loki-mode 11.2.2 → 11.3.1

package/loki-ts/data/model-pricing.json

@@ -1,32 +1,56 @@
 {
   "$schema_version": 1,
   "_comment": "Rolling pricing table consumed by loki-ts/src/runner/budget.ts. Update this file when Anthropic / OpenAI / others publish new prices; no code change required. Pricing is USD per 1 million tokens. Aliases (opus/sonnet/haiku) point to the latest model of that family per providers/model_catalog.json.",
-  "_updated": "2026-10-07",
-  "_source": "https://www.anthropic.com/pricing + provider docs. sonnet=claude-sonnet-5 and claude-sonnet-5-5, both $2/$10 per MTok (the Sonnet 5 intro price became the standard price; the 2026-09-01 increase to $3/$15 will not occur), cache write 5m $2.50, cache read $0.20, 1M context at standard pricing (platform.claude.com/docs/en/about-claude/pricing, read 2026-10-03). claude-haiku-5-5 (exact-id key; the haiku alias stays Haiku 4.5 at $1/$5): $0.10 in / $0.50 out / cache write 5m $0.125 / cache read $0.01 for prompts up to 100,000 tokens, and $0.50 / $2.50 / $0.625 / $0.05 over 100,000 tokens in over_100k (https://platform.claude.com/docs/en/about-claude/pricing, read 2026-10-07). opus=claude-opus-5. codex=gpt-5.3-codex standard tier. Cache tiers: read 0.1x input, write 1.25x input (Anthropic + OpenAI published multipliers).",
+  "_updated": "2026-10-08",
+  "_source": "https://platform.claude.com/docs/en/about-claude/pricing (docs.anthropic.com/en/docs/about-claude/pricing 301-redirects there), read 2026-10-08. Per MTok. fable=Claude Fable 5.1 $10/$50, cache read $0.25 (0.025x), 5m write $12.50, 1h write $20. opus=Claude Opus 5.5 $4/$20, cache read $0.20 (0.05x), 5m write $5, 1h write $8. sonnet=Claude Sonnet 5.5 $2/$10, cache read $0.10 (0.05x), 5m write $2.50, 1h write $4. haiku alias row prices as its catalog target claude-haiku-5-5 (providers/model_catalog.json cli_aliases), so it equals that row including over_100k; Haiku 4.5 ($1/$5) is no longer an alias target. claude-haiku-5-5 (exact id, same as the haiku alias): $0.10/$0.50, read $0.01, 5m $0.125, 1h $0.20 up to 100,000 prompt tokens; over_100k $0.50/$2.50, read $0.05, 5m $0.625, 1h $1. Fields: cache_write is the 5m write rate (legacy readers); cache_write_5m and cache_write_1h are the explicit tiers. Multipliers: 5m write 1.25x, 1h write 2x, read 0.1x (0.05x on Opus 5.5 and Sonnet 5.5, 0.025x on Fable 5.1). OpenAI rows (gpt-5.3-codex, gpt-5.6-sol/terra/luna): https://developers.openai.com/api/docs/pricing, read 2026-10-08, Standard tier, short context (up to 272K); cached input is the cache_read field; OpenAI bills no cache write, cache_write is a 1.25x placeholder.",
   "pricing": {
     "fable": {
       "input": 10.0,
       "output": 50.0,
-      "cache_read": 1.0,
-      "cache_write": 12.5
+      "cache_read": 0.25,
+      "cache_write": 12.5,
+      "cache_write_5m": 12.5,
+      "cache_write_1h": 20.0
     },
     "opus": {
-      "input": 5.0,
-      "output": 25.0,
-      "cache_read": 0.5,
-      "cache_write": 6.25
+      "input": 4.0,
+      "output": 20.0,
+      "cache_read": 0.2,
+      "cache_write": 5,
+      "cache_write_5m": 5,
+      "cache_write_1h": 8.0
     },
     "sonnet": {
       "input": 2.0,
       "output": 10.0,
-      "cache_read": 0.2,
-      "cache_write": 2.5
+      "cache_read": 0.1,
+      "cache_write": 2.5,
+      "cache_write_5m": 2.5,
+      "cache_write_1h": 4.0
     },
     "haiku": {
+      "input": 0.1,
+      "output": 0.5,
+      "cache_read": 0.01,
+      "cache_write": 0.125,
+      "over_100k": {
+        "input": 0.5,
+        "output": 2.5,
+        "cache_read": 0.05,
+        "cache_write": 0.625,
+        "cache_write_5m": 0.625,
+        "cache_write_1h": 1.0
+      },
+      "cache_write_5m": 0.125,
+      "cache_write_1h": 0.2
+    },
+    "claude-haiku-4-5": {
       "input": 1.0,
       "output": 5.0,
       "cache_read": 0.1,
-      "cache_write": 1.25
+      "cache_write": 1.25,
+      "cache_write_5m": 1.25,
+      "cache_write_1h": 2.0
     },
     "claude-haiku-5-5": {
       "input": 0.1,
@@ -37,8 +61,12 @@
         "input": 0.5,
         "output": 2.5,
         "cache_read": 0.05,
-        "cache_write": 0.625
-      }
+        "cache_write": 0.625,
+        "cache_write_5m": 0.625,
+        "cache_write_1h": 1.0
+      },
+      "cache_write_5m": 0.125,
+      "cache_write_1h": 0.2
     },
     "gpt-5.3-codex": {
       "input": 1.75,
@@ -47,22 +75,22 @@
       "cache_write": 2.1875
     },
     "gpt-5.6-sol": {
-      "input": 1.75,
-      "output": 14.0,
-      "cache_read": 0.175,
-      "cache_write": 2.1875
+      "input": 4.0,
+      "output": 20.0,
+      "cache_read": 0.4,
+      "cache_write": 5.0
     },
     "gpt-5.6-terra": {
-      "input": 0.6,
-      "output": 4.8,
-      "cache_read": 0.06,
-      "cache_write": 0.75
+      "input": 2.0,
+      "output": 12.0,
+      "cache_read": 0.2,
+      "cache_write": 2.5
     },
     "gpt-5.6-luna": {
-      "input": 0.15,
+      "input": 0.2,
       "output": 1.2,
-      "cache_read": 0.015,
-      "cache_write": 0.1875
+      "cache_read": 0.02,
+      "cache_write": 0.25
     }
   }
 }