From 9b29206ba34bd268a1184049faa75ebb206d680c Mon Sep 17 00:00:00 2001
From: garrytan <garrytan@gmail.com>
Date: Sat, 31 Oct 2026 18:32:47 +0000
Subject: [PATCH] pricing: rows for claude-haiku-5-5, gpt-6-luna and
 gemini-4-argon (#3640)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
---
 lib/pricing.ts                 |  8 ++++++++
 test/pricing-eval-plan.test.ts | 17 +++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/lib/pricing.ts b/lib/pricing.ts
index 9d867e442..95c94598a 100644
--- a/lib/pricing.ts
+++ b/lib/pricing.ts
@@ -51,6 +51,9 @@ export const PRICING: Record<string, ModelPricing> = {
   // https://platform.claude.com/docs/en/about-claude/pricing (fetched 2026-10-12)
   'claude-sonnet-5-5':  { input_per_mtok: 2.00,  output_per_mtok: 10.00, cached_input_per_mtok: 0.10, as_of: '2026-10' },
   'claude-sonnet-4-6':  { input_per_mtok: 3.00,  output_per_mtok: 15.00, as_of: '2026-04' },
+  // https://platform.claude.com/docs/en/about-claude/pricing (fetched 2026-10-31; standard tier, prompts up to
+  // 100,000 tokens; the $0.50 / $2.50 / $0.05 rate above that is excluded like the other long-context surcharges)
+  'claude-haiku-5-5':   { input_per_mtok: 0.10,  output_per_mtok: 0.50,  cached_input_per_mtok: 0.01, as_of: '2026-10' },
   'claude-haiku-4-5':   { input_per_mtok: 1.00,  output_per_mtok: 5.00,  as_of: '2026-04' },
 
   // OpenAI (GPT + o-series)
@@ -58,6 +61,8 @@ export const PRICING: Record<string, ModelPricing> = {
   'gpt-6-astra':        { input_per_mtok: 10.00, output_per_mtok: 50.00, cached_input_per_mtok: 1.00, as_of: '2026-09' },
   // https://developers.openai.com/api/docs/models/gpt-6.1-sol (standard tier, up to 272K input)
   'gpt-6.1-sol':        { input_per_mtok: 2.00,  output_per_mtok: 10.00, cached_input_per_mtok: 0.10, as_of: '2026-10' },
+  // https://developers.openai.com/api/docs/models/gpt-6-luna (fetched 2026-10-31; standard tier, up to 272K input)
+  'gpt-6-luna':         { input_per_mtok: 0.10,  output_per_mtok: 0.50,  cached_input_per_mtok: 0.01, as_of: '2026-10' },
   'gpt-5.4':            { input_per_mtok: 2.50,  output_per_mtok: 10.00, as_of: '2026-04' },
   // https://developers.openai.com/api/docs/models/gpt-4o (fetched 2026-10-13; gbrain's LongMemEval judge, the official scorer's model;
   // the alias only: the gpt-4o-2024-05-13 snapshot has its own price)
@@ -67,6 +72,9 @@ export const PRICING: Record<string, ModelPricing> = {
   'o4-mini':            { input_per_mtok: 1.10,  output_per_mtok: 4.40,  as_of: '2026-04' },
 
   // Google
+  // https://ai.google.dev/gemini-api/docs/pricing (fetched 2026-10-31; the rates starting 2026-12-01, so estimates
+  // never under-price; through 2026-11-30 the page lists $2.00 / $10.00 / $0.10 cached; thinking tokens bill as output)
+  'gemini-4-argon':     { input_per_mtok: 4.00,  output_per_mtok: 20.00, cached_input_per_mtok: 0.20, as_of: '2026-10' },
   // https://ai.google.dev/gemini-api/docs/pricing (fetched 2026-10-12; standard tier through 2026-12-31,
   // the page lists $1.50 / $7.50 / $0.15 cached starting 2027-01-01)
   'gemini-3.8-flash':   { input_per_mtok: 0.75,  output_per_mtok: 3.75,  cached_input_per_mtok: 0.075, as_of: '2026-10' },
diff --git a/test/pricing-eval-plan.test.ts b/test/pricing-eval-plan.test.ts
index 8784d88a0..ae4f03a7f 100644
--- a/test/pricing-eval-plan.test.ts
+++ b/test/pricing-eval-plan.test.ts
@@ -41,6 +41,12 @@ describe('lib/pricing', () => {
   test('the default eval-arms tier (smart) is priced out of the box', () => {
     for (const model of ['claude-opus-5-5', 'gpt-6.1-sol']) expect(hasPricing(model)).toBe(true);
   });
+
+  test('claude-haiku-5-5, gpt-6-luna and gemini-4-argon are priced (#3640)', () => {
+    for (const model of ['claude-haiku-5-5', 'anthropic/claude-haiku-5-5', 'gpt-6-luna', 'openai/gpt-6-luna', 'gemini-4-argon']) expect(hasPricing(model)).toBe(true);
+    expect(estimateCostUsd({ input: 1_000_000, output: 1_000_000 }, 'claude-haiku-5-5')).toBe(0.6);
+    expect(estimateCostUsd({ input: 1_000_000, output: 1_000_000 }, 'gemini-4-argon')).toBe(24);
+  });
 });
 
 describe('preregistration', () => {
@@ -67,6 +73,17 @@ describe('arms', () => {
     const unpriced = resolveArms({ cwd: d, explicit: ['gpt-6-astra', 'made-up-model'] });
     expect(unpriced.errors.map(e => e.code)).toEqual(['EVAL_PRICE_MISSING']);
     expect(renderArms(unpriced, { input: 1000, output: 1000 })).toContain('price=MISSING');
+    const added = resolveArms({ cwd: d, explicit: ['claude-haiku-5-5', 'gpt-6-luna', 'gemini-4-argon'] });
+    expect(added.errors).toEqual([]);
+  });
+
+  test('a policy document naming a newly priced model yields that arm', () => {
+    const d = tmp();
+    const doc = path.join(d, 'MODELS.md');
+    fs.writeFileSync(doc, '- cheap arm: claude-haiku-5-5\n- strong arm: claude-opus-5-5\n');
+    const r = resolveArms({ cwd: d, policyDoc: doc, modelsCli: () => ({ code: 1, stdout: '' }) });
+    expect(r.errors).toEqual([]);
+    expect(r.arms.map(a => a.model).sort()).toEqual(['claude-haiku-5-5', 'claude-opus-5-5']);
   });
 
   test('the eval-arms role is read through the models CLI seam, never the network', () => {