llmshim 0.8.0__tar.gz → 0.9.0__tar.gz

{llmshim-0.8.0 → llmshim-0.9.0}/.github/workflows/release.yml

@@ -18,7 +18,7 @@ jobs:
       - name: Check formatting
         run: cargo fmt --all --check
       - name: Clippy
-        run: cargo clippy --workspace --features proxy -- -D warnings
+        run: cargo clippy --workspace --all-targets --features proxy -- -D warnings
       - name: Unit tests
         env:
           LLMSHIM_CATALOG_OFFLINE: '1'

{llmshim-0.8.0 → llmshim-0.9.0}/CLAUDE.md

@@ -16,7 +16,7 @@ This is a public crate on crates.io. Do NOT make breaking changes to `pub` items
 - **ChatGPT subscription (OAuth):** only `chatgpt/gpt-6-astra`, `chatgpt/gpt-5.6-sol`, `chatgpt/gpt-5.6-terra`, and `chatgpt/gpt-5.6-luna`. `CHATGPT_MODELS` in `src/models.rs` is shared by discovery, CLI selection, and validation; older/unlisted models fail before authentication or network calls.
 - **Anthropic:** `claude-fable-5-1`, `claude-opus-5`, `claude-sonnet-5`, `claude-haiku-4-5-20251001`
 - **Gemini:** `gemini-3.8-flash`, `gemini-3.5-flash-lite`
-- **xAI:** `grok-4.6`
+- **xAI:** `grok-4.7`
 - **OpenRouter:** not enumerated (huge/dynamic catalog) — any `openrouter/<vendor>/<model>` slug routes through, e.g. `openrouter/anthropic/claude-sonnet-5`.
 - **vLLM / SGLang:** not enumerated (self-hosted) — any `vllm/<served-model>` or `sglang/<served-model>` routes through to the configured server, e.g. `sglang/Qwen/Qwen3.6-35B-A3B-FP8`.
 
@@ -73,6 +73,30 @@ for whichever stream chunk carries usage; `log.rs`, `proxy::types::Usage`, both
 native facades and the four bundled clients carry it through as a nullable
 field. `null` means unknown, not free.
 
+**A provider-reported bill outranks the catalog.** Where a response carries
+`usage.cost` — OpenRouter returns it on every call, with no parameter to set —
+`stamp` uses that number and records `usage.cost_source: "provider"`;
+otherwise it prices from the catalog and records `"catalog"`. Measured
+2026-09-22 on `deepseek/deepseek-v4.1-flash`: the catalog's rate for the
+OpenRouter slug was half what OpenRouter billed, so the estimate this replaces
+was under-reporting 2:1. A catalog cannot detect that from the inside. The
+catalog product is an estimate of that bill and deliberately an upper bound, so
+it must never overwrite one. `cost_source` rides beside `cost_usd` everywhere
+it goes (`LogEntry`, `proxy::types::Usage`, OpenAPI, the typed clients).
+`shim::add_usage` sums a reported `cost` across a repair's two attempts, because
+two dispatches are two charges.
+
+`ModelInfo.context_cost_tiers` adds context-dependent standard rates without
+changing the public `Cost` struct. `cost_for_input_tokens` includes cached input
+in tier selection; `src/cost.rs` applies the resulting rates to the whole
+response. Local per-field prices outrank lower-source tier rates. Builtin
+launch metadata lives in `crates/llmshim-catalog/data/verified.json`, separate
+from the unmodified models.dev snapshot. Grok 4.7 live regression tests are in
+`tests/integration_grok_4_7.rs`; they use an ephemeral proxy port, configured
+keys, and billed API calls. `none` clamps to `low`; named tool choice must be
+flat on the Responses wire. Preserve encrypted reasoning on both normal and
+streaming tool round trips.
+
 `src/gateway/quota.rs` adds a per-identity dollar cap beside the RPM/TPM
 buckets: `budget_usd` + `budget_window_secs` on an `Identity`, checked before
 dispatch and charged after (cost is only knowable once a response exists, so
@@ -321,15 +345,15 @@ accounts exercise enforcement too. The provider handles incompatible
 thinking on a switch to older models; do not infer signatures from text.
 
 `tests/unit_fable.rs` pins these rules. Live checks for Fable 5, Fable 5.1,
-Opus 5, Gemini 3.8 Flash, and Grok 4.6:
+Opus 5, Gemini 3.8 Flash, and Grok 4.7:
 
 ```bash
 cargo test --features proxy --test integration_current_models -- --ignored --nocapture
 ```
 
 The live tests consume API usage and are ignored during offline preflight.
-Gemini 3.8 Flash and Opus 5 already had catalog/adapter support; Grok 4.6 is
-the verified xAI model ID. Keep the ChatGPT four-model allowlist independent.
+Gemini 3.8 Flash and Opus 5 already had catalog/adapter support; Grok 4.7 is
+the current xAI model ID (verified live 2026-09-21); retain Grok 4.6 for explicit routing. Keep the ChatGPT four-model allowlist independent.
 
 Two knobs work across every provider: `reasoning_effort` (`none|low|medium|high|xhigh|max`) and `reasoning_mode` (`standard|pro`). A third, `reasoning_summary` (`auto|none`), controls reasoning-text visibility → Anthropic `thinking.display` (`auto`→`summarized`, the default when `reasoning_effort` is present so newer models like Sonnet 5 / Opus 4.7-4.8 return reasoning text instead of the API-default `omitted`; `none`→`omitted` for lower latency). Applies to both the adaptive and pre-4.6 enabled thinking builders; a caller-supplied `thinking` block bypasses it. Each provider transform maps them to its native dialect, **clamping to the nearest tier the target model accepts** (all boundaries verified live — e.g. `max` is native on OpenAI gpt-5.6 and GPT-6 Astra; Anthropic 4.6 rejects `xhigh` but has `max`; Gemini's enum tops out at `high`; xAI grok-4.20 models reject any reasoning param). `mode: "pro"` is native on OpenAI gpt-5.6/-pro models (`reasoning.mode`), emulated as a one-tier effort bump elsewhere; explicit `none` always wins. Native passthrough (`x-openai.reasoning`, `x-anthropic.thinking`, `x-gemini.thinkingConfig`) bypasses the mapping entirely and always takes precedence. **Full per-provider mapping tables: `docs/src/guides/reasoning.md`** — update it and the pinning tests in `tests/unit_*.rs` together whenever a mapping changes.
 

{llmshim-0.8.0 → llmshim-0.9.0}/Cargo.lock

@@ -320,6 +320,17 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
+[[package]]
+name = "chacha20"
+version = "0.10.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65c35e4b699c7e15ccbe7ee35c005e4fc0a278d22238a2857e6ce2dadeda1b06"
+dependencies = [
+ "cfg-if",
+ "cpufeatures 0.3.1",
+ "rand_core 0.10.1",
+]
+
 [[package]]
 name = "chrono"
 version = "0.4.44"
@@ -377,15 +388,6 @@ version = "0.4.31"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "75984efb6ed102a0d42db99afb6c1948f0380d1d91808d5529916e6c08b49d8d"
 
-[[package]]
-name = "concurrent-queue"
-version = "2.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4ca0197aee26d1ae37445ee532fefce43251d24cc7c166799f4d46817f1d3973"
-dependencies = [
- "crossbeam-utils",
-]
-
 [[package]]
 name = "core-foundation"
 version = "0.10.1"
@@ -411,6 +413,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "cpufeatures"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ca28b0ae3115b884660db4118d803791fd6756b6e88f39c0f3f7859060d7566"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -420,12 +431,6 @@ dependencies = [
  "cfg-if",
 ]
 
-[[package]]
-name = "crossbeam-utils"
-version = "0.8.21"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
-
 [[package]]
 name = "crossterm"
 version = "0.28.1"
@@ -536,11 +541,10 @@ dependencies = [
 
 [[package]]
 name = "event-listener"
-version = "5.4.1"
+version = "5.4.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e13b66accf52311f30a0db42147dadea9850cb48cd070028831ae5f5d4b856ab"
+checksum = "5a23add41df1562121a9393cb065eab5146a1242410f23a644851e90cfd669d2"
 dependencies = [
- "concurrent-queue",
  "parking",
  "pin-project-lite",
 ]
@@ -783,15 +787,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "300e883d756b2e4ec94e02791f39b04b522276138852cfc41d9fb7e904106099"
 dependencies = [
  "cfg-if",
+ "js-sys",
  "libc",
  "r-efi 6.0.0",
+ "rand_core 0.10.1",
+ "wasm-bindgen",
 ]
 
 [[package]]
 name = "h2"
-version = "0.4.13"
+version = "0.4.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2f44da3a8150a6703ed5d34e164b875fd14c2cdab9af1252a9a1020bde2bdc54"
+checksum = "ef8e5e5a340588f4452631496976cf8636d4a7ecf600239fdc27615d2530bc16"
 dependencies = [
  "atomic-waker",
  "bytes",
@@ -1180,7 +1187,7 @@ checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
 
 [[package]]
 name = "llmshim"
-version = "0.8.0"
+version = "0.9.0"
 dependencies = [
  "async-stream",
  "async-trait",
@@ -1215,7 +1222,7 @@ dependencies = [
 
 [[package]]
 name = "llmshim-catalog"
-version = "0.1.0"
+version = "0.1.1"
 dependencies = [
  "chrono",
  "dirs",
@@ -1321,7 +1328,7 @@ dependencies = [
  "hyper-util",
  "log",
  "pin-project-lite",
- "rand",
+ "rand 0.9.5",
  "regex",
  "serde_json",
  "serde_urlencoded",
@@ -1543,14 +1550,15 @@ dependencies = [
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.13"
+version = "0.11.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f1906b49b0c3bc04b5fe5d86a77925ae6524a19b816ae38ce1e426255f1d8a31"
+checksum = "a9746dbde176634f4f2f1faf2404e30a31b2bc1e9cafb5329c95d8177a18c9fc"
 dependencies = [
  "bytes",
- "getrandom 0.3.4",
+ "getrandom 0.4.3",
  "lru-slab",
- "rand",
+ "rand 0.10.3",
+ "rand_pcg",
  "ring",
  "rustc-hash",
  "rustls",
@@ -1599,12 +1607,23 @@ checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
 
 [[package]]
 name = "rand"
-version = "0.9.2"
+version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
+checksum = "b9ef1d0d795eb7d84685bca4f72f3649f064e6641543d3a8c415898726a57b41"
 dependencies = [
  "rand_chacha",
- "rand_core",
+ "rand_core 0.9.5",
+]
+
+[[package]]
+name = "rand"
+version = "0.10.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65c9fb96cbc91e3478eaae79a69fcd3f1ae4ad052e471fe6732fff548984b4af"
+dependencies = [
+ "chacha20",
+ "getrandom 0.4.3",
+ "rand_core 0.10.1",
 ]
 
 [[package]]
@@ -1614,7 +1633,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
 dependencies = [
  "ppv-lite86",
- "rand_core",
+ "rand_core 0.9.5",
 ]
 
 [[package]]
@@ -1626,6 +1645,21 @@ dependencies = [
  "getrandom 0.3.4",
 ]
 
+[[package]]
+name = "rand_core"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "63b8176103e19a2643978565ca18b50549f6101881c443590420e4dc998a3c69"
+
+[[package]]
+name = "rand_pcg"
+version = "0.10.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "caa0f4137e1c0a72f4c651489402276c8e8e1cf081f3b0ba156d2cbeef09e86a"
+dependencies = [
+ "rand_core 0.10.1",
+]
+
 [[package]]
 name = "redis"
 version = "1.2.4"
@@ -1832,9 +1866,9 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.37"
+version = "0.23.45"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "758025cb5fccfd3bc2fd74708fd4682be41d99e5dff73c377c0646c6012c73a4"
+checksum = "0d41d731c7d2f962d1ccc364cec258de3c0e93b38c2fb3ba97ac74513048d634"
 dependencies = [
  "once_cell",
  "ring",
@@ -1868,9 +1902,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-webpki"
-version = "0.103.9"
+version = "0.103.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d7df23109aa6c1567d1c575b9952556388da57401e4ace1d15f79eedad0d8f53"
+checksum = "f3c3cf1d8b1e7d4927e2d154c3fcb02979afb9939629c62cd9048d4f07b60ac2"
 dependencies = [
  "ring",
  "rustls-pki-types",
@@ -2015,7 +2049,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
 dependencies = [
  "cfg-if",
- "cpufeatures",
+ "cpufeatures 0.2.17",
  "digest",
 ]
 

{llmshim-0.8.0 → llmshim-0.9.0}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "llmshim"
-version = "0.8.0"
+version = "0.9.0"
 edition = "2021"
 description = "Blazing fast LLM API translation layer in pure Rust"
 license = "MIT OR Apache-2.0"
@@ -24,7 +24,7 @@ gateway-redis = ["gateway", "redis-coordination"]
 redis-coordination = ["proxy", "dep:redis"]
 
 [dependencies]
-llmshim-catalog = { version = "0.1.0", path = "crates/llmshim-catalog" }
+llmshim-catalog = { version = "0.1.1", path = "crates/llmshim-catalog" }
 tokio = { version = "1", features = ["full"] }
 reqwest = { version = "0.12", default-features = false, features = ["json", "stream", "rustls-tls", "http2", "gzip", "brotli", "zstd", "deflate"] }
 serde = { version = "1", features = ["derive"] }

{llmshim-0.8.0 → llmshim-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: llmshim
-Version: 0.8.0
+Version: 0.9.0
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License

{llmshim-0.8.0 → llmshim-0.9.0}/README.md

@@ -88,6 +88,20 @@ OpenRouter is OpenAI Chat Completions-compatible, so tools, vision, streaming,
 and `reasoning_effort` all pass through; OpenRouter-only controls (provider
 routing, model fallbacks, transforms) go under an `x-openrouter` key.
 
+OpenRouter also reports **what it actually charged**, on every call and with no
+parameter to set. llmshim keeps it: the response carries `usage.cost_usd` with
+`usage.cost_source: "provider"` — the bill, not a catalog estimate — alongside
+`usage.cost_details` and `usage.is_byok`. On a stream it rides on the terminal
+chunk. Because OpenRouter is an aggregator, the response's top-level
+**`provider`** names the upstream that actually served the call (`"Together"`,
+`"Fireworks"`, …) and `id` is the OpenRouter generation id; both survive the
+streaming and buffered paths.
+
+This matters more than a rounding difference. Measured on
+`deepseek/deepseek-v4.1-flash`, the catalog's own rate for the OpenRouter slug
+was **half** what OpenRouter actually billed, so the estimate it replaces was
+under-reporting 2:1.
+
 Point at a **self-hosted vLLM or SGLang** server (local or remote) by setting its
 base URL — no key needed unless the server was launched with one:
 
@@ -473,7 +487,7 @@ Standard library only. Full docs: [`clients/ruby/README.md`](clients/ruby/README
 | **OpenAI** | `gpt-6-astra`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` | Yes (summaries) |
 | **Anthropic** | `claude-fable-5-1`, `claude-opus-5`, `claude-sonnet-5`, `claude-haiku-4-5-20251001` | Yes (thinking summaries) |
 | **Google Gemini** | `gemini-3.8-flash`, `gemini-3.5-flash-lite` | Yes (thought summaries) |
-| **xAI** | `grok-4.6` | No (hidden) |
+| **xAI** | `grok-4.7` | No (hidden) |
 
 The CLI and server advertise these current tiers. ChatGPT subscription access
 uses the same four OpenAI models under `chatgpt/`. OpenRouter and self-hosted

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "llmshim-catalog"
-version = "0.1.0"
+version = "0.1.1"
 edition = "2021"
 description = "Offline-first model metadata with verified defaults, models.dev, and local overrides"
 license = "MIT OR Apache-2.0"

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/README.md

@@ -18,9 +18,31 @@ input/output modalities, knowledge/release dates, and field-level sources.
 Missing data remains unknown. A date given only as a month is not turned into
 an invented day. Unknown family keys remain absent and must not authorize replay.
 
+`ModelInfo::cost_for_input_tokens(total)` selects context-dependent rates from
+`context_cost_tiers`; `cost` remains the base rates. The total includes cached
+input. A tier applies to the entire request strictly above its threshold, with
+missing rates inherited from the preceding tier. Models.dev `cost.tiers` entries
+whose type is `context` are imported. Local policy can set
+`context_cost_tiers = []` to disable inherited tiers, or use:
+
+```toml
+[[models."xai/grok-4.7".context_cost_tiers]]
+above_input_tokens = 200000
+[models."xai/grok-4.7".context_cost_tiers.cost]
+input = 4.0
+cache_read = 1.0
+output = 12.0
+```
+
+The strongest source replaces the tier list as a whole. Higher-priority base
+price overrides still win per field over lower-priority tier rates. Provider
+discovery cannot supply either base prices or tiers.
+
 The compiled `builtin` module retains the small verified discovery table,
 historical metadata, and the separate ChatGPT subscription allowlist. Catalog
 coverage does not authorize or configure an API route or a subscription model.
+`data/verified.json` supplies sourced launch metadata independently of the
+models.dev snapshot. It does not add models to the curated discovery list.
 
 ## Layers and policy
 

llmshim-0.9.0/crates/llmshim-catalog/data/README.md

@@ -0,0 +1,26 @@
+`models.dev.json` is the unmodified response downloaded from
+https://models.dev/api.json on 2026-09-16. It is third-party data under the MIT
+license in `LICENSE.models.dev`. No credentials, local overrides, provider
+account discovery, or private fixtures belong in this directory.
+
+The refresh workflow replaces only this public snapshot. Tests validate its
+structure and minimum coverage before proposing an update. The builtin table
+continues to win conflicts for the fields it asserts.
+
+`verified.json` contains separate verified builtin assertions, checked on
+2026-09-21. It is maintained here, not copied into the models.dev artifact:
+
+- Native Grok 4.7 capabilities, reasoning efforts, dates, and standard token
+  prices: https://docs.x.ai/developers/grok-4-7 and
+  https://docs.x.ai/developers/release-notes (including Grok 4.6 context pricing).
+- Grok 4.7 streaming, image input, structured output, named tool selection,
+  and encrypted-reasoning round trips: `tests/integration_grok_4_7.rs` in the
+  parent repository, verified against the live xAI Responses API.
+- OpenRouter's Grok 4.7 identity, capabilities, limits and standard endpoint
+  prices: https://openrouter.ai/api/v1/models/x-ai/grok-4.7/endpoints . Priority
+  endpoint rates are different; the catalog entries describe standard rates.
+  The `:nitro` entry supplies replay metadata without a fixed price because
+  standard and priority endpoints can compete for that route.
+
+No public `grok-4.7-fast` API route is asserted. Its launch availability is
+limited to Cursor and Grok Build.

llmshim-0.9.0/crates/llmshim-catalog/data/verified.json

@@ -0,0 +1,43 @@
+{
+  "xai/grok-4.7": {
+    "name": "Grok 4.7",
+    "family": "grok",
+    "limit": {"context": 500000},
+    "release_date": "2026-09-21",
+    "modalities": {"input": ["text", "image"], "output": ["text"]},
+    "reasoning_options": [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}],
+    "streaming": true,
+    "forced_tool_choice": true,
+    "cost": {"input": 2, "cache_read": 0.5, "output": 6},
+    "context_cost_tiers": [{"above_input_tokens": 200000, "cost": {"input": 4, "cache_read": 1, "output": 12}}]
+  },
+  "xai/grok-4.6": {
+    "cost": {"input": 2, "cache_read": 0.5, "output": 6},
+    "context_cost_tiers": [{"above_input_tokens": 200000, "cost": {"input": 4, "cache_read": 1, "output": 12}}]
+  },
+  "openrouter/x-ai/grok-4.7:nitro": {
+    "name": "Grok 4.7 (Nitro)",
+    "family": "grok",
+    "limit": {"context": 500000, "output": 450000},
+    "modalities": {"input": ["text", "image", "file"], "output": ["text"]},
+    "reasoning_options": [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}],
+    "reasoning": true,
+    "tool_call": true,
+    "structured_output": true,
+    "forced_tool_choice": true
+  },
+  "openrouter/x-ai/grok-4.7": {
+    "name": "Grok 4.7",
+    "family": "grok",
+    "limit": {"context": 500000, "output": 450000},
+    "release_date": "2026-09-21",
+    "modalities": {"input": ["text", "image", "file"], "output": ["text"]},
+    "reasoning_options": [{"type": "effort", "values": ["low", "medium", "high", "xhigh"]}],
+    "reasoning": true,
+    "tool_call": true,
+    "structured_output": true,
+    "forced_tool_choice": true,
+    "cost": {"input": 1.6, "cache_read": 0.4, "output": 4.8},
+    "context_cost_tiers": [{"above_input_tokens": 200000, "cost": {"input": 3.2, "cache_read": 0.8, "output": 9.6}}]
+  }
+}

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/src/builtin.rs

@@ -261,11 +261,11 @@ pub const MODELS: &[BuiltinModelInfo] = &[
         capabilities: CAPS_STD,
     },
     BuiltinModelInfo {
-        id: "xai/grok-4.6",
+        id: "xai/grok-4.7",
         provider: "xai",
         family: Some(ModelFamily::Grok),
-        name: "grok-4.6",
-        label: "Grok 4.6",
+        name: "grok-4.7",
+        label: "Grok 4.7",
         context_window_tokens: Some(500_000),
         max_output_tokens: None,
         capabilities: CAPS_XAI,
@@ -279,6 +279,16 @@ pub const MODELS: &[BuiltinModelInfo] = &[
 /// Historical metadata remains available to explicit `spec()` lookups without
 /// appearing in discovery or model pickers. Routing is provider-owned.
 const LEGACY_MODELS: &[BuiltinModelInfo] = &[
+    BuiltinModelInfo {
+        id: "xai/grok-4.6",
+        provider: "xai",
+        family: Some(ModelFamily::Grok),
+        name: "grok-4.6",
+        label: "Grok 4.6",
+        context_window_tokens: Some(500_000),
+        max_output_tokens: None,
+        capabilities: CAPS_XAI,
+    },
     BuiltinModelInfo {
         id: "openai/gpt-5.5",
         provider: "openai",

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/src/lib.rs

@@ -165,6 +165,20 @@ impl Catalog {
             model.source = CatalogSource::Builtin;
             self.merge_model(model);
         }
+        // Verified launch-day metadata is separate from the unmodified
+        // models.dev snapshot and does not expand curated discovery.
+        let entries: Value = serde_json::from_str(include_str!("../data/verified.json"))
+            .expect("validated builtin metadata");
+        for (id, value) in entries.as_object().expect("builtin metadata object") {
+            let (provider, name) = id.split_once('/').expect("qualified builtin id");
+            self.merge_model(parse::model_from_value(
+                provider,
+                name,
+                value,
+                CatalogSource::Builtin,
+                None,
+            ));
+        }
     }
 
     pub fn merge_models_dev(
@@ -235,6 +249,9 @@ impl Catalog {
                     ))?;
                 let mut model =
                     parse::model_from_value(provider, name, v, CatalogSource::Local, None);
+                if v.get("context_cost_tiers").is_some() && model.context_cost_tiers.is_none() {
+                    return Err(CatalogError::Invalid("invalid context_cost_tiers"));
+                }
                 if let Some(label) = v["label"].as_str() {
                     model.label = label.into();
                 }

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/src/merge.rs

@@ -1,6 +1,6 @@
 use crate::{CatalogSource, Cost, ModelInfo, Support};
 
-fn rank(source: CatalogSource) -> u8 {
+pub(crate) fn rank(source: CatalogSource) -> u8 {
     match source {
         CatalogSource::ModelsDev => 1,
         CatalogSource::Builtin => 2,
@@ -76,6 +76,7 @@ pub(crate) fn merge(target: &mut ModelInfo, incoming: &ModelInfo) {
         }
     }
     if source != CatalogSource::ProviderApi {
+        field!(context_cost_tiers, incoming.context_cost_tiers.is_some());
         if let Some(cost) = incoming.cost {
             let mut merged = target.cost.unwrap_or_default();
             for (key, value, slot) in [

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/src/parse.rs

@@ -1,5 +1,6 @@
 use crate::{
-    CatalogError, CatalogSource, Cost, ModelCapabilities, ModelFamily, ModelInfo, Support,
+    CatalogError, CatalogSource, ContextCostTier, Cost, ModelCapabilities, ModelFamily, ModelInfo,
+    Support,
 };
 use chrono::{DateTime, NaiveDate, Utc};
 use serde_json::Value;
@@ -77,6 +78,24 @@ pub(crate) fn model_from_value(
         };
     }
     m.cost = cost(&v["cost"]);
+    m.context_cost_tiers = if let Some(tiers) = v.get("context_cost_tiers") {
+        serde_json::from_value(tiers.clone()).ok()
+    } else {
+        v["cost"]["tiers"].as_array().map(|tiers| {
+            tiers
+                .iter()
+                .filter_map(|tier| {
+                    if tier["tier"]["type"] != "context" {
+                        return None;
+                    }
+                    Some(ContextCostTier {
+                        above_input_tokens: tier["tier"]["size"].as_u64()?,
+                        cost: cost(tier)?,
+                    })
+                })
+                .collect()
+        })
+    };
     m.reasoning_options = v["reasoning_options"]
         .as_array()
         .into_iter()

{llmshim-0.8.0 → llmshim-0.9.0}/crates/llmshim-catalog/src/types.rs

@@ -81,6 +81,14 @@ pub struct Cost {
     pub cache_write: Option<f64>,
 }
 
+/// Rates for the entire request when total input (including cached input)
+/// exceeds `above_input_tokens`. Missing rates inherit the previous tier.
+#[derive(Debug, Clone, Copy, PartialEq, Serialize, Deserialize)]
+pub struct ContextCostTier {
+    pub above_input_tokens: u64,
+    pub cost: Cost,
+}
+
 /// Media types are strings so new catalog modalities survive without a release.
 #[derive(Debug, Clone, PartialEq, Eq, Default, Serialize, Deserialize)]
 #[serde(default)]
@@ -123,6 +131,9 @@ pub struct ModelInfo {
     pub capabilities: crate::ModelCapabilities,
     pub family: Option<ModelFamily>,
     pub cost: Option<Cost>,
+    /// None means unspecified; an explicit empty list disables inherited tiers.
+    #[serde(default)]
+    pub context_cost_tiers: Option<Vec<ContextCostTier>>,
     pub reasoning_options: Vec<ReasoningOption>,
     pub modalities: Modalities,
     pub knowledge_cutoff: Option<NaiveDate>,
@@ -148,6 +159,7 @@ impl ModelInfo {
             capabilities: crate::ModelCapabilities::unknown(),
             family: None,
             cost: None,
+            context_cost_tiers: None,
             reasoning_options: Vec::new(),
             modalities: Modalities::default(),
             knowledge_cutoff: None,
@@ -158,4 +170,48 @@ impl ModelInfo {
             field_sources: BTreeMap::new(),
         }
     }
+
+    /// Resolve context-dependent rates without changing the base `Cost` API.
+    /// Higher-priority per-field base overrides also override lower-priority
+    /// tier rates. Tier lists are replaced atomically by a stronger source.
+    pub fn cost_for_input_tokens(&self, input_tokens: u64) -> Option<Cost> {
+        let mut cost = self.cost?;
+        let mut tiers: Vec<_> = self
+            .context_cost_tiers
+            .as_deref()
+            .unwrap_or_default()
+            .iter()
+            .filter(|t| input_tokens > t.above_input_tokens)
+            .collect();
+        tiers.sort_by_key(|t| t.above_input_tokens);
+        let tier_source = self
+            .field_sources
+            .get("context_cost_tiers")
+            .copied()
+            .unwrap_or(self.source);
+        for tier in tiers {
+            for (key, rate, slot) in [
+                ("cost.input", tier.cost.input, &mut cost.input),
+                ("cost.output", tier.cost.output, &mut cost.output),
+                (
+                    "cost.cache_read",
+                    tier.cost.cache_read,
+                    &mut cost.cache_read,
+                ),
+                (
+                    "cost.cache_write",
+                    tier.cost.cache_write,
+                    &mut cost.cache_write,
+                ),
+            ] {
+                let base_source = self.field_sources.get(key).copied().unwrap_or(self.source);
+                if rate.is_some_and(|n| n.is_finite() && n >= 0.0)
+                    && crate::merge::rank(tier_source) >= crate::merge::rank(base_source)
+                {
+                    *slot = rate;
+                }
+            }
+        }
+        Some(cost)
+    }
 }