@bitkyc08/opencodex 2.54.0-preview.20260914 → 2.55.0-preview.20260914

package/src/generated/model-metadata.ts

@@ -48,6 +48,7 @@ const DATA: Record<string, readonly Row[]> = {
   "mistral": [["codestral-latest",256000,4096,"text",0,null,0.3,0.9,0,0],["devstral-2512",262144,262144,"text",0,null,0.4,2,0,0],["devstral-latest",262144,262144,"text",0,null,0.4,2,0,0],["devstral-medium-2507",128000,128000,"text",0,null,0.4,2,0,0],["devstral-medium-latest",262144,262144,"text",0,null,0.4,2,0,0],["devstral-small-2505",128000,128000,"text",0,null,0.1,0.3,0,0],["devstral-small-2507",128000,128000,"text",0,null,0.1,0.3,0,0],["labs-devstral-small-2512",256000,256000,"text,image",0,null,0,0,0,0],["magistral-medium-latest",128000,16384,"text",1,null,2,5,0,0],["magistral-small",128000,128000,"text",1,null,0.5,1.5,0,0],["ministral-3b-latest",128000,128000,"text",0,null,0.04,0.04,0,0],["ministral-8b-latest",128000,128000,"text",0,null,0.1,0.1,0,0],["mistral-large-2411",131072,16384,"text",0,null,2,6,0,0],["mistral-large-2512",262144,262144,"text,image",0,null,0.5,1.5,0,0],["mistral-large-latest",262144,262144,"text,image",0,null,0.5,1.5,0,0],["mistral-medium-2505",131072,131072,"text,image",0,null,0.4,2,0,0],["mistral-medium-2508",262144,262144,"text,image",0,null,0.4,2,0,0],["mistral-medium-2604",262144,262144,"text,image",1,null,1.5,7.5,0,0],["mistral-medium-latest",262144,262144,"text,image",1,null,1.5,7.5,0,0],["mistral-nemo",128000,128000,"text",0,null,0.15,0.15,0,0],["mistral-small-2506",128000,16384,"text,image",0,null,0.1,0.3,0,0],["mistral-small-2603",256000,256000,"text,image",1,null,0.15,0.6,0,0],["mistral-small-latest",256000,256000,"text,image",1,null,0.15,0.6,0,0],["open-mistral-7b",8000,8000,"text",0,null,0.25,0.25,0,0],["open-mistral-nemo",128000,128000,"text",0,null,0.15,0.15,0,0],["open-mixtral-8x22b",64000,64000,"text",0,null,2,6,0,0],["open-mixtral-8x7b",32000,32000,"text",0,null,0.7,0.7,0,0],["pixtral-12b",128000,128000,"text,image",0,null,0.15,0.15,0,0],["pixtral-large-latest",128000,128000,"text,image",0,null,2,6,0,0]],
   "moonshot": [["kimi-k2.5",262144,65536,"text,image",1,null,0,0,0,0]],
   "openai": [["codex-mini-latest",200000,100000,"text",1,null,1.5,6,0.375,0],["gpt-4",8192,8192,"text",0,null,30,60,0,0],["gpt-4-turbo",128000,4096,"text,image",0,null,10,30,0,0],["gpt-4.1",1047576,32768,"text,image",0,null,2,8,0.5,0],["gpt-4.1-mini",1047576,32768,"text,image",0,null,0.4,1.6,0.1,0],["gpt-4.1-nano",1047576,32768,"text,image",0,null,0.1,0.4,0.025,0],["gpt-4o",128000,16384,"text,image",0,null,2.5,10,1.25,0],["gpt-4o-2024-05-13",128000,4096,"text,image",0,null,5,15,0,0],["gpt-4o-2024-08-06",128000,16384,"text,image",0,null,2.5,10,1.25,0],["gpt-4o-2024-11-20",128000,16384,"text,image",0,null,2.5,10,1.25,0],["gpt-4o-mini",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-chat-latest",128000,16384,"text,image",0,null,1.25,10,0.125,0],["gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-mini",400000,128000,"text,image",1,null,0.25,2,0.025,0],["gpt-5-nano",400000,128000,"text,image",1,null,0.05,0.4,0.005,0],["gpt-5-pro",400000,272000,"text,image",1,null,15,120,0,0],["gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-chat-latest",128000,16384,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-mini",272000,128000,"text,image",1,null,0.25,2,0.025,0],["gpt-5.2",400000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-chat-latest",128000,16384,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-pro",400000,128000,"text,image",1,null,21,168,0,0],["gpt-5.3-chat-latest",128000,16384,"text,image",0,null,1.75,14,0.175,0],["gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.3-codex-spark",128000,32000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.4",1050000,128000,"text,image",1,null,2.5,15,0.25,0],["gpt-5.4-mini",400000,128000,"text,image",1,null,0.75,4.5,0.075,0],["gpt-5.4-nano",400000,128000,"text,image",1,null,0.2,1.25,0.02,0],["gpt-5.4-pro",1050000,128000,"text,image",1,null,30,180,0,0],["gpt-5.5",1050000,128000,"text,image",1,null,5,30,0.5,0],["gpt-5.5-pro",1050000,128000,"text,image",1,null,30,180,0,0],["gpt-5.6",373000,128000,"text,image",1,null,5,30,0.5,6.25],["gpt-5.6-luna",373000,128000,"text,image",1,null,0.2,1.2,0.02,0.25],["gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["gpt-5.6-terra",373000,128000,"text,image",1,null,2,12,0.2,2.5],["gpt-realtime-2.1",128000,32000,"text,image",1,null,4,24,0.4,0],["o1",200000,100000,"text,image",1,null,15,60,7.5,0],["o1-pro",200000,100000,"text,image",1,null,150,600,0,0],["o3",200000,100000,"text,image",1,null,2,8,0.5,0],["o3-deep-research",200000,100000,"text,image",1,null,10,40,2.5,0],["o3-mini",200000,100000,"text",1,null,1.1,4.4,0.55,0],["o3-pro",200000,100000,"text,image",1,null,20,80,0,0],["o4-mini",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["o4-mini-deep-research",200000,100000,"text,image",1,null,2,8,0.5,0]],
+  "openai-codex": [["codex-auto-review",1000000,128000,"text,image",1,null,0,0,0,0],["gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5-codex-mini",272000,128000,"text,image",1,null,0,0,0,0],["gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.13,0],["gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["gpt-5.1-codex-mini",272000,128000,"text,image",1,null,0.25,2,0.025,0],["gpt-5.2",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["gpt-5.3-codex-spark",128000,128000,"text",1,null,1.75,14,0.175,0],["gpt-5.4",1000000,128000,"text,image",1,null,2.5,15,0.25,0],["gpt-5.4-mini",272000,128000,"text,image",1,null,0.75,4.5,0.075,0],["gpt-5.4-nano",272000,128000,"text,image",1,null,0.2,1.25,0.02,0],["gpt-5.5",272000,128000,"text,image",1,null,5,30,0.5,0],["gpt-5.6-luna",373000,128000,"text,image",1,null,0.2,1.2,0.02,0.25],["gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["gpt-5.6-terra",373000,128000,"text,image",1,null,2,12,0.2,2.5]],
   "opencode-go": [["deepseek-v4-flash",1000000,384000,"text",1,null,0.14,0.28,0.0028,0],["deepseek-v4-pro",1000000,384000,"text",1,null,1.74,3.48,0.0145,0],["glm-5",204800,131072,"text",1,null,1,3.2,0.2,0],["glm-5.1",200000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.2",1000000,131072,"text",1,null,1.4,4.4,0.26,0],["glm-5.3",1000000,131072,"text",1,null,1.4,4.4,0.26,0],["grok-4.5",500000,500000,"text,image",1,null,2,6,0.5,0],["grok-4.6",500000,500000,"text,image",1,null,2,6,0.5,0],["hy3",256000,64000,"text",1,null,0.14,0.58,0.035,0],["kimi-k2.5",262144,262144,"text,image",1,null,0.3,1.9,0,0],["kimi-k2.6",262144,262144,"text,image",1,null,0.95,4,0.2,0],["kimi-k2.7-code",262144,262144,"text,image",1,null,0.95,4,0.19,0],["kimi-k3",1048576,131072,"text,image",1,null,3,15,0.3,0],["mimo-v2-omni",262144,131072,"text,image",1,null,0.4,2,0.08,0],["mimo-v2-pro",1048576,131072,"text",1,null,1,3,0.2,0],["mimo-v2.5",1048576,131072,"text,image",1,null,0.14,0.28,0.0028,0],["mimo-v2.5-pro",1048576,131072,"text",1,null,1.74,3.48,0.0145,0],["minimax-m2.5",204800,131072,"text",1,null,0.3,1.2,0.06,0.375],["minimax-m2.7",204800,131072,"text",1,null,0.3,1.2,0.06,0.375],["minimax-m3",512000,128000,"text,image",1,null,0.3,1.2,0.06,0],["qwen3.5-plus",1000000,65536,"text,image",1,null,0.4,2.4,0,0],["qwen3.6-plus",1000000,65536,"text,image",1,null,2,6,0.2,2.5],["qwen3.7-max",1000000,65536,"text",1,null,2.5,7.5,0.5,3.125],["qwen3.7-plus",1000000,64000,"text,image",1,null,1.2,4.8,0.12,1.5]],
   "openrouter": [["~anthropic/claude-fable-latest",1000000,128000,"text,image",1,null,10,50,1,12.5],["~anthropic/claude-haiku-latest",200000,64000,"text,image",1,null,1,5,0.09999999999999999,1.25],["~anthropic/claude-opus-latest",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["~anthropic/claude-sonnet-latest",1000000,128000,"text,image",1,null,2,10,0.19999999999999998,2.5],["~google/gemini-flash-latest",1048576,65536,"text,image",1,null,1.5,7.5,0.15,0.08333333333333334],["~google/gemini-pro-latest",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["~moonshotai/kimi-latest",1048576,8888,"text,image",1,null,3,15,0.3,0],["~openai/gpt-latest",1050000,128000,"text,image",1,null,5,30,0.5,6.25],["~openai/gpt-mini-latest",400000,128000,"text,image",1,null,0.75,4.5,0.075,0],["~x-ai/grok-latest",500000,8888,"text,image",1,null,2,6,0.3,0],["ai21/jamba-large-1.7",256000,4096,"text",0,null,2,8,0,0],["aion-labs/aion-2.0",131072,32768,"text",1,null,0.7999999999999999,1.5999999999999999,0.19999999999999998,0],["aion-labs/aion-3.0",131072,32768,"text",1,null,3,6,0.75,0],["aion-labs/aion-3.0-mini",131072,32768,"text",1,null,0.7,1.4,0.18,0],["alibaba/tongyi-deepresearch-30b-a3b",131072,131072,"text",1,null,0.09,0.44999999999999996,0.09,0],["allenai/olmo-3.1-32b-instruct",65536,16384,"text",0,null,0.19999999999999998,0.6,0,0],["amazon/nova-2-lite-v1",1000000,65535,"text,image",1,null,0.3,2.5,0,0],["amazon/nova-lite-v1",300000,5120,"text,image",0,null,0.06,0.24,0,0],["amazon/nova-micro-v1",128000,5120,"text",0,null,0.035,0.14,0,0],["amazon/nova-premier-v1",1000000,32000,"text,image",0,null,2.5,12.5,0.625,0],["amazon/nova-pro-v1",300000,5120,"text,image",0,null,0.7999999999999999,3.1999999999999997,0,0],["anthropic/claude-3-haiku",200000,4096,"text,image",0,null,0.25,1.25,0.03,0.3],["anthropic/claude-3.5-haiku",200000,8192,"text,image",0,null,0.7999999999999999,4,0.08,1],["anthropic/claude-3.5-sonnet",200000,8192,"text,image",0,null,6,30,0.6,7.5],["anthropic/claude-3.7-sonnet",200000,128000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-3.7-sonnet:thinking",200000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-fable-5",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-haiku-4.5",200000,64000,"text,image",0,null,1,5,0.09999999999999999,1.25],["anthropic/claude-opus-4",200000,32000,"text,image",1,null,15,75,1.5,18.75],["anthropic/claude-opus-4.1",200000,32000,"text,image",1,null,15,75,1.5,18.75],["anthropic/claude-opus-4.5",200000,64000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.6",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.6-fast",1000000,128000,"text,image",1,null,30,150,3,37.5],["anthropic/claude-opus-4.7",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.7-fast",1000000,128000,"text,image",1,null,30,150,3,37.5],["anthropic/claude-opus-4.8",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-4.8-fast",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-opus-5",1000000,128000,"text,image",1,null,5,25,0.5,6.25],["anthropic/claude-opus-5-fast",1000000,128000,"text,image",1,null,10,50,1,12.5],["anthropic/claude-sonnet-4",1000000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-4.5",1000000,64000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-4.6",1000000,128000,"text,image",1,null,3,15,0.3,3.75],["anthropic/claude-sonnet-5",1000000,128000,"text,image",1,null,2,10,0.19999999999999998,2.5],["arcee-ai/trinity-large-preview",131000,8888,"text",0,null,0.15,0.44999999999999996,0,0],["arcee-ai/trinity-large-preview:free",131000,8888,"text",0,null,0,0,0,0],["arcee-ai/trinity-large-thinking",262144,262144,"text",1,null,0.22,0.85,0.06,0],["arcee-ai/trinity-large-thinking:free",262144,80000,"text",1,null,0,0,0,0],["arcee-ai/trinity-mini",131072,131072,"text",1,null,0.045,0.15,0,0],["arcee-ai/trinity-mini:free",131072,8888,"text",1,null,0,0,0,0],["arcee-ai/virtuoso-large",131072,64000,"text",0,null,0.75,1.2,0,0],["auto",2000000,30000,"text,image",1,null,0,0,0,0],["baidu/cobuddy:free",131072,65536,"text",1,null,0,0,0,0],["baidu/ernie-4.5-21b-a3b",131072,8000,"text",0,null,0.07,0.28,0,0],["baidu/ernie-4.5-vl-28b-a3b",131072,8000,"text,image",1,null,0.14,0.56,0,0],["bytedance-seed/seed-1.6",262144,32768,"text,image",1,null,0.25,2,0,0],["bytedance-seed/seed-1.6-flash",262144,32768,"text,image",1,null,0.075,0.3,0,0],["bytedance-seed/seed-2.0-lite",262144,131072,"text,image",1,null,0.25,2,0,0],["bytedance-seed/seed-2.0-mini",262144,131072,"text,image",1,null,0.09999999999999999,0.39999999999999997,0,0],["cohere/command-r-08-2024",128000,4000,"text",0,null,0.15,0.6,0,0],["cohere/command-r-plus-08-2024",128000,4000,"text",0,null,2.5,10,0,0],["cohere/north-mini-code:free",256000,64000,"text",1,null,0,0,0,0],["deepseek/deepseek-chat",163840,16000,"text",0,null,0.20020000000000002,0.8000999999999999,0.15,0],["deepseek/deepseek-chat-v3-0324",163840,65536,"text",1,null,0.27,1.12,0.135,0],["deepseek/deepseek-chat-v3.1",163840,32768,"text",1,null,0.25,0.95,0.13,0],["deepseek/deepseek-r1",163840,16000,"text",1,null,0.7,2.5,0,0],["deepseek/deepseek-r1-0528",163840,32768,"text",1,null,0.5,2.1500000000000004,0.35,0],["deepseek/deepseek-v3.1-terminus",163840,32768,"text",1,null,0.27,1,0.135,0],["deepseek/deepseek-v3.1-terminus:exacto",163840,8888,"text",1,null,0.21,0.7899999999999999,0.16799999999999998,0],["deepseek/deepseek-v3.2",163840,65536,"text",1,null,0.26899999999999996,0.39999999999999997,0.13449999999999998,0],["deepseek/deepseek-v3.2-exp",163840,65536,"text",1,null,0.27,0.41,0,0],["deepseek/deepseek-v4-flash",1048576,384000,"text",1,null,0.09380000000000001,0.18760000000000002,0.01876,0],["deepseek/deepseek-v4-flash:free",1048576,384000,"text",1,null,0,0,0,0],["deepseek/deepseek-v4-pro",1048576,384000,"text",1,null,0.435,0.87,0.003625,0],["essentialai/rnj-1-instruct",32768,8888,"text",0,null,0.15,0.15,0,0],["google/gemini-2.0-flash-001",1048576,8192,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.024999999999999998,0.08333333333333334],["google/gemini-2.0-flash-lite-001",1048576,8192,"text,image",0,null,0.075,0.3,0,0],["google/gemini-2.5-flash",1048576,65535,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-2.5-flash-lite",1048576,65535,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.01,0.08333333333333334],["google/gemini-2.5-flash-lite-preview-09-2025",1048576,65535,"text,image",1,null,0.09999999999999999,0.39999999999999997,0.01,0.08333333333333334],["google/gemini-2.5-flash-preview-09-2025",1048576,65536,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-2.5-pro",1048576,65536,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-2.5-pro-preview",1048576,65536,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-2.5-pro-preview-05-06",1048576,65535,"text,image",1,null,1.25,10,0.125,0.375],["google/gemini-3-flash-preview",1048576,65535,"text,image",1,null,0.5,3,0.049999999999999996,0.08333333333333334],["google/gemini-3-pro-image",131072,32768,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3-pro-preview",1048000,64000,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.1-flash-lite",1048576,65536,"text,image",1,null,0.25,1.5,0.024999999999999998,0.08333333333333334],["google/gemini-3.1-flash-lite-preview",1048576,65536,"text,image",0,null,0.25,1.5,0.024999999999999998,0.08333333333333334],["google/gemini-3.1-pro-preview",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.1-pro-preview-customtools",1048576,65536,"text,image",1,null,2,12,0.19999999999999998,0.375],["google/gemini-3.5-flash",1048576,65536,"text,image",1,null,1.5,9,0.15,0.08333333333333334],["google/gemini-3.5-flash-lite",1048576,65536,"text,image",1,null,0.3,2.5,0.03,0.08333333333333334],["google/gemini-3.6-flash",1048576,65536,"text,image",1,null,1.5,7.5,0.15,0.08333333333333334],["google/gemma-3-12b-it",131072,16384,"text,image",0,null,0.049999999999999996,0.15,0,0],["google/gemma-3-27b-it",262144,131072,"text,image",1,null,0.08,0.44999999999999996,0.04,0],["google/gemma-3-27b-it:free",131072,8192,"text,image",0,null,0,0,0,0],["google/gemma-4-26b-a4b-it",262144,262144,"text,image",1,null,0.12,0.35,0.049999999999999996,0],["google/gemma-4-26b-a4b-it:free",262144,32768,"text,image",1,null,0,0,0,0],["google/gemma-4-31b-it",262144,262144,"text,image",1,null,0.14,0.39999999999999997,0.09,0],["google/gemma-4-31b-it:free",262144,32768,"text,image",1,null,0,0,0,0],["ibm-granite/granite-4.1-8b",131072,131072,"text",0,null,0.049999999999999996,0.09999999999999999,0.049999999999999996,0],["inception/mercury",128000,32000,"text",0,null,0.25,0.75,0.024999999999999998,0],["inception/mercury-2",128000,50000,"text",1,null,0.25,0.75,0.024999999999999998,0],["inception/mercury-coder",128000,32000,"text",0,null,0.25,0.75,0.024999999999999998,0],["inclusionai/ling-2.6-1t",262144,32768,"text",0,null,0.075,0.625,0.015,0],["inclusionai/ling-2.6-1t:free",262144,32768,"text",0,null,0,0,0,0],["inclusionai/ling-2.6-flash",262144,32768,"text",0,null,0.01,0.03,0.002,0],["inclusionai/ling-2.6-flash:free",262144,32768,"text",0,null,0,0,0,0],["inclusionai/ling-3.0-flash:free",262144,32768,"text",1,null,0,0,0,0],["inclusionai/ring-2.6-1t",262144,65536,"text",1,null,0.075,0.625,0.015,0],["inclusionai/ring-2.6-1t:free",262144,65536,"text",1,null,0,0,0,0],["kwaipilot/kat-coder-air-v2.5",256000,80000,"text",0,null,0.15,0.6,0.03,0],["kwaipilot/kat-coder-pro",256000,128000,"text",0,null,0.207,0.828,0.0414,0],["kwaipilot/kat-coder-pro-v2",262144,80000,"text",0,null,0.3,1.2,0.06,0],["kwaipilot/kat-coder-pro-v2.5",256000,80000,"text",0,null,0.74,2.96,0.15,0],["liquid/lfm-2.5-1.2b-thinking:free",32768,8888,"text",1,null,0,0,0,0],["meituan/longcat-2.0",1048756,262144,"text",1,null,0.3,1.2,0.006,0],["meituan/longcat-flash-chat",131072,131072,"text",0,null,0.19999999999999998,0.7999999999999999,0.19999999999999998,0],["meta-llama/llama-3-8b-instruct",8192,16384,"text",0,null,0.03,0.04,0,0],["meta-llama/llama-3.1-405b-instruct",131000,8888,"text",0,null,4,4,0,0],["meta-llama/llama-3.1-70b-instruct",131072,16384,"text",0,null,0.39999999999999997,0.39999999999999997,0,0],["meta-llama/llama-3.1-8b-instruct",131072,131072,"text",0,null,0.049999999999999996,0.08,0.024999999999999998,0],["meta-llama/llama-3.3-70b-instruct",131072,128000,"text",0,null,0.13,0.39999999999999997,0,0],["meta-llama/llama-3.3-70b-instruct:free",131072,8888,"text",0,null,0,0,0,0],["meta-llama/llama-4-maverick",1048576,16384,"text,image",0,null,0.19999999999999998,0.7999999999999999,0,0],["meta-llama/llama-4-scout",1310720,16384,"text,image",0,null,0.09999999999999999,0.3,0,0],["meta/muse-spark-1.1",1048576,8888,"text,image",1,null,1.25,4.25,0.15,0],["minimax/minimax-m1",1000000,40000,"text",1,null,0.55,2.2,0,0],["minimax/minimax-m2",204800,131072,"text",1,null,0.255,1.02,0.03,0],["minimax/minimax-m2.1",204800,131072,"text",1,null,0.3,1.2,0.03,0],["minimax/minimax-m2.5",204800,196608,"text",1,null,0.15,0.8999999999999999,0.049999999999999996,0],["minimax/minimax-m2.5:free",262144,8192,"text",1,null,0,0,0,0],["minimax/minimax-m2.7",204800,131072,"text",1,null,0.25,1,0.049999999999999996,0],["minimax/minimax-m3",1048576,512000,"text,image",1,null,0.3,1.2,0.06,0],["mistralai/codestral-2508",256000,8888,"text",0,null,0.3,0.8999999999999999,0.03,0],["mistralai/devstral-2512",262144,8888,"text",0,null,0.39999999999999997,2,0.04,0],["mistralai/devstral-medium",131072,8888,"text",0,null,0.39999999999999997,2,0.04,0],["mistralai/devstral-small",131072,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/ministral-14b-2512",262144,8888,"text,image",0,null,0.19999999999999998,0.19999999999999998,0.02,0],["mistralai/ministral-3b-2512",131072,8888,"text,image",0,null,0.09999999999999999,0.09999999999999999,0.01,0],["mistralai/ministral-8b-2512",262144,8888,"text,image",0,null,0.15,0.15,0.015,0],["mistralai/mistral-large",128000,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2407",131072,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2411",131072,8888,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mistral-large-2512",262144,8888,"text,image",0,null,0.5,1.5,0.049999999999999996,0],["mistralai/mistral-medium-3",131072,8888,"text,image",0,null,0.39999999999999997,2,0.04,0],["mistralai/mistral-medium-3-5",262144,8888,"text,image",1,null,1.5,7.5,0,0],["mistralai/mistral-medium-3.1",131072,8888,"text,image",0,null,0.39999999999999997,2,0.04,0],["mistralai/mistral-nemo",131072,16384,"text",0,null,0.019000000000000003,0.03,0,0],["mistralai/mistral-saba",32768,8888,"text",0,null,0.19999999999999998,0.6,0.02,0],["mistralai/mistral-small-24b-instruct-2501",32768,16384,"text",0,null,0.049999999999999996,0.08,0,0],["mistralai/mistral-small-2603",262144,8888,"text,image",1,null,0.15,0.6,0.015,0],["mistralai/mistral-small-3.1-24b-instruct",131072,131072,"text,image",0,null,0.03,0.11,0.015,0],["mistralai/mistral-small-3.1-24b-instruct:free",128000,8888,"text,image",0,null,0,0,0,0],["mistralai/mistral-small-3.2-24b-instruct",256000,8888,"text,image",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/mistral-small-creative",32768,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["mistralai/mixtral-8x22b-instruct",65536,13108,"text",0,null,2,6,0.19999999999999998,0],["mistralai/mixtral-8x7b-instruct",32768,16384,"text",0,null,0.54,0.54,0,0],["mistralai/pixtral-large-2411",131072,8888,"text,image",0,null,2,6,0.19999999999999998,0],["mistralai/voxtral-small-24b-2507",32000,8888,"text",0,null,0.09999999999999999,0.3,0.01,0],["moonshotai/kimi-k2",131072,100352,"text",0,null,0.5700000000000001,2.3,0,0],["moonshotai/kimi-k2-0905",262144,100352,"text",0,null,0.6,2.5,0.15,0],["moonshotai/kimi-k2-0905:exacto",262144,8888,"text",0,null,0.6,2.5,0,0],["moonshotai/kimi-k2-thinking",262144,100352,"text",1,null,0.6,2.5,0.15,0],["moonshotai/kimi-k2.5",262144,262144,"text,image",1,null,0.5700000000000001,2.8499999999999996,0.095,0],["moonshotai/kimi-k2.6",262144,262144,"text,image",1,null,0.646,2.7199999999999998,0.1088,0],["moonshotai/kimi-k2.6:free",262144,8888,"text,image",1,null,0,0,0,0],["moonshotai/kimi-k2.7-code",262144,262144,"text,image",1,null,0.78,3.5,0.15,0],["moonshotai/kimi-k3",1048576,131072,"text,image",1,null,3,15,0.3,0],["nex-agi/deepseek-v3.1-nex-n1",131072,163840,"text",0,null,0.135,0.5,0,0],["nex-agi/nex-n2-mini",262144,262144,"text,image",1,null,0.024999999999999998,0.09999999999999999,0.0025,0],["nex-agi/nex-n2-pro",262144,262144,"text,image",1,null,0.25,1,0.024999999999999998,0],["nex-agi/nex-n2-pro:free",262144,262144,"text,image",1,null,0,0,0,0],["nousresearch/deephermes-3-mistral-24b-preview",32768,32768,"text",1,null,0.02,0.09999999999999999,0.01,0],["nousresearch/hermes-4-70b",131072,131072,"text",1,null,0.11,0.38,0.055,0],["nvidia/llama-3.1-nemotron-70b-instruct",131072,16384,"text",0,null,1.2,1.2,0,0],["nvidia/llama-3.3-nemotron-super-49b-v1.5",131072,16384,"text",1,null,0.39999999999999997,0.39999999999999997,0,0],["nvidia/nemotron-3-nano-30b-a3b",262144,228000,"text",1,null,0.049999999999999996,0.19999999999999998,0,0],["nvidia/nemotron-3-nano-30b-a3b:free",256000,8888,"text",1,null,0,0,0,0],["nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",256000,65536,"text,image",1,null,0,0,0,0],["nvidia/nemotron-3-super-120b-a12b",1000000,16384,"text",1,null,0.08499999999999999,0.39999999999999997,0.09999999999999999,0],["nvidia/nemotron-3-super-120b-a12b:free",262144,262144,"text",1,null,0,0,0,0],["nvidia/nemotron-3-ultra-550b-a55b",512288,65536,"text",1,null,0.6,3.5999999999999996,0.19999999999999998,0],["nvidia/nemotron-3-ultra-550b-a55b:free",1000000,65536,"text",1,null,0,0,0,0],["nvidia/nemotron-nano-12b-v2-vl:free",128000,128000,"text,image",1,null,0,0,0,0],["nvidia/nemotron-nano-9b-v2",131072,16384,"text",1,null,0.04,0.16,0,0],["nvidia/nemotron-nano-9b-v2:free",128000,8888,"text",1,null,0,0,0,0],["openai/gpt-3.5-turbo",16385,4096,"text",0,null,0.5,1.5,0,0],["openai/gpt-3.5-turbo-0613",4095,4096,"text",0,null,1,2,0,0],["openai/gpt-3.5-turbo-16k",16385,4096,"text",0,null,3,4,0,0],["openai/gpt-4",8191,8192,"text",0,null,30,60,0,0],["openai/gpt-4-0314",8191,4096,"text",0,null,30,60,0,0],["openai/gpt-4-1106-preview",128000,4096,"text",0,null,10,30,0,0],["openai/gpt-4-turbo",128000,4096,"text,image",0,null,10,30,0,0],["openai/gpt-4-turbo-preview",128000,4096,"text",0,null,10,30,0,0],["openai/gpt-4.1",1047576,32768,"text,image",0,null,2,8,0.5,0],["openai/gpt-4.1-mini",1047576,32768,"text,image",0,null,0.39999999999999997,1.5999999999999999,0.09999999999999999,0],["openai/gpt-4.1-nano",1047576,32768,"text,image",0,null,0.09999999999999999,0.39999999999999997,0.024999999999999998,0],["openai/gpt-4o",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-2024-05-13",128000,4096,"text,image",0,null,5,15,0,0],["openai/gpt-4o-2024-08-06",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-2024-11-20",128000,16384,"text,image",0,null,2.5,10,1.25,0],["openai/gpt-4o-audio-preview",128000,16384,"text",0,null,2.5,10,0,0],["openai/gpt-4o-mini",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["openai/gpt-4o-mini-2024-07-18",128000,16384,"text,image",0,null,0.15,0.6,0.075,0],["openai/gpt-4o:extended",128000,64000,"text,image",0,null,6,18,0,0],["openai/gpt-5",400000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5-image",400000,128000,"text,image",1,null,10,10,1.25,0],["openai/gpt-5-image-mini",400000,128000,"text,image",1,null,2.5,2,0.25,0],["openai/gpt-5-mini",400000,128000,"text,image",1,null,0.25,2,0.024999999999999998,0],["openai/gpt-5-nano",400000,128000,"text,image",1,null,0.049999999999999996,0.39999999999999997,0.005,0],["openai/gpt-5-pro",400000,128000,"text,image",1,null,15,120,0,0],["openai/gpt-5.1",400000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-chat",128000,16384,"text,image",0,null,1.25,10,0.125,0],["openai/gpt-5.1-codex",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-codex-max",272000,128000,"text,image",1,null,1.25,10,0.125,0],["openai/gpt-5.1-codex-mini",272000,100000,"text,image",1,null,0.25,2,0.024999999999999998,0],["openai/gpt-5.2",400000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.2-chat",128000,16384,"text,image",0,null,1.75,14,0.175,0],["openai/gpt-5.2-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.2-pro",400000,128000,"text,image",1,null,21,168,0,0],["openai/gpt-5.3-chat",128000,16384,"text",0,null,1.75,14,0.175,0],["openai/gpt-5.3-codex",272000,128000,"text,image",1,null,1.75,14,0.175,0],["openai/gpt-5.4",1050000,128000,"text,image",1,null,2.5,15,0.25,0],["openai/gpt-5.4-mini",400000,128000,"text",0,null,0.75,4.5,0.075,0],["openai/gpt-5.4-nano",400000,128000,"text",0,null,0.19999999999999998,1.25,0.02,0],["openai/gpt-5.4-pro",1050000,128000,"text,image",1,null,30,180,0,0],["openai/gpt-5.5",1050000,128000,"text,image",1,null,5,30,0.5,0],["openai/gpt-5.5-pro",1050000,128000,"text,image",1,null,30,180,0,0],["openai/gpt-5.6-luna",373000,128000,"text,image",1,null,1,6,0.09999999999999999,1.25],["openai/gpt-5.6-luna-pro",373000,128000,"text,image",1,null,1,6,0.09999999999999999,1.25],["openai/gpt-5.6-sol",373000,128000,"text,image",1,null,5,30,0.5,6.25],["openai/gpt-5.6-sol-pro",373000,128000,"text,image",1,null,5,30,0.5,6.25],["openai/gpt-5.6-terra",373000,128000,"text,image",1,null,2.5,15,0.25,3.125],["openai/gpt-5.6-terra-pro",373000,128000,"text,image",1,null,2.5,15,0.25,3.125],["openai/gpt-audio",128000,16384,"text",0,null,2.5,10,0,0],["openai/gpt-audio-mini",128000,16384,"text",0,null,0.6,2.4,0,0],["openai/gpt-chat-latest",400000,128000,"text,image",0,null,5,30,0.5,0],["openai/gpt-oss-120b",131072,131072,"text",1,null,0.037,0.16999999999999998,0,0],["openai/gpt-oss-120b:exacto",131072,8888,"text",1,null,0.039,0.19,0,0],["openai/gpt-oss-120b:free",131072,131072,"text",1,null,0,0,0,0],["openai/gpt-oss-20b",131072,131072,"text",1,null,0.03,0.13,0.03,0],["openai/gpt-oss-20b:free",131072,32768,"text",1,null,0,0,0,0],["openai/gpt-oss-safeguard-20b",131072,65536,"text",1,null,0.075,0.3,0.0375,0],["openai/o1",200000,100000,"text,image",1,null,15,60,7.5,0],["openai/o3",200000,100000,"text,image",1,null,2,8,0.5,0],["openai/o3-deep-research",200000,100000,"text,image",1,null,10,40,2.5,0],["openai/o3-mini",200000,100000,"text",1,null,1.1,4.4,0.55,0],["openai/o3-mini-high",200000,100000,"text",1,null,1.1,4.4,0.55,0],["openai/o3-pro",200000,100000,"text,image",1,null,20,80,0,0],["openai/o4-mini",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["openai/o4-mini-deep-research",200000,100000,"text,image",1,null,2,8,0.5,0],["openai/o4-mini-high",200000,100000,"text,image",1,null,1.1,4.4,0.275,0],["openrouter/aurora-alpha",128000,50000,"text",1,null,0,0,0,0],["openrouter/auto",2000000,8888,"text,image",1,null,-1000000,-1000000,0,0],["openrouter/auto-beta",2000000,8888,"text,image",1,null,-1000000,-1000000,0,0],["openrouter/elephant-alpha",262144,32768,"text",0,null,0,0,0,0],["openrouter/free",200000,8888,"text,image",1,null,0,0,0,0],["openrouter/healer-alpha",262144,32000,"text,image",1,null,0,0,0,0],["openrouter/hunter-alpha",1048576,32000,"text",1,null,0,0,0,0],["openrouter/owl-alpha",1048756,262144,"text",0,null,0,0,0,0],["poolside/laguna-m.1",262144,32768,"text",1,null,0.19999999999999998,0.39999999999999997,0.09999999999999999,0],["poolside/laguna-m.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-s-2.1",1048576,131072,"text",1,null,0.09999999999999999,0.19999999999999998,0.01,0],["poolside/laguna-s-2.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-xs-2.1",262144,32768,"text",1,null,0.06,0.12,0.03,0],["poolside/laguna-xs-2.1:free",262144,32768,"text",1,null,0,0,0,0],["poolside/laguna-xs.2",262144,32768,"text",1,null,0.09999999999999999,0.19999999999999998,0.049999999999999996,0],["poolside/laguna-xs.2:free",262144,32768,"text",1,null,0,0,0,0],["prime-intellect/intellect-3",131072,131072,"text",1,null,0.19999999999999998,1.1,0,0],["qwen/qwen-2.5-72b-instruct",32768,16384,"text",0,null,0.36,0.39999999999999997,0,0],["qwen/qwen-2.5-7b-instruct",32768,32768,"text",0,null,0.04,0.09999999999999999,0,0],["qwen/qwen-max",32768,8192,"text",0,null,1.04,4.16,0.20800000000000002,0],["qwen/qwen-plus",1000000,32768,"text",0,null,0.26,0.78,0.052000000000000005,0.325],["qwen/qwen-plus-2025-07-28",1000000,32768,"text",0,null,0.26,0.78,0,0.325],["qwen/qwen-plus-2025-07-28:thinking",1000000,32768,"text",1,null,0.26,0.78,0,0.325],["qwen/qwen-turbo",131072,8192,"text",0,null,0.0325,0.13,0.006500000000000001,0],["qwen/qwen-vl-max",131072,32768,"text,image",0,null,0.52,2.08,0,0],["qwen/qwen3-14b",131072,8192,"text",1,null,0.22749999999999998,0.9099999999999999,0,0],["qwen/qwen3-235b-a22b",131072,8192,"text",1,null,0.45499999999999996,1.8199999999999998,0,0],["qwen/qwen3-235b-a22b-2507",262144,16384,"text",1,null,0.09,0.55,0,0],["qwen/qwen3-235b-a22b-thinking-2507",262144,32768,"text",1,null,0.3,3,0.09999999999999999,0],["qwen/qwen3-30b-a3b",131072,8192,"text",1,null,0.13,0.52,0,0],["qwen/qwen3-30b-a3b-instruct-2507",262144,32000,"text",0,null,0.04815,0.19305,0,0],["qwen/qwen3-30b-a3b-thinking-2507",81920,32768,"text",1,null,0.13,1.56,0.08,0],["qwen/qwen3-32b",131072,16384,"text",1,null,0.08,0.28,0.04,0],["qwen/qwen3-4b",131072,8192,"text",1,null,0.0715,0.273,0,0],["qwen/qwen3-4b:free",40960,8888,"text",1,null,0,0,0,0],["qwen/qwen3-8b",131072,8192,"text",1,null,0.117,0.45499999999999996,0.049999999999999996,0],["qwen/qwen3-coder",262144,65536,"text",0,null,0.3,1,0.09999999999999999,0],["qwen/qwen3-coder-30b-a3b-instruct",262144,32768,"text",0,null,0.07,0.27,0,0],["qwen/qwen3-coder-flash",1000000,65536,"text",0,null,0.195,0.975,0.039,0.24375],["qwen/qwen3-coder-next",262144,262144,"text",0,null,0.11,0.7999999999999999,0.07,0],["qwen/qwen3-coder-plus",1000000,65536,"text",0,null,0.65,3.25,0.13,0.8125],["qwen/qwen3-coder:exacto",262144,65536,"text",0,null,0.22,1.7999999999999998,0.022,0],["qwen/qwen3-coder:free",1048576,262000,"text",0,null,0,0,0,0],["qwen/qwen3-max",262144,32768,"text",1,null,0.78,3.9,0.156,0.975],["qwen/qwen3-max-thinking",262144,32768,"text",1,null,0.78,3.9,0,0],["qwen/qwen3-next-80b-a3b-instruct",262144,262144,"text",0,null,0.09999999999999999,1.1,0.07,0],["qwen/qwen3-next-80b-a3b-instruct:free",262144,8888,"text",0,null,0,0,0,0],["qwen/qwen3-next-80b-a3b-thinking",262144,32768,"text",1,null,0.0975,0.78,0,0],["qwen/qwen3-vl-235b-a22b-instruct",262144,32768,"text,image",0,null,0.21,1.9,0.09999999999999999,0],["qwen/qwen3-vl-235b-a22b-thinking",131072,32768,"text,image",1,null,0.26,2.6,0,0],["qwen/qwen3-vl-30b-a3b-instruct",262144,16384,"text,image",0,null,0.15,0.6,0,0],["qwen/qwen3-vl-30b-a3b-thinking",262144,32768,"text,image",1,null,0.13,1.56,0,0],["qwen/qwen3-vl-32b-instruct",131072,32768,"text,image",0,null,0.10400000000000001,0.41600000000000004,0,0],["qwen/qwen3-vl-8b-instruct",262144,32768,"text,image",0,null,0.117,0.45499999999999996,0,0],["qwen/qwen3-vl-8b-thinking",131072,32768,"text,image",1,null,0.117,1.365,0,0],["qwen/qwen3.5-122b-a10b",262144,65536,"text,image",1,null,0.26,2.08,0,0],["qwen/qwen3.5-27b",262144,65536,"text,image",1,null,0.195,1.56,0,0],["qwen/qwen3.5-35b-a3b",262144,262144,"text,image",1,null,0.14,1,0.049999999999999996,0],["qwen/qwen3.5-397b-a17b",262144,65536,"text,image",1,null,0.39,2.34,0.111,0],["qwen/qwen3.5-9b",262144,262144,"text,image",1,null,0.09999999999999999,0.15,0,0],["qwen/qwen3.5-flash-02-23",1000000,65536,"text,image",1,null,0.065,0.26,0,0.08125],["qwen/qwen3.5-plus-02-15",1000000,65536,"text,image",1,null,0.26,1.56,0,0.325],["qwen/qwen3.5-plus-20260420",1000000,65536,"text,image",1,null,0.3,1.7999999999999998,0,0.375],["qwen/qwen3.6-27b",262144,131072,"text,image",1,null,0.28900000000000003,2.4,0.15,0],["qwen/qwen3.6-35b-a3b",262144,262144,"text,image",1,null,0.14,1,0.049999999999999996,0],["qwen/qwen3.6-flash",1000000,65536,"text,image",1,null,0.1875,1.125,0,0.234375],["qwen/qwen3.6-max-preview",262144,65536,"text",1,null,1.04,6.24,0,1.3],["qwen/qwen3.6-plus",1000000,65536,"text",1,null,0.325,1.95,0,0.40625],["qwen/qwen3.6-plus-preview:free",1000000,32000,"text",1,null,0,0,0,0],["qwen/qwen3.6-plus:free",1000000,65536,"text,image",1,null,0,0,0,0],["qwen/qwen3.7-max",1000000,65536,"text",1,null,1.475,4.425,0.295,1.84375],["qwen/qwen3.7-plus",1000000,65536,"text,image",1,null,0.32,1.28,0.064,0.39999999999999997],["qwen/qwq-32b",131072,131072,"text",1,null,0.15,0.58,0,0],["reka/reka-edge",16384,16384,"text,image",0,null,0.09999999999999999,0.09999999999999999,0,0],["rekaai/reka-edge",16384,16384,"text,image",0,null,0.09999999999999999,0.09999999999999999,0,0],["relace/relace-search",256000,128000,"text",0,null,1,3,0,0],["sakana/fugu-ultra",1000000,128000,"text,image",1,null,5,30,0.5,0],["sao10k/l3-euryale-70b",8192,8192,"text",0,null,1.48,1.48,0,0],["sao10k/l3.1-euryale-70b",131072,16384,"text",0,null,0.85,0.85,0,0],["stepfun/step-3.5-flash",262144,65536,"text",0,null,0.09999999999999999,0.3,0.02,0],["stepfun/step-3.5-flash:free",256000,256000,"text",1,null,0,0,0,0],["stepfun/step-3.7-flash",262144,256000,"text,image",1,null,0.19999999999999998,1.15,0.04,0],["tencent/hy3",262144,128000,"text",1,null,0.13199999999999998,0.5279999999999999,0.032999999999999995,0],["tencent/hy3-preview",262144,64000,"text",1,null,0.063,0.21,0.020999999999999998,0],["tencent/hy3-preview:free",262144,262144,"text",1,null,0,0,0,0],["tencent/hy3:free",262144,262144,"text",1,null,0,0,0,0],["thedrummer/rocinante-12b",32768,32768,"text",0,null,0.16999999999999998,0.43,0,0],["thedrummer/unslopnemo-12b",32768,32768,"text",0,null,0.39999999999999997,0.39999999999999997,0,0],["thinkingmachines/inkling",1048576,8888,"text,image",1,null,1,4.05,0.16999999999999998,0],["tngtech/deepseek-r1t2-chimera",163840,163840,"text",1,null,0.3,1.1,0.15,0],["tngtech/tng-r1t-chimera",163840,65536,"text",1,null,0.25,0.85,0.125,0],["upstage/solar-pro-3",128000,8888,"text",1,null,0.15,0.6,0.015,0],["upstage/solar-pro-3:free",128000,8888,"text",1,null,0,0,0,0],["x-ai/grok-3",131072,8888,"text",0,null,3,15,0.75,0],["x-ai/grok-3-beta",131072,8888,"text",0,null,3,15,0.75,0],["x-ai/grok-3-mini",131072,8888,"text",1,null,0.3,0.5,0.075,0],["x-ai/grok-3-mini-beta",131072,8888,"text",1,null,0.3,0.5,0.075,0],["x-ai/grok-4",256000,64000,"text,image",1,null,3,15,0.75,0],["x-ai/grok-4-fast",2000000,30000,"text,image",1,null,0.19999999999999998,0.5,0.049999999999999996,0],["x-ai/grok-4.1-fast",2000000,30000,"text,image",1,null,0.19999999999999998,0.5,0.049999999999999996,0],["x-ai/grok-4.20",2000000,8888,"text,image",1,null,1.25,2.5,0.19999999999999998,0],["x-ai/grok-4.20-beta",2000000,8888,"text,image",1,null,2,6,0.19999999999999998,0],["x-ai/grok-4.3",1000000,1000000,"text,image",1,null,1.25,2.5,0.19999999999999998,0],["x-ai/grok-4.5",500000,500000,"text,image",1,null,2,6,0.3,0],["x-ai/grok-4.6",500000,500000,"text,image",1,null,2,6,0.3,0],["x-ai/grok-build-0.1",256000,256000,"text,image",1,null,1,2,0.19999999999999998,0],["x-ai/grok-code-fast-1",256000,10000,"text",1,null,0.19999999999999998,1.5,0.02,0],["xiaomi/mimo-v2-flash",262144,65536,"text",1,null,0.09999999999999999,0.3,0.01,0],["xiaomi/mimo-v2-omni",262144,65536,"text,image",1,null,0.39999999999999997,2,0.08,0],["xiaomi/mimo-v2-pro",1048576,131072,"text",1,null,1,3,0.19999999999999998,0],["xiaomi/mimo-v2.5",1050000,131072,"text,image",1,null,0.14,0.28,0.0028,0],["xiaomi/mimo-v2.5-pro",1050000,131072,"text",1,null,0.435,0.87,0.0036,0],["z-ai/glm-4-32b",128000,8888,"text",0,null,0.09999999999999999,0.09999999999999999,0,0],["z-ai/glm-4.5",131072,98304,"text",1,null,0.6,2.2,0.11,0],["z-ai/glm-4.5-air",131072,98304,"text",1,null,0.13,0.85,0.024999999999999998,0],["z-ai/glm-4.5-air:free",131072,96000,"text",1,null,0,0,0,0],["z-ai/glm-4.5v",65536,16384,"text,image",1,null,0.6,1.7999999999999998,0.11,0],["z-ai/glm-4.6",204800,131072,"text",1,null,0.5,2,0.09999999999999999,0],["z-ai/glm-4.6:exacto",204800,131072,"text",1,null,0.44,1.76,0.11,0],["z-ai/glm-4.6v",131072,32768,"text,image",1,null,0.3,0.8999999999999999,0.055,0],["z-ai/glm-4.7",204800,131072,"text",1,null,0.39999999999999997,1.75,0.08,0],["z-ai/glm-4.7-flash",202752,16384,"text",1,null,0.06,0.39999999999999997,0.01,0],["z-ai/glm-5",204800,131072,"text",1,null,0.95,2.5500000000000003,0.19999999999999998,0],["z-ai/glm-5-turbo",202752,131072,"text",1,null,1.2,4,0.24,0],["z-ai/glm-5.1",204800,128000,"text",1,null,0.966,3.036,0.1794,0],["z-ai/glm-5.2",1048576,131072,"text",1,null,0.707,2.222,0.1313,0],["z-ai/glm-5.3",1048576,131072,"text",1,null,0.707,2.222,0.1313,0],["z-ai/glm-5v-turbo",202752,131072,"text,image",1,null,1.2,4,0.24,0]],
   "xai": [["grok-2",131072,8192,"text",0,null,2,10,2,0],["grok-2-1212",131072,8192,"text",0,null,2,10,2,0],["grok-2-latest",131072,8192,"text",0,null,2,10,2,0],["grok-2-vision",8192,4096,"text,image",0,null,2,10,2,0],["grok-2-vision-1212",8192,4096,"text,image",0,null,2,10,2,0],["grok-2-vision-latest",8192,4096,"text,image",0,null,2,10,2,0],["grok-3",131072,8192,"text",0,null,3,15,0.75,0],["grok-3-fast",131072,8192,"text",0,null,5,25,1.25,0],["grok-3-fast-latest",131072,8192,"text",0,null,5,25,1.25,0],["grok-3-latest",131072,8192,"text",0,null,3,15,0.75,0],["grok-3-mini",131072,8192,"text",1,null,0.3,0.5,0.075,0],["grok-3-mini-fast",131072,8192,"text",1,null,0.6,4,0.15,0],["grok-3-mini-fast-latest",131072,8192,"text",1,null,0.6,4,0.15,0],["grok-3-mini-latest",131072,8192,"text",1,null,0.3,0.5,0.075,0],["grok-4",256000,64000,"text",1,null,3,15,0.75,0],["grok-4-1-fast",2000000,30000,"text,image",1,null,0.2,0.5,0.05,0],["grok-4-1-fast-non-reasoning",2000000,30000,"text,image",0,null,0.2,0.5,0.05,0],["grok-4-fast",2000000,30000,"text,image",1,null,0.2,0.5,0.05,0],["grok-4-fast-non-reasoning",2000000,30000,"text,image",0,null,0.2,0.5,0.05,0],["grok-4.20-0309-non-reasoning",1000000,30000,"text,image",0,null,1.25,2.5,0.2,0],["grok-4.20-0309-reasoning",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.20-beta-latest-non-reasoning",2000000,30000,"text,image",0,null,2,6,0.2,0],["grok-4.20-beta-latest-reasoning",2000000,30000,"text,image",1,null,2,6,0.2,0],["grok-4.20-multi-agent-0309",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.20-multi-agent-beta-latest",2000000,30000,"text,image",1,null,2,6,0.2,0],["grok-4.3",1000000,30000,"text,image",1,null,1.25,2.5,0.2,0],["grok-4.5",500000,500000,"text,image",1,null,2,6,0.3,0],["grok-4.6",500000,500000,"text,image",1,null,2,6,0.3,0],["grok-beta",131072,4096,"text",0,null,5,15,5,0],["grok-build-0.1",256000,256000,"text,image",1,null,1,2,0.2,0],["grok-code-fast-1",256000,10000,"text",1,null,0.2,1.5,0.02,0],["grok-composer-2.5-fast",200000,64000,"text",1,null,0,0,0,0],["grok-vision-beta",8192,4096,"text,image",0,null,5,15,5,0]],

package/src/lib/request-execution-budget.ts

@@ -0,0 +1,202 @@
+/**
+ * One logical request, one execution budget (#4546).
+ *
+ * The amplification behind #4546 was never a single missing limit. Every layer that can
+ * re-send a request -- transport retry, adapter retry, auth recovery, account failover, combo
+ * failover, repair -- counted its own allowance, so a per-layer 3 composed into a per-request
+ * 12. #4605 and #4608 gave the transient layers one shared counter; this module is the policy
+ * that counter answers to.
+ *
+ * The policy is an INTERSECTION of constraints, not four independent counters. A request that
+ * still has total allowance left is not thereby entitled to a second account move, and a
+ * request that changed credentials does not get its target-transition allowance back. The
+ * default profile keeps the recovery shape that actually works today -- three same-account
+ * sends plus one alternate -- by funding the alternate from a reserve that a validated
+ * sanitized repair can spend instead, but never both.
+ */
+import type { TransientSendBudget } from "./upstream-retry";
+
+export type SendClass =
+  | "initial"
+  | "transient"
+  | "auth-recovery"
+  | "repair"
+  | "account-failover"
+  | "combo-failover"
+  | "prewarm";
+
+export interface RequestExecutionBudgetPolicy {
+  /** Every model send of one logical request, including the reserve. */
+  readonly maxTotalModelSends: number;
+  /** Shared by the initial send, same-target transient retries, and refresh/repair legs. */
+  readonly baseSendAllowance: number;
+  /** ONE final recovery, shared by an account move and a validated rebuild. Not one each. */
+  readonly finalRecoveryAllowance: number;
+  readonly maxAlternateTargetSends: number;
+  readonly maxTargetTransitions: number;
+}
+
+/**
+ * Text Codex guarded profile. Three same-account sends plus one alternate is the recovery
+ * shape that live traffic depends on, so a flat ceiling of 3 would break a working path.
+ */
+export const CODEX_TEXT_GUARDED_BUDGET_POLICY: RequestExecutionBudgetPolicy = {
+  maxTotalModelSends: 4,
+  baseSendAllowance: 3,
+  finalRecoveryAllowance: 1,
+  maxAlternateTargetSends: 1,
+  maxTargetTransitions: 1,
+};
+
+export const REQUEST_BUDGET_POLICY_VERSION = "guarded-v1";
+
+export type BudgetDenial =
+  | "total-exhausted"
+  | "base-allowance-exhausted"
+  | "final-recovery-spent"
+  | "alternate-target-exhausted"
+  | "target-transition-exhausted"
+  | "not-replay-safe";
+
+export interface DispatchIntent {
+  readonly sendClass: SendClass;
+  /**
+   * (provider route, endpoint, model lane, upstream credential identity). A quota domain is a
+   * different thing and must not be folded in here.
+   */
+  readonly targetKey: string;
+  /**
+   * False refuses the dispatch outright. A request whose execution state upstream is unknown
+   * is not replayable just because budget remains (RFC 9110 9.2.2).
+   */
+  readonly replaySafe?: boolean;
+  /**
+   * True when the physical send is already reported through another counter -- the retry
+   * helpers' `onSendsConsumed` hook. The permit then books the reserve, alternate-target and
+   * transition ledgers but leaves `used` to that reporter, because charging both is how a
+   * four-send cap silently becomes a two-send cap.
+   */
+  readonly countedExternally?: boolean;
+}
+
+export interface SingleUseDispatchPermit {
+  readonly sendClass: SendClass;
+  /** Consume exactly once. A second call returns false and charges nothing. */
+  use(): boolean;
+}
+
+export type DispatchDecision =
+  | { allowed: true; permit: SingleUseDispatchPermit }
+  | { allowed: false; reason: BudgetDenial };
+
+/**
+ * Carried on HandleResponsesOptions so a combo child, a rebuild and an alternate-account leg
+ * all decrement the same holder. `used` is the existing #4605 counter and still counts every
+ * model send; the reserve is what the fourth send draws on once the base allowance is gone.
+ */
+export interface RequestExecutionBudget extends TransientSendBudget {
+  readonly logicalRequestId: string;
+  readonly policyVersion: string;
+  readonly policy: RequestExecutionBudgetPolicy;
+  reserveDispatch(intent: DispatchIntent): DispatchDecision;
+  /**
+   * Sends still available from the base allowance, capped by a layer's own maximum.
+   * Returns 0 when the allowance is gone -- it never floors to 1, because a floor of 1 is
+   * what let every recovery leg send one more time forever.
+   */
+  remainingBaseSends(cap: number): number;
+  readonly reserveSpent: boolean;
+  readonly alternateTargetSends: number;
+  readonly targetTransitions: number;
+  readonly lastTargetKey: string | undefined;
+}
+
+const RESERVE_FUNDED_CLASSES: ReadonlySet<SendClass> = new Set<SendClass>([
+  "account-failover",
+  "combo-failover",
+  "repair",
+  "auth-recovery",
+]);
+
+let logicalRequestSeq = 0;
+
+export function createRequestExecutionBudget(
+  policy: RequestExecutionBudgetPolicy = CODEX_TEXT_GUARDED_BUDGET_POLICY,
+  logicalRequestId?: string,
+): RequestExecutionBudget {
+  let reserveSpent = false;
+  let alternateTargetSends = 0;
+  let targetTransitions = 0;
+  let lastTargetKey: string | undefined;
+
+  const budget: RequestExecutionBudget = {
+    used: 0,
+    logicalRequestId: logicalRequestId ?? `lr-${Date.now().toString(36)}-${(logicalRequestSeq += 1).toString(36)}`,
+    policyVersion: REQUEST_BUDGET_POLICY_VERSION,
+    policy,
+    get reserveSpent() { return reserveSpent; },
+    get alternateTargetSends() { return alternateTargetSends; },
+    get targetTransitions() { return targetTransitions; },
+    get lastTargetKey() { return lastTargetKey; },
+    remainingBaseSends(cap: number): number {
+      const capped = Number.isFinite(cap) ? Math.trunc(cap) : 0;
+      return Math.max(0, Math.min(capped, policy.baseSendAllowance - budget.used));
+    },
+    reserveDispatch(intent: DispatchIntent): DispatchDecision {
+      if (intent.replaySafe === false) return { allowed: false, reason: "not-replay-safe" };
+      if (budget.used >= policy.maxTotalModelSends) return { allowed: false, reason: "total-exhausted" };
+
+      const changesTarget = lastTargetKey !== undefined && lastTargetKey !== intent.targetKey;
+      const isAlternateTarget = changesTarget || intent.sendClass === "account-failover"
+        || intent.sendClass === "combo-failover";
+      if (isAlternateTarget && changesTarget && targetTransitions >= policy.maxTargetTransitions) {
+        return { allowed: false, reason: "target-transition-exhausted" };
+      }
+      if (isAlternateTarget && alternateTargetSends >= policy.maxAlternateTargetSends) {
+        return { allowed: false, reason: "alternate-target-exhausted" };
+      }
+
+      // The base allowance is spent first. Only once it is gone does a recovery class reach
+      // for the single shared reserve -- an account move and a validated rebuild cannot each
+      // take one.
+      const drawsReserve = budget.remainingBaseSends(policy.baseSendAllowance) === 0;
+      if (drawsReserve) {
+        if (!RESERVE_FUNDED_CLASSES.has(intent.sendClass)) {
+          return { allowed: false, reason: "base-allowance-exhausted" };
+        }
+        if (reserveSpent || policy.finalRecoveryAllowance <= 0) {
+          return { allowed: false, reason: "final-recovery-spent" };
+        }
+      }
+
+      let consumed = false;
+      return {
+        allowed: true,
+        permit: {
+          sendClass: intent.sendClass,
+          use(): boolean {
+            if (consumed) return false;
+            consumed = true;
+            // Charged here, immediately before the physical send, rather than reported after
+            // the helper returns: a counter that is only reconciled afterwards cannot stop two
+            // concurrent legs that both read the same remainder.
+            if (intent.countedExternally !== true) budget.used += 1;
+            if (drawsReserve) reserveSpent = true;
+            if (isAlternateTarget) alternateTargetSends += 1;
+            if (changesTarget) targetTransitions += 1;
+            lastTargetKey = intent.targetKey;
+            return true;
+          },
+        },
+      };
+    },
+  };
+  if (lastTargetKey === undefined) lastTargetKey = undefined;
+  return budget;
+}
+
+export function isRequestExecutionBudget(
+  value: TransientSendBudget | undefined,
+): value is RequestExecutionBudget {
+  return typeof (value as RequestExecutionBudget | undefined)?.reserveDispatch === "function";
+}

package/src/lib/upstream-retry.ts

@@ -55,7 +55,63 @@ const RESET_RETRY_BASE_DELAY_MS = 150;
 const RESET_RETRY_MAX_DELAY_MS = 1_000;
 
 // Transient-5xx status retry layer (pre-stream only; devlog/_plan/260716_claudecode_hardening/010).
-const TRANSIENT_RETRY_MAX_ATTEMPTS = 3; // 1 initial + 2 retries
+/** Total sends one transient-retry helper call may make: 1 initial + 2 retries. */
+export const TRANSIENT_RETRY_MAX_ATTEMPTS = 3;
+
+/**
+ * Transient sends already spent by one LOGICAL request.
+ *
+ * A mutable holder rather than a counter local to one call frame, because the thing that has to
+ * share it spans frames: a combo parent runs a separate child turn per target, and a per-child
+ * counter is what let one logical request reach upstream three times per target (#4546).
+ */
+export interface TransientSendBudget {
+  used: number;
+}
+
+export function createTransientSendBudget(): TransientSendBudget {
+  return { used: 0 };
+}
+
+/**
+ * Refusal raised when a logical request has no send left (#4546, REQ-B04/B05).
+ *
+ * It is deliberately a distinct type rather than a generic `Error`: every call site that
+ * catches a helper rejection today launders it into HTTP 502 `upstream_error`, which would
+ * report a proxy-side budget decision as an upstream fault and hide the real 401/429 the
+ * request already had. Callers must recognise this and return the structured local error
+ * instead. It is a backstop, not the policy -- a call site that still holds a reusable
+ * upstream response is supposed to check the remainder BEFORE it cancels that body.
+ */
+export class SendBudgetExhaustedError extends Error {
+  readonly code = "request_send_budget_exhausted";
+  constructor(label?: string) {
+    super(label
+      ? `request send budget exhausted before dispatch (${label})`
+      : "request send budget exhausted before dispatch");
+    this.name = "SendBudgetExhaustedError";
+  }
+}
+
+/**
+ * Configuration refusal for an attempts value that is not a send count.
+ *
+ * `undefined` means "use the policy default" and `0` means "refuse". A negative, fractional,
+ * NaN or infinite value is a programming or configuration error, and silently substituting the
+ * default for it is how a broken budget turns back into three free sends.
+ */
+export class InvalidSendBudgetError extends Error {
+  constructor(value: unknown) {
+    super(`invalid upstream send budget: ${String(value)}`);
+    this.name = "InvalidSendBudgetError";
+  }
+}
+
+function normalizeSendAttempts(value: number | undefined, fallback: number): number {
+  if (value === undefined) return fallback;
+  if (!Number.isInteger(value) || value < 0) throw new InvalidSendBudgetError(value);
+  return value;
+}
 const TRANSIENT_RETRY_BASE_DELAY_MS = 400;
 const TRANSIENT_RETRY_MAX_DELAY_MS = 5_000;
 // A failed attempt slower than this is the "slow 502" incident shape (191s observed on
@@ -77,8 +133,19 @@ export interface RetryBackoffOptions {
   baseDelayMs: number;
   maxDelayMs: number;
   headers?: Headers;
+  /**
+   * Treat a provider's `Retry-After` as the earliest legal send rather than something the
+   * local maximum may shorten. Opt-in per caller so the change lands on the transient path
+   * first instead of silently lengthening every adapter's backoff.
+   */
+  retryAfterIsLowerBound?: boolean;
+  /** Hard ceiling for an honoured `Retry-After`, so an hour-long wait cannot park a request. */
+  retryAfterCeilingMs?: number;
 }
 
+/** One minute, matching the same-target 429 ceiling the key-failover path already uses. */
+export const RETRY_AFTER_CEILING_MS = 60_000;
+
 export function abortError(signal?: AbortSignal): unknown {
   return signal?.reason ?? new DOMException("The operation was aborted", "AbortError");
 }
@@ -228,9 +295,20 @@ function retryAfterDelayMs(headers: Headers): number | undefined {
 
 export function retryBackoffDelayMs(attempt: number, opts: RetryBackoffOptions): number {
   const retryAfter = opts.headers ? retryAfterDelayMs(opts.headers) : undefined;
-  if (retryAfter !== undefined) return Math.min(retryAfter, opts.maxDelayMs);
   const exp = Math.min(opts.baseDelayMs * (2 ** attempt), opts.maxDelayMs);
-  return Math.floor(exp * (0.8 + Math.random() * 0.4));
+  const jittered = Math.floor(exp * (0.8 + Math.random() * 0.4));
+  if (retryAfter === undefined) return jittered;
+  if (opts.retryAfterIsLowerBound !== true) {
+    // Historical behaviour, still the default for every caller that has not opted in.
+    return Math.min(retryAfter, opts.maxDelayMs);
+  }
+  // A provider that names a wait is stating when it will serve again; sending earlier is a
+  // request we already know will be refused, and refusing it twice is the retry storm the
+  // header exists to prevent. The local maximum bounds our OWN exponential backoff and has no
+  // business shortening someone else's instruction. The ceiling is separate: it stops an
+  // hour-long Retry-After from parking a request forever.
+  const ceiling = opts.retryAfterCeilingMs ?? RETRY_AFTER_CEILING_MS;
+  return Math.min(Math.max(retryAfter, jittered), ceiling);
 }
 
 export function cancelResponseBodyBestEffort(res: Response): void {
@@ -355,7 +433,11 @@ export async function fetchWithResetRetry(
   opts: ResetRetryOptions = {},
   firstRecovery?: UpstreamSendRecovery,
 ): Promise<Response> {
-  const attempts = Math.max(1, opts.attempts ?? RESET_RETRY_MAX_ATTEMPTS);
+  const attempts = normalizeSendAttempts(opts.attempts, RESET_RETRY_MAX_ATTEMPTS);
+  // Zero is zero. The old Math.max(1, ...) floor meant an exhausted budget still bought one
+  // more send on every recovery leg, which is most of what made a bounded per-layer retry
+  // compose into an unbounded per-request count.
+  if (attempts === 0) throw new SendBudgetExhaustedError(opts.label);
   let lastError: unknown;
   let sawReset = false;
   for (let attempt = 0; attempt < attempts; attempt++) {
@@ -401,7 +483,7 @@ export async function fetchWithTransientRetry(
   doFetch: ReplayableFetch,
   opts: TransientRetryOptions = {},
 ): Promise<Response> {
-  const budget = Math.max(1, opts.attempts ?? TRANSIENT_RETRY_MAX_ATTEMPTS);
+  const budget = normalizeSendAttempts(opts.attempts, TRANSIENT_RETRY_MAX_ATTEMPTS);
   const slowAttemptMs = opts.slowAttemptMs ?? TRANSIENT_RETRY_SLOW_ATTEMPT_MS;
   const transientStatuses: number[] = [];
   // `attempts` is ONE total-send budget shared with the inner reset layer, not a per-layer
@@ -418,13 +500,15 @@ export async function fetchWithTransientRetry(
     sent += 1;
     return doFetch(recovery);
   };
-  // Floor of 1 keeps the inner call legal once the budget is spent; the loop condition, not a
-  // zero-attempt inner call, is what actually stops the retries.
-  const remaining = () => Math.max(1, budget - sent);
+  // No floor. A spent budget hands the inner helper 0, which refuses rather than buying one
+  // more send -- the loop condition alone was never enough, because every later recovery leg
+  // called this helper again and the floor funded each of them.
+  const remaining = () => Math.max(0, budget - sent);
   // Reported in `finally` rather than at each exit: this function returns from five places
   // and throws from one, and a caller sharing the budget across request legs must be told the
   // real count on every one of them.
   try {
+  if (budget === 0) throw new SendBudgetExhaustedError(opts.label);
   let attemptStart = Date.now();
   let res = await fetchWithResetRetry(countedFetch, { ...opts, attempts: remaining() });
   for (let attempt = 0; sent < budget; attempt++) {
@@ -442,6 +526,7 @@ export async function fetchWithTransientRetry(
       baseDelayMs: TRANSIENT_RETRY_BASE_DELAY_MS,
       maxDelayMs: TRANSIENT_RETRY_MAX_DELAY_MS,
       headers: res.headers,
+      retryAfterIsLowerBound: true,
     });
     cancelResponseBodyBestEffort(res);
     // Throws on abort (see sleepWithAbort): the rejection propagates, and the body we just
@@ -454,6 +539,8 @@ export async function fetchWithTransientRetry(
     } catch (err) {
       // Keep the prior 5xx evidence attached: the origin already responded, so
       // this rejection is not pre-connection and must not classify as neutral.
+      // A budget refusal is not upstream evidence of anything and must stay recognisable.
+      if (err instanceof SendBudgetExhaustedError) throw err;
       throw new UpstreamRetryEvidenceError(transientStatuses, err);
     }
   }

package/src/lib/workflow-budget.ts

@@ -0,0 +1,172 @@
+/**
+ * Root-workflow admission: a finite budget above the logical request (#4546).
+ *
+ * The per-request send budget bounds how many times ONE request reaches upstream. It cannot
+ * bound how many requests a fan-out makes. A worker that spawns seven hundred children, each
+ * of which sends exactly once, never violates a per-request cap and still spends the account.
+ * That is the second half of the #4546 incident and it needs a ceiling of its own.
+ *
+ * The unit is the root workflow -- the user-visible task -- identified by the parent thread
+ * header when the client supplies one. A retry is not a new user task and gets no new
+ * allowance; a genuinely new top-level request does.
+ *
+ * This ledger is process-local and in-memory. It bounds a single proxy process honestly and
+ * says nothing about a second process sharing the same account pool; that needs a shared
+ * durable store and is declared out of scope rather than implied.
+ */
+
+export interface WorkflowBudgetPolicy {
+  /** Children admitted concurrently under one root. */
+  readonly maxConcurrentChildren: number;
+  /** Physical model sends charged to one root across its whole life. */
+  readonly maxPhysicalSends: number;
+  /** Distinct children one root may ever create. */
+  readonly maxDistinctChildren: number;
+  /**
+   * Concurrency slots a fan-out may never take. An interactive turn arriving into a saturated
+   * root still gets admitted; without this a worker burst starves the conversation it serves.
+   */
+  readonly interactiveReserve: number;
+  /** Roots tracked at once. Bounded so a caller minting new ids cannot grow this forever. */
+  readonly maxTrackedRoots: number;
+}
+
+export const DEFAULT_WORKFLOW_BUDGET_POLICY: WorkflowBudgetPolicy = {
+  maxConcurrentChildren: 8,
+  maxPhysicalSends: 256,
+  maxDistinctChildren: 64,
+  interactiveReserve: 1,
+  maxTrackedRoots: 512,
+};
+
+export type WorkflowDenial =
+  | "workflow-concurrency-exhausted"
+  | "workflow-sends-exhausted"
+  | "workflow-children-exhausted";
+
+export type WorkflowLane = "interactive" | "worker";
+
+export interface WorkflowAdmission {
+  readonly rootId: string;
+  release(): void;
+}
+
+export type WorkflowDecision =
+  | { admitted: true; lease: WorkflowAdmission }
+  | { admitted: false; reason: WorkflowDenial; rootId: string };
+
+interface WorkflowState {
+  active: number;
+  sends: number;
+  children: Set<string>;
+  lastSeenMs: number;
+}
+
+const roots = new Map<string, WorkflowState>();
+
+function pruneOldestRoot(): void {
+  let oldestKey: string | undefined;
+  let oldestAt = Number.POSITIVE_INFINITY;
+  for (const [key, state] of roots) {
+    // An active root is never evicted: dropping it would hand its fan-out a fresh allowance,
+    // which is the exact laundering this ledger exists to prevent.
+    if (state.active > 0) continue;
+    if (state.lastSeenMs < oldestAt) { oldestAt = state.lastSeenMs; oldestKey = key; }
+  }
+  if (oldestKey !== undefined) roots.delete(oldestKey);
+}
+
+/**
+ * Admit one turn under a root workflow.
+ *
+ * `childId` distinguishes the members of a fan-out; omit it for the root's own turns.
+ * An interactive lane may use the reserved slots a worker lane may not.
+ */
+export function admitWorkflowTurn(
+  rootId: string | undefined,
+  lane: WorkflowLane,
+  policy: WorkflowBudgetPolicy = DEFAULT_WORKFLOW_BUDGET_POLICY,
+  childId?: string,
+  now: number = Date.now(),
+): WorkflowDecision | undefined {
+  if (!rootId) return undefined;
+  let state = roots.get(rootId);
+  if (!state) {
+    if (roots.size >= policy.maxTrackedRoots) pruneOldestRoot();
+    state = { active: 0, sends: 0, children: new Set(), lastSeenMs: now };
+    roots.set(rootId, state);
+  }
+  state.lastSeenMs = now;
+
+  if (state.sends >= policy.maxPhysicalSends) {
+    return { admitted: false, reason: "workflow-sends-exhausted", rootId };
+  }
+  if (childId !== undefined && !state.children.has(childId)
+    && state.children.size >= policy.maxDistinctChildren) {
+    return { admitted: false, reason: "workflow-children-exhausted", rootId };
+  }
+  const ceiling = lane === "worker"
+    ? Math.max(0, policy.maxConcurrentChildren - policy.interactiveReserve)
+    : policy.maxConcurrentChildren;
+  if (state.active >= ceiling) {
+    return { admitted: false, reason: "workflow-concurrency-exhausted", rootId };
+  }
+
+  state.active += 1;
+  if (childId !== undefined) state.children.add(childId);
+  let released = false;
+  return {
+    admitted: true,
+    lease: {
+      rootId,
+      release(): void {
+        if (released) return;
+        released = true;
+        const current = roots.get(rootId);
+        if (!current) return;
+        current.active = Math.max(0, current.active - 1);
+        current.lastSeenMs = Date.now();
+      },
+    },
+  };
+}
+
+/**
+ * Charge physical sends to a root. Called from the send budget's own accounting so a retry
+ * inside one request counts toward the workflow total, not only the request total.
+ */
+export function chargeWorkflowSends(rootId: string | undefined, sends: number): void {
+  if (!rootId || sends <= 0) return;
+  const state = roots.get(rootId);
+  if (!state) return;
+  state.sends += sends;
+  state.lastSeenMs = Date.now();
+}
+
+/**
+ * Whether this root has already spent its whole physical-send ceiling.
+ *
+ * Separate from `admitWorkflowTurn` so a caller can refuse before dispatch without taking a
+ * concurrency slot it would have to remember to release.
+ */
+export function workflowSendCeilingReached(
+  rootId: string | undefined,
+  policy: WorkflowBudgetPolicy = DEFAULT_WORKFLOW_BUDGET_POLICY,
+): boolean {
+  if (!rootId) return false;
+  const state = roots.get(rootId);
+  return state !== undefined && state.sends >= policy.maxPhysicalSends;
+}
+
+export function workflowBudgetSnapshot(rootId: string): {
+
+  active: number; sends: number; children: number;
+} | undefined {
+  const state = roots.get(rootId);
+  return state ? { active: state.active, sends: state.sends, children: state.children.size } : undefined;
+}
+
+/** Test seam. Production never clears a live ledger: that would reset a spent budget. */
+export function resetWorkflowBudgetsForTest(): void {
+  roots.clear();
+}