feat(ai): add input-based pricing tiers

packages/coding-agent/CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Added
 
 - Added the opt-in `max` thinking level across CLI, SDK, RPC, model selection, and themes. Custom themes can define `thinkingMax`; existing themes fall back to `thinkingXhigh`.
+- Added request-wide input-token pricing tiers to custom model costs in `models.json`, `modelOverrides`, and extension-registered providers.
 
 ## [0.80.5] - 2026-07-09
 

packages/coding-agent/docs/models.md

@@ -205,9 +205,31 @@ If your command is slow, expensive, rate-limited, or should keep using a previou
 | `input` | No | `["text"]` | Input types: `["text"]` or `["text", "image"]` |
 | `contextWindow` | No | `128000` | Context window size in tokens |
 | `maxTokens` | No | `16384` | Maximum output tokens |
-| `cost` | No | all zeros | `{"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}` (per million tokens) |
+| `cost` | No | all zeros | Per-million-token rates with optional request-wide input pricing tiers |
 | `compat` | No | provider `compat` | Provider compatibility overrides. Merged with provider-level `compat` when both are set. |
 
+A cost tier supplies a complete alternate rate set and applies to the full request when total input usage (`input + cacheRead + cacheWrite`) exceeds `inputTokensAbove`. When multiple tiers match, the highest threshold wins.
+
+```json
+{
+  "cost": {
+    "input": 5,
+    "output": 30,
+    "cacheRead": 0.5,
+    "cacheWrite": 6.25,
+    "tiers": [
+      {
+        "inputTokensAbove": 272000,
+        "input": 10,
+        "output": 45,
+        "cacheRead": 1,
+        "cacheWrite": 12.5
+      }
+    ]
+  }
+}
+```
+
 Current behavior:
 - `/model`, `--list-models`, and the interactive footer display entries by model `id`.
 - The configured `name` is used for model matching and secondary model detail text. It does not replace the footer/status-bar model id.
@@ -317,6 +339,24 @@ Use `modelOverrides` to customize built-in models and matching extension-registe
 
 `modelOverrides` supports these fields per model: `name`, `reasoning`, `thinkingLevelMap`, `input`, `cost` (partial), `contextWindow`, `maxTokens`, `headers`, `compat`.
 
+Direct OpenAI GPT-5.6 Sol, Terra, and Luna default to a `272000` context window so requests remain within OpenAI's short-context pricing tier. To opt into OpenAI's 1.05M context window, increase it for each model you use:
+
+```json
+{
+  "providers": {
+    "openai": {
+      "modelOverrides": {
+        "gpt-5.6-sol": {
+          "contextWindow": 1050000
+        }
+      }
+    }
+  }
+}
+```
+
+The override preserves the built-in pricing metadata. Requests with more than 272K total input tokens use GPT-5.6's long-context rates for the entire request. Apply the same override to `gpt-5.6-terra` or `gpt-5.6-luna` when needed.
+
 Behavior notes:
 - `modelOverrides` are applied to built-in provider models and matching extension-registered provider models.
 - Unknown model IDs are ignored.

packages/coding-agent/src/core/extensions/types.ts

@@ -1451,8 +1451,8 @@ export interface ProviderModelConfig {
 	thinkingLevelMap?: Model<Api>["thinkingLevelMap"];
 	/** Supported input types. */
 	input: ("text" | "image")[];
-	/** Cost per token (for tracking, can be 0). */
-	cost: { input: number; output: number; cacheRead: number; cacheWrite: number };
+	/** Per-million-token cost rates and optional request-wide input pricing tiers. */
+	cost: Model<Api>["cost"];
 	/** Maximum context window size in tokens. */
 	contextWindow: number;
 	/** Maximum output tokens. */

packages/coding-agent/src/core/model-registry.ts

@@ -156,6 +156,21 @@ const ProviderCompatSchema = Type.Union([
 	AnthropicMessagesCompatSchema,
 ]);
 
+const ModelCostRatesSchema = {
+	input: Type.Number(),
+	output: Type.Number(),
+	cacheRead: Type.Number(),
+	cacheWrite: Type.Number(),
+};
+const ModelCostTierSchema = Type.Object({
+	inputTokensAbove: Type.Number(),
+	...ModelCostRatesSchema,
+});
+const ModelCostSchema = Type.Object({
+	...ModelCostRatesSchema,
+	tiers: Type.Optional(Type.Array(ModelCostTierSchema)),
+});
+
 // Schema for custom model definition
 // Most fields are optional with sensible defaults for local models (Ollama, LM Studio, etc.)
 const ModelDefinitionSchema = Type.Object({
@@ -166,14 +181,7 @@ const ModelDefinitionSchema = Type.Object({
 	reasoning: Type.Optional(Type.Boolean()),
 	thinkingLevelMap: Type.Optional(ThinkingLevelMapSchema),
 	input: Type.Optional(Type.Array(Type.Union([Type.Literal("text"), Type.Literal("image")]))),
-	cost: Type.Optional(
-		Type.Object({
-			input: Type.Number(),
-			output: Type.Number(),
-			cacheRead: Type.Number(),
-			cacheWrite: Type.Number(),
-		}),
-	),
+	cost: Type.Optional(ModelCostSchema),
 	contextWindow: Type.Optional(Type.Number()),
 	maxTokens: Type.Optional(Type.Number()),
 	headers: Type.Optional(Type.Record(Type.String(), Type.String())),
@@ -192,6 +200,7 @@ const ModelOverrideSchema = Type.Object({
 			output: Type.Optional(Type.Number()),
 			cacheRead: Type.Optional(Type.Number()),
 			cacheWrite: Type.Optional(Type.Number()),
+			tiers: Type.Optional(Type.Array(ModelCostTierSchema)),
 		}),
 	),
 	contextWindow: Type.Optional(Type.Number()),
@@ -335,6 +344,7 @@ function applyModelOverride(model: Model<Api>, override: ModelOverride): Model<A
 			output: override.cost.output ?? model.cost.output,
 			cacheRead: override.cost.cacheRead ?? model.cost.cacheRead,
 			cacheWrite: override.cost.cacheWrite ?? model.cost.cacheWrite,
+			tiers: override.cost.tiers ?? model.cost.tiers,
 		};
 	}
 
@@ -999,7 +1009,7 @@ export interface ProviderConfigInput {
 		reasoning: boolean;
 		thinkingLevelMap?: Model<Api>["thinkingLevelMap"];
 		input: ("text" | "image")[];
-		cost: { input: number; output: number; cacheRead: number; cacheWrite: number };
+		cost: Model<Api>["cost"];
 		contextWindow: number;
 		maxTokens: number;
 		headers?: Record<string, string>;

packages/coding-agent/test/extensions-runner.test.ts

@@ -49,7 +49,21 @@ describe("ExtensionRunner", () => {
 				name: "Instant Model",
 				reasoning: false,
 				input: ["text"],
-				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+				cost: {
+					input: 1,
+					output: 2,
+					cacheRead: 0.1,
+					cacheWrite: 1.25,
+					tiers: [
+						{
+							inputTokensAbove: 272000,
+							input: 2,
+							output: 3,
+							cacheRead: 0.2,
+							cacheWrite: 2.5,
+						},
+					],
+				},
 				contextWindow: 128000,
 				maxTokens: 4096,
 			},
@@ -859,7 +873,15 @@ describe("ExtensionRunner", () => {
 
 			runtime.registerProvider("instant-provider", providerModelConfig);
 			expect(runtime.pendingProviderRegistrations).toHaveLength(0);
-			expect(modelRegistry.find("instant-provider", "instant-model")).toBeDefined();
+			expect(modelRegistry.find("instant-provider", "instant-model")?.cost.tiers).toEqual([
+				{
+					inputTokensAbove: 272000,
+					input: 2,
+					output: 3,
+					cacheRead: 0.2,
+					cacheWrite: 2.5,
+				},
+			]);
 
 			runtime.unregisterProvider("instant-provider");
 			expect(modelRegistry.find("instant-provider", "instant-model")).toBeUndefined();