
   "model_key": "anthropic-prior",
   "lab": "anthropic",
   "model": "claude-opus-4-8",
   "generation": "prior",
   "endpoint": "https://api.anthropic.com/v1/messages",
   "search": "web_search_20260209",
   "input_price_per_m": 5,
   "output_price_per_m": 25,
   "search_price_per_call": 0.01,
   "tier": "expanded",
   "transport": "direct"
  },
  {
   "model_key": "openai-current",
   "lab": "openai",
   "model": "gpt-6-astra",
   "generation": "current",
   "endpoint": "https://api.openai.com/v1/responses",
   "search": "web_search",
   "input_price_per_m": 10,
   "output_price_per_m": 50,
   "search_price_per_call": 0.01,
   "tier": "expanded",
   "transport": "direct"
  },
  {
   "model_key": "openai-prior",
   "lab": "openai",
   "model": "gpt-5.6-sol",
   "generation": "prior",
   "endpoint": "https://api.openai.com/v1/responses",
   "search": "web_search",
   "input_price_per_m": 4,
   "output_price_per_m": 20,
   "search_price_per_call": 0.01,
   "tier": "expanded",
   "transport": "direct"
  },
  {
   "model_key": "google-single",
   "lab": "google",
   "model": "gemini-3.1-pro-preview",
   "generation": "single",
   "endpoint": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.1-pro-preview:generateContent",
   "search": "google_search",
   "input_price_per_m": 2,
   "output_price_per_m": 12,
   "search_price_per_call": 0.014,
   "note": "Switched from gemini-3.8-flash on 2026-09-08: Flash never invoked Google Search in testing, Pro grounds. Preview build.",
   "tier": "expanded",
   "transport": "direct"
  },
  {
   "model_key": "challenger-single",
   "lab": "challenger",
   "model": "sonar-pro",
   "generation": "single",
   "endpoint": "https://api.perplexity.ai/chat/completions",
   "search": "native",
   "input_price_per_m": 3,
   "output_price_per_m": 15,
   "search_price_per_call": 0.01,
   "tier": "expanded",
   "transport": "direct"
  },
  {
   "model_key": "anthropic-small",
   "lab": "anthropic",
   "model": "claude-haiku-4-5",
   "generation": "small",
   "tier": "standard",
   "transport": "direct",
   "endpoint": "https://api.anthropic.com/v1/messages",
   "search": "web_search_20250305",
   "input_price_per_m": 1,
   "output_price_per_m": 5,
   "search_price_per_call": 0.01,
   "note": "Haiku 4.5 takes the 20250305 web search tool; the 20260209 tool needs programmatic tool calling it does not support.",
   "smoke_cost_per_pair": 0.024
  },
  {
   "model_key": "openai-small",
   "lab": "openai",
   "model": "gpt-5.4-mini",
   "generation": "small",
   "tier": "standard",
   "transport": "direct",
   "endpoint": "https://api.openai.com/v1/responses",
   "search": "web_search",
   "input_price_per_m": 0.25,
   "output_price_per_m": 2,
   "search_price_per_call": 0.01,
   "smoke_cost_per_pair": 0.013
  },
  {
   "model_key": "google-small",
   "lab": "google",
   "model": "gemini-3.5-flash",
   "generation": "small",
   "tier": "standard",
   "transport": "direct",
   "endpoint": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:generateContent",
   "search": "google_search",
   "input_price_per_m": 0.3,
   "output_price_per_m": 2.5,
   "search_price_per_call": 0.014,
   "note": "Chosen 2026-09-14: 3.6, 3.7 and 3.8 Flash answered without invoking Google Search in testing; 3.5 Flash and 3.1 Flash-Lite ground on every prompt tried.",
   "smoke_cost_per_pair": 0.023
  },
  {
   "model_key": "challenger-small",
   "lab": "challenger",
   "model": "sonar",
   "generation": "small",
   "tier": "standard",
   "transport": "direct",
   "endpoint": "https://api.perplexity.ai/chat/completions",
   "search": "native",
   "input_price_per_m": 1,
   "output_price_per_m": 1,
   "search_price_per_call": 0.005,
   "smoke_cost_per_pair": 0.005
  },
  {
   "model_key": "xai-small",
   "lab": "xai",
   "provider": "vertex",
   "model": "spacexai/grok-4.1-fast-non-reasoning",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.2,
   "output_price_per_m": 0.5,
   "search_price_per_call": 0.005,
   "note": "xAI does not serve Grok through the gateway itself; Vertex AI is the only host offered. Smoke 2026-09-14 after top-up: searched, served by vertex, about $0.038 a pair (two searches, long context); the dearest of the free set.",
   "smoke_cost_per_pair": 0.038
  },
  {
   "model_key": "mistral-small",
   "lab": "mistral",
   "provider": "mistral",
   "model": "mistral/mistral-small",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.1,
   "output_price_per_m": 0.3,
   "search_price_per_call": 0.005,
   "note": "Smoke 2026-09-14: searched, served by mistral, about $0.016 a pair (three searches).",
   "smoke_cost_per_pair": 0.016
  },
  {
   "model_key": "deepseek-small",
   "lab": "deepseek",
   "provider": [
    "fireworks",
    "deepinfra",
    "baseten"
   ],
   "model": "deepseek/deepseek-v4-flash",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.06,
   "output_price_per_m": 0.18,
   "search_price_per_call": 0.005,
   "note": "DeepSeek does not serve its own model through the gateway. Fireworks is the first host; DeepInfra and Baseten follow only when Fireworks reports no capacity, and the host that answered is recorded on every row. Smoke 2026-09-14 after top-up: searched, served by fireworks, about $0.011 a pair.",
   "smoke_cost_per_pair": 0.011
  },
  {
   "model_key": "meta-small",
   "lab": "meta",
   "provider": "bedrock",
   "model": "meta/llama-4-maverick",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.5,
   "output_price_per_m": 1.5,
   "search_price_per_call": 0.005,
   "note": "Meta does not serve Llama itself; Amazon Bedrock is the pinned host. Smoke 2026-09-14: searched, served by bedrock, about $0.011 a pair.",
   "smoke_cost_per_pair": 0.011
  },
  {
   "model_key": "alibaba-small",
   "lab": "alibaba",
   "provider": "alibaba",
   "model": "alibaba/qwen3.7-flash",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.03,
   "output_price_per_m": 0.13,
   "search_price_per_call": 0.005,
   "note": "Smoke 2026-09-14: searched, served by alibaba, about $0.005 a pair.",
   "smoke_cost_per_pair": 0.005
  },
  {
   "model_key": "moonshot-small",
   "lab": "moonshotai",
   "provider": "novita",
   "model": "moonshotai/kimi-k2",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.57,
   "output_price_per_m": 2.3,
   "search_price_per_call": 0.005,
   "note": "Moonshot does not serve Kimi through the gateway itself; Novita is the only host offered. Smoke 2026-09-14: searched, served by novita, about $0.008 a pair.",
   "smoke_cost_per_pair": 0.008
  },
  {
   "model_key": "zai-small",
   "lab": "zai",
   "provider": "zai",
   "model": "zai/glm-4.7-flashx",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.06,
   "output_price_per_m": 0.4,
   "search_price_per_call": 0.005,
   "note": "Smoke 2026-09-14: gateway refused on free credits (rate-limited until paid credits are added); retry after top-up. Smoke 2026-09-14 after top-up: searched, served by zai, about $0.011 a pair.",
   "smoke_cost_per_pair": 0.011
  },
  {
   "model_key": "minimax-small",
   "lab": "minimax",
   "provider": "minimax",
   "model": "minimax/minimax-m2.5",
   "generation": "small",
   "tier": "standard",
   "transport": "gateway",
   "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
   "search": "vercel:perplexity_search",
   "input_price_per_m": 0.3,
   "output_price_per_m": 1.2,
   "search_price_per_call": 0.005,
   "note": "Smoke 2026-09-14: searched, served by minimax, about $0.007 a pair; slow, 156 s on the test prompt.",
   "smoke_cost_per_pair": 0.007
  }
 ],
 "settings": {
  "temperature": "provider default",
  "max_output_tokens": 4000,
  "anthropic_max_search_uses": 5,
  "fresh_session_per_prompt": true,
  "system_prompt": "none"
 },
 "pricing_note": "List prices captured 2026-09-08 from each provider pricing page. Gemini prices rise on 2027-01-01. Gemini grounding has 5000 free requests per month, not modeled. Perplexity request fee assumes medium search context unless the response reports usage.cost.total_cost. Free-tier list prices captured 2026-09-14 from each lab pricing page (direct) and the Vercel AI Gateway model list (gateway), which carries no markup.",
 "gateway": {
  "endpoint": "https://ai-gateway.vercel.sh/v1/chat/completions",
  "search_tool": "vercel:perplexity_search",
  "search_price_per_call": 0.005,
  "note": "Models without a native search tool are asked through Vercel AI Gateway in the OpenAI Chat Completions format, pinned to the lab own provider or to a short named list of hosts in order (providerOptions.gateway.only and order), no model fallback. search: client means the search tool is a function the collector runs itself against Perplexity's search API (the index the gateway's own tool reads), so the results each model was shown are recorded as its source list, the way the direct models' citations are; the September 2026 standard run used the gateway's server-side tool, which returns no source list. Zero markup on list prices; a search is $5 per 1,000.",
  "search": "client",
  "search_endpoint": "https://api.perplexity.ai/search",
  "search_results": 5
 }
}