Self-improving AI Employees for everyone
Python ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
chore(models): refresh the OpenRouter registry and sync the curated catalogue
trohitge76dcca0c48b
diff --git a/docs-internal/native_llm_sdk.md b/docs-internal/native_llm_sdk.mdindex 8779f4b4..5c4b9b0e 100644--- a/docs-internal/native_llm_sdk.md+++ b/docs-internal/native_llm_sdk.md@@ -107,13 +107,13 @@ The curated lists and figures in `llm_defaults.json` and `pricing.json` take the|----------|-----------|---------|-----------|----------|------------|| **OpenAI** | GPT-6 Sol/Luna/Astra (+ `-pro`; default `gpt-6-sol`), GPT-5.6 Sol/Terra/Luna (+ `-pro`), GPT-5.5/5.4 | 1.05M | 128K | effort | omitted for reasoning models || **OpenAI** | GPT-4.1 | ~1.05M | 32K | none | 0-2 |-| **Anthropic** | Claude Opus 5.5 (default `claude-opus-5-5`), Opus 5, Fable 5.1 / 5, Sonnet 5 | 1M | 128K | adaptive | omitted (`temperature` / `top_p` / `top_k` rejected — `sampling_params_removed`) |+| **Anthropic** | Claude Opus 5.5 (default `claude-opus-5-5`), Opus 5, Fable 5.1 / 5, Sonnet 5.5 / 5 | 1M | 128K | adaptive | omitted (`temperature` / `top_p` / `top_k` rejected — `sampling_params_removed`) || **Anthropic** | Claude Opus 4.8/4.7 | 1M | 128K | adaptive | omitted (`sampling_params_removed`) || **Anthropic** | Claude Sonnet 4.6 | 1M | 128K | budget | 0-1 || **Anthropic** | Claude Haiku 4.5 | 200K | 64K | budget | 0-1 || **Google** | Gemini 3.8-flash (default), 3.7/3.6/3.5-flash, 3.5-flash-lite, 3.1-pro-preview/flash-lite, 3-flash-preview, 2.5-pro/flash/flash-lite | 1M | 64K | budget (`thinking_level` on 3.x when set explicitly) | 0-2 || **xAI** | Grok 4.20/4.20-multi-agent, 4.3, 4.7, 4.6, 4.5 | 500K-2M | 450K-1.8M | model/provider dependent | 0-2 |-| **DeepSeek** | deepseek-v4.1-flash (default), deepseek-v4-pro, deepseek-v4-flash | 1M | 131K (V4.1 Flash); 384K | thinking modes | 0-2 |+| **DeepSeek** | deepseek-v4.1-flash (default), deepseek-v4-pro, deepseek-v4-flash | 1M | ~944K (V4.1 Flash); 384K (V4 Pro); 131K (V4 Flash) | thinking modes | 0-2 || **Kimi** | kimi-k3 (default), kimi-k2.6, kimi-k2.7-code (+ `-highspeed`) | 1M (K3); 256K (K2) | 131K (K3); 32K/96K (K2) | K2 provider default explicitly disabled unless requested | K2 fixed 0.6; K3 0-1 || **Mistral** | mistral-large/medium/small-latest (Large 3 / Medium 3.5 / Small 4), codestral-latest | 256K | 32K-131K | none | 0-1.5 || **Groq** | GPT-OSS-120b/20b, Llama 3.x tiers, qwen3.8-27b + minimax-m2.7 (preview) | 131K-196K | 16K-131K | effort (GPT-OSS), format (Qwen3) | 0-2 |@@ -354,7 +354,7 @@ Each provider's `chat()` method reads only the fields it supports. The extracted| Provider | Models | Parameter | Thinking Type | Notes ||----------|--------|-----------|---------------|-------|-| **Claude** (adaptive) | `claude-opus-5*`, `claude-fable-5*`, `claude-mythos-5`, `claude-sonnet-5`, `claude-opus-4-8`, `claude-opus-4-7` (`adaptive_thinking_models`, prefix-matched) | `thinkingEnabled` only — the budget is ignored | adaptive | Sends `{"type":"adaptive","display":"summarized"}` when enabled; when disabled the field is omitted (`disabled` is itself rejected on Fable/Mythos). `budget_tokens` is a 400 on these generations. No `temperature` / `top_p` / `top_k` is sent at all (`sampling_params_removed`). `anthropic.py:72-92`. |+| **Claude** (adaptive) | `claude-opus-5*`, `claude-fable-5*`, `claude-mythos-5`, `claude-sonnet-5*`, `claude-opus-4-8`, `claude-opus-4-7` (`adaptive_thinking_models`, prefix-matched) | `thinkingEnabled` only — the budget is ignored | adaptive | Sends `{"type":"adaptive","display":"summarized"}` when enabled; when disabled the field is omitted (`disabled` is itself rejected on Fable/Mythos). `budget_tokens` is a 400 on these generations. No `temperature` / `top_p` / `top_k` is sent at all (`sampling_params_removed`). `anthropic.py:72-92`. || **Claude** (budget) | `claude-sonnet-4-6`, `claude-haiku-4-5` and older 4.x/3.5 | `thinkingBudget` (1024-16000 tokens) | budget | `{"type":"enabled","budget_tokens":N}`; provider bumps `max_tokens` to `budget + 1024` if it is not already larger. Temperature auto-set to 1. || **Gemini** | gemini-3.x, gemini-2.5-pro/flash | `thinkingBudget` (token count); `thinkingLevel` on 3.x when set explicitly | budget | Uses `thinking_budget` API parameter (`thinking_level` only when the user set it — Vertex rejects an unsolicited level on 2.5-era models) || **OpenAI** | `o3`, `o4-mini` (reasoning-only; both on the API-shutdown path per `_models_note`, `o1`/`o3`/`o4` prefixes still detected) | `reasoningEffort` (low/medium/high) | effort | Reasoning-only models. Temperature omitted. |diff --git a/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md b/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.mdindex ce983c67..ca6e9442 100644--- a/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md+++ b/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md@@ -99,7 +99,7 @@ flowchart TD- **`thinkingEnabled=false` does not suppress a trace**: it only means the UI will not highlight one. If the model returns `reasoning_content`, the response still carries it.- **`thinkingBudget` has no effect**: DeepSeek reasoning is not budget-configurable; the field is silently ignored.-- **Context and output**: all three curated models have a 1,048,576-token context window. The output ceiling is 131,072 tokens for `deepseek-v4.1-flash` and 384,000 for `deepseek-v4-pro` and `deepseek-v4-flash` (OpenRouter snapshot, 2026-09-26).+- **Context and output**: all three curated models have a 1,048,576-token context window. The output ceiling is 943,718 tokens for `deepseek-v4.1-flash`, 384,000 for `deepseek-v4-pro` and 131,072 for `deepseek-v4-flash` (OpenRouter snapshot, 2026-09-29). A node that leaves `max_tokens` unset requests the whole ceiling (`resolve_max_tokens`).- **OpenAI-compatible but not OpenAI**: features like `response_format: json_object` have subtly different behavior.- **Error boundary**: typed OpenAI SDK failures become user-safe `NodeUserError` values in `ChatUnifier` and are re-raised to `BaseNode.execute()`, which produces the standard failure envelope. Unexpected failures are logged and returned by `execute_chat`.diff --git a/server/config/llm_defaults.json b/server/config/llm_defaults.jsonindex f8ea696c..d206a6b8 100644--- a/server/config/llm_defaults.json+++ b/server/config/llm_defaults.json@@ -1,6 +1,6 @@{- "version": "2026.09.26",- "last_updated": "2026-09-26",+ "version": "2026.09.29",+ "last_updated": "2026-09-29","_description": "LLM provider defaults. popular_models drives the ordered global selector and offline fallback independently of token constraints. POLICY (2026-07-23): popular_models lists only models with >= 1M-token context windows — providers whose models are all below 1M carry an empty list and contribute nothing to the global selector (their models stay reachable via the live per-provider fetch_models dropdown). SOURCE (2026-09-26): model_registry.json, the OpenRouter snapshot, is the ground truth for the curated ids, context, max output and prices of every provider whose models it lists; an id it does not list is not curated (Mistral's -latest aliases excepted, see its note). It carries nothing for the hosts (groq, cerebras, sarvam), which keep their own documented values. base_url directly configures the nine OpenAI-compatible native providers; dedicated OpenAI, Anthropic, and Gemini providers use SDK defaults, while OpenRouter has its own gateway default. Runtime proxy credentials can override supported endpoints. Model specs are enriched by model_registry.json at runtime; kimi and mistral are the exception, because the registry files their models under moonshotai/ and mistralai/, so their maps here are what requests use.","agent": {@@ -26,7 +26,7 @@"enabled": false,"_note": "Native image input is emitted only when enabled is true; unknown/absent providers get a text placeholder instead (a rejected image block would poison journaled history). Read by services/llm/media.py provider_supports_vision. False here until the OpenAI request encoder renders image blocks (Responses input_image in function_call_output; Chat Completions hoist-to-user-turn) — flipping it early would hydrate bytes the encoder silently drops. Anthropic ships the first encoder; text-only providers keep the visionAnalyze delegate tool."},- "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-26). GPT-6 is the current generation: gpt-6-sol is the default ($2/$10 per MTok), gpt-6-luna the low tier ($0.10/$0.50) and gpt-6-astra the flagship ($10/$50); all have 1.05M context and 128K max output, and each -pro variant is priced like its base model. GPT-6 has no Terra model, so gpt-5.6-terra ($2/$12) stays the middle tier; the rest of the GPT-5.6 family, gpt-5.5, gpt-5.4 and gpt-4.1 stay curated as earlier tiers. The rolling -latest aliases (gpt-astra-latest, gpt-sol-latest, gpt-terra-latest, gpt-luna-latest) are deliberately not curated: real model names only, like gemini. gpt-5.2, o3 and o4-mini are not curated because OpenAI is retiring them; the registry still describes them, so their limits resolve from it.",+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-29). GPT-6 is the current generation: gpt-6-sol is the default ($2/$10 per MTok), gpt-6-luna the low tier ($0.10/$0.50) and gpt-6-astra the flagship ($10/$50); all have 1.05M context and 128K max output, and each -pro variant is priced like its base model. GPT-6 has no Terra model, so gpt-5.6-terra ($2/$12) stays the middle tier; the rest of the GPT-5.6 family, gpt-5.5, gpt-5.4 and gpt-4.1 stay curated as earlier tiers (unlike GPT-6, gpt-5.6-sol-pro costs twice its base: $4/$20). The rolling -latest aliases (gpt-astra-latest, gpt-sol-latest, gpt-terra-latest, gpt-luna-latest) are deliberately not curated: real model names only, like gemini. gpt-5.2, o3 and o4-mini are not curated because OpenAI is retiring them; the registry still describes them, so their limits resolve from it.","max_output_tokens": {"gpt-6-sol": 128000,"gpt-6-astra": 128000,@@ -71,8 +71,8 @@"anthropic": {"display_name": "Anthropic","default_model": "claude-opus-5-5",- "popular_models": ["claude-opus-5-5", "claude-fable-5-1", "claude-fable-5", "claude-opus-5", "claude-sonnet-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],- "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-26), which gives every curated Claude model 1,000,000 tokens of context and 128K max output (Haiku 4.5: 200K and 64K). claude-opus-5-5 is the default: the newest Opus, at $4/$20 per MTok, below claude-opus-5 ($5/$25), which stays curated. claude-fable-5-1 ($10/$50) is the top tier and supersedes claude-fable-5 (same price), also still curated; claude-sonnet-5 is $2/$10. Ids use Anthropic's hyphenated form; the registry's dotted ids (claude-opus-5.5) match them through ModelRegistryService's dot/hyphen variants. The adaptive-thinking / sampling-removed lists below match by prefix, so the claude-opus-5 and claude-fable-5 entries cover 5.5 and 5.1. claude-opus-5-fast is not a registry model and is not curated.",+ "popular_models": ["claude-opus-5-5", "claude-fable-5-1", "claude-fable-5", "claude-opus-5", "claude-sonnet-5-5", "claude-sonnet-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-29), which gives every curated Claude model 1,000,000 tokens of context and 128K max output (Haiku 4.5: 200K and 64K). claude-opus-5-5 is the default: the newest Opus, at $4/$20 per MTok, below claude-opus-5 ($5/$25), which stays curated. claude-fable-5-1 ($10/$50) is the top tier and supersedes claude-fable-5 (same price), also still curated. claude-sonnet-5-5 (new in the 2026-09-29 registry) and claude-sonnet-5 are both $2/$10. Ids use Anthropic's hyphenated form; the registry's dotted ids (claude-opus-5.5) match them through ModelRegistryService's dot/hyphen variants. The adaptive-thinking / sampling-removed lists below match by prefix, so the claude-opus-5, claude-fable-5 and claude-sonnet-5 entries cover Opus 5.5, Fable 5.1 and Sonnet 5.5. claude-opus-5-fast and the registry's claude-sonnet-5.5:batch variant are not curated.","detection_patterns": ["claude", "anthropic"],"base_url": "https://api.anthropic.com/v1","models_endpoint": "https://api.anthropic.com/v1/models",@@ -88,6 +88,7 @@"claude-opus-5": 128000,"claude-opus-4-8": 128000,"claude-opus-4-7": 128000,+ "claude-sonnet-5-5": 128000,"claude-sonnet-5": 128000,"claude-sonnet-4-6": 128000,"claude-haiku-4-5": 64000,@@ -100,6 +101,7 @@"claude-opus-5": 1000000,"claude-opus-4-8": 1000000,"claude-opus-4-7": 1000000,+ "claude-sonnet-5-5": 1000000,"claude-sonnet-5": 1000000,"claude-sonnet-4-6": 1000000,"claude-haiku-4-5": 200000,@@ -139,7 +141,7 @@"enabled": false,"_note": "See openai.vision._note — off until the Gemini encoder renders inline_data parts beside function_response."},- "_models_note": "Real (concrete) model names only — no -latest rolling aliases. The curated list (max_output_tokens keys) serves BOTH the Gemini Developer API (AIza keys) and Vertex / Agent Platform (AQ. keys); gemini-* entries live-verified on both endpoints (2026-06-12). Vertex 404s on -latest aliases and its models.list rejects API keys, which is why the dropdown is curated instead of live-fetched. Gemma exception: gemma-4-31b-it + gemma-4-26b-a4b-it are served ONLY on the Developer API (free tier, ai.google.dev/gemma/docs/core/gemma_on_gemini_api, verified 2026-07-11) — Vertex keys must not see them, hence vertex_incompatible_models below. Gemma 4 supports systemInstruction and function calling natively (unlike the gemma-3 era). Context and max output for every entry follow the OpenRouter registry (2026-09-26), including Gemma's 262K context and 16K / 236K max output.",+ "_models_note": "Real (concrete) model names only — no -latest rolling aliases. The curated list (max_output_tokens keys) serves BOTH the Gemini Developer API (AIza keys) and Vertex / Agent Platform (AQ. keys); gemini-* entries live-verified on both endpoints (2026-06-12). Vertex 404s on -latest aliases and its models.list rejects API keys, which is why the dropdown is curated instead of live-fetched. Gemma exception: gemma-4-31b-it + gemma-4-26b-a4b-it are served ONLY on the Developer API (free tier, ai.google.dev/gemma/docs/core/gemma_on_gemini_api, verified 2026-07-11) — Vertex keys must not see them, hence vertex_incompatible_models below. Gemma 4 supports systemInstruction and function calling natively (unlike the gemma-3 era). Context and max output for every entry follow the OpenRouter registry (2026-09-29), including Gemma's 262K context and 16K / 236K max output.","max_output_tokens": {"gemini-3.8-flash": 65536,"gemini-3.7-flash": 65536,@@ -183,9 +185,9 @@},"openrouter": {"display_name": "OpenRouter",- "default_model": "anthropic/claude-sonnet-5",- "popular_models": ["anthropic/claude-sonnet-5", "anthropic/claude-opus-5.5", "openai/gpt-5.6-terra", "openai/gpt-6-sol", "openai/gpt-6-astra", "google/gemini-3.8-flash", "google/gemini-3.5-flash", "deepseek/deepseek-v4.1-flash", "moonshotai/kimi-k3", "x-ai/grok-4.20"],- "_popular_note": "Registry ids verbatim (OpenRouter registry, 2026-09-26), one or two current models per vendor; tests/llm/test_global_model_catalogue.py checks each is in model_registry.json.",+ "default_model": "anthropic/claude-sonnet-5.5",+ "popular_models": ["anthropic/claude-sonnet-5.5", "anthropic/claude-opus-5.5", "openai/gpt-5.6-terra", "openai/gpt-6-sol", "openai/gpt-6-astra", "google/gemini-3.8-flash", "google/gemini-3.5-flash", "deepseek/deepseek-v4.1-flash", "moonshotai/kimi-k3", "x-ai/grok-4.20"],+ "_popular_note": "Registry ids verbatim (OpenRouter registry, 2026-09-29), one or two current models per vendor; Claude Sonnet 5.5 replaced Sonnet 5 as the default on 2026-09-29, at the same price; tests/llm/test_global_model_catalogue.py checks each is in model_registry.json.","detection_patterns": ["openrouter"],"open_world_models": true,"base_url": "https://openrouter.ai/api/v1",@@ -272,7 +274,7 @@"models_endpoint": "https://api.x.ai/v1/models","api_key_param": "api_key","max_tokens_param": "max_tokens",- "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-26): grok-4.20 and grok-4.20-multi-agent have 2M context and 1.8M max output at $1.25/$2.50 per MTok; grok-4.3 1M and 900K at $1.25/$2.50; grok-4.7 500K and 450K at $1.60/$4.80; grok-4.6 and grok-4.5 500K and 450K at $2/$6. grok-3 is not in the registry and is no longer curated. grok-4.6 and grok-4.5 take reasoning effort low/medium/high/xhigh (default high).",+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-29): grok-4.20 and grok-4.20-multi-agent have 2M context and 1.8M max output at $1.25/$2.50 per MTok; grok-4.3 1M and 900K at $1.25/$2.50; grok-4.7, grok-4.6 and grok-4.5 500K and 450K at $2/$6. grok-3 is not in the registry and is no longer curated. grok-4.6 and grok-4.5 take reasoning effort low/medium/high/xhigh (default high).","max_output_tokens": {"grok-4.20": 1800000,"grok-4.20-multi-agent": 1800000,@@ -298,7 +300,7 @@"default_model": "deepseek-v4.1-flash","popular_models": ["deepseek-v4.1-flash", "deepseek-v4-pro"],"_popular_note": "Both curated ids are 1M-context; deepseek-v4-flash, the earlier Flash model, stays in the maps but not in the global list.",- "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-26): deepseek-v4.1-flash (default) has 1M context and 131K max output at $0.14/$0.42 per MTok; deepseek-v4-pro 1M and 384K at $0.4188/$0.8376; deepseek-v4-flash 1M and 384K at $0.047/$0.0941. deepseek-flash, the other name DeepSeek's API accepts for V4.1-Flash, is not a registry model, so it is no longer curated or the default; a node that still names it is sized by the registry's deepseek-flash-latest alias. Dated snapshots (-0731 / -0813), the -latest aliases and deepseek-v4-flash-vision-exp are deliberately not curated.",+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-09-29): deepseek-v4.1-flash (default) has 1M context and 943,718 max output at $0.30/$1.20 per MTok; deepseek-v4-pro 1M and 384K at $0.9553/$1.9105; deepseek-v4-flash 1M and 131K at $0.14/$0.28. deepseek-flash, the other name DeepSeek's API accepts for V4.1-Flash, is not a registry model, so it is no longer curated or the default; a node that still names it is sized by the registry's deepseek-flash-latest alias. Dated snapshots (-0731 / -0813), the -latest aliases and deepseek-v4-flash-vision-exp are deliberately not curated.","detection_patterns": ["deepseek"],"base_url": "https://api.deepseek.com","models_endpoint": "https://api.deepseek.com/models",@@ -306,9 +308,9 @@"max_tokens_param": "max_tokens","supported_params": ["temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "stop", "seed", "tools", "tool_choice", "response_format"],"max_output_tokens": {- "deepseek-v4.1-flash": 131072,+ "deepseek-v4.1-flash": 943718,"deepseek-v4-pro": 384000,- "deepseek-v4-flash": 384000,+ "deepseek-v4-flash": 131072,"_default": 8192},"context_length": {@@ -325,7 +327,7 @@"default_model": "kimi-k3","popular_models": ["kimi-k3"],"_popular_note": "Only kimi-k3 meets the 1M-context policy (k2.x are 262144); k2.x remain reachable via live fetch_models.",- "_models_note": "Ids, context and prices follow the OpenRouter registry (2026-09-26), which files these models under moonshotai/: kimi-k3 has 1M context at $3/$15 per MTok; kimi-k2.6 ($0.95/$4.00) and kimi-k2.7-code ($0.6562/$3.30) have 262K. max_output_tokens deliberately stays below the registry's caps (943,718 for kimi-k3, 235,929 for the k2 models, about 90% of each window): the registry lookup never matches the kimi provider name, so these numbers are what resolve_max_tokens sends as max_tokens, and a cap that close to the window would leave the prompt a tenth of it. 131072 is Moonshot's own default for kimi-k3. kimi-k2.7-code-highspeed is not a registry model, so it has no limits or price of its own here (it matches kimi-k2.7-code by prefix); the thinking and temperature lists still name it because they describe how Moonshot's API treats it.",+ "_models_note": "Ids, context and prices follow the OpenRouter registry (2026-09-29), which files these models under moonshotai/: kimi-k3 has 1M context at $3/$15 per MTok; kimi-k2.6 ($0.65/$3.41) and kimi-k2.7-code ($0.6562/$3.30) have 262K. max_output_tokens deliberately stays below the registry's caps (943,718 for kimi-k3, 235,929 for the k2 models, about 90% of each window): the registry lookup never matches the kimi provider name, so these numbers are what resolve_max_tokens sends as max_tokens, and a cap that close to the window would leave the prompt a tenth of it. 131072 is Moonshot's own default for kimi-k3. kimi-k2.7-code-highspeed is not a registry model, so it has no limits or price of its own here (it matches kimi-k2.7-code by prefix); the thinking and temperature lists still name it because they describe how Moonshot's API treats it.","detection_patterns": ["kimi", "moonshot"],"base_url": "https://api.moonshot.ai/v1","models_endpoint": "https://api.moonshot.ai/v1/models",@@ -353,7 +355,7 @@"default_model": "mistral-large-latest","popular_models": [],"_popular_note": "Empty per the 1M-context policy — Mistral tops out at 262144 (large/medium/small). Models remain reachable via live fetch_models.",- "_models_note": "The curated keys are Mistral's -latest aliases, because the node defaults to one and saved nodes hold them; each takes its context and price from the registry model it names (OpenRouter registry, 2026-09-26, under mistralai/): mistral-large-2512 (Large 3, 262K, $0.50/$1.50), mistral-medium-3-5 (Medium 3.5, 262K, $1.50/$7.50), mistral-small-2603 (Small 4, 262K, $0.15/$0.60) and codestral-2508 (256K, $0.30/$0.90). The registry lookup never matches the mistral provider name, so these maps are what requests use, and max_output_tokens keeps the current budgets rather than the registry's caps of about 80% of the window (209,715): resolve_max_tokens sends this number as max_tokens, and a cap that large would leave the prompt a fifth of the window.",+ "_models_note": "The curated keys are Mistral's -latest aliases, because the node defaults to one and saved nodes hold them; each takes its context and price from the registry model it names (OpenRouter registry, 2026-09-29, under mistralai/): mistral-large-2512 (Large 3, 262K, $0.50/$1.50), mistral-medium-3-5 (Medium 3.5, 262K, $1.50/$7.50), mistral-small-2603 (Small 4, 262K, $0.15/$0.60) and codestral-2508 (256K, $0.30/$0.90). The registry lookup never matches the mistral provider name, so these maps are what requests use, and max_output_tokens keeps the current budgets rather than the registry's caps of about 80% of the window (209,715): resolve_max_tokens sends this number as max_tokens, and a cap that large would leave the prompt a fifth of the window.","detection_patterns": ["mistral", "codestral"],"base_url": "https://api.mistral.ai/v1","models_endpoint": "https://api.mistral.ai/v1/models",diff --git a/server/config/model_registry.json b/server/config/model_registry.jsonindex 2dd51585..0347ec52 100644--- a/server/config/model_registry.json+++ b/server/config/model_registry.json@@ -1,8 +1,68 @@{- "_generated": "2026-09-26T06:38:55.512843+00:00",+ "_generated": "2026-09-29T06:46:41.936995+00:00","_source": "openrouter",- "_model_count": 458,+ "_model_count": 460,"models": {+ "anthropic/claude-sonnet-5.5": {+ "id": "anthropic/claude-sonnet-5.5",+ "name": "Anthropic: Claude Sonnet 5.5",+ "provider": "anthropic",+ "local_id": "claude-sonnet-5.5",+ "context_length": 1000000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 10.0,+ "supports_thinking": true,+ "thinking_type": "budget",+ "temperature_range": [+ 0.0,+ 1.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "verbosity"+ ]+ },+ "anthropic/claude-sonnet-5.5:batch": {+ "id": "anthropic/claude-sonnet-5.5:batch",+ "name": "Anthropic: Claude Sonnet 5.5 (batch)",+ "provider": "anthropic",+ "local_id": "claude-sonnet-5.5:batch",+ "context_length": 1000000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 5.0,+ "supports_thinking": true,+ "thinking_type": "budget",+ "temperature_range": [+ 0.0,+ 1.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "stop",+ "structured_outputs",+ "tool_choice",+ "tools",+ "verbosity"+ ]+ },"typesafe/jev-router": {"id": "typesafe/jev-router","name": "TypeSafe: Jev Router",@@ -706,8 +766,8 @@"local_id": "grok-4.7","context_length": 500000,"max_output_tokens": 450000,- "input_price_per_mtok": 1.6,- "output_price_per_mtok": 4.8,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 6.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -863,8 +923,8 @@"local_id": "deepseek-pro-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.25,- "output_price_per_mtok": 3.5,+ "input_price_per_mtok": 0.1581,+ "output_price_per_mtok": 1.9584,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -901,9 +961,9 @@"provider": "deepseek","local_id": "deepseek-flash-latest","context_length": 1048576,- "max_output_tokens": 384000,- "input_price_per_mtok": 0.035,- "output_price_per_mtok": 0.29,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.02,+ "output_price_per_mtok": 0.6,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1208,9 +1268,9 @@"provider": "deepseek","local_id": "deepseek-v4.1-flash","context_length": 1048576,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.14,- "output_price_per_mtok": 0.42,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 1.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1307,6 +1367,66 @@"tools"]},+ "nex-agi/nex-n2.5-mini": {+ "id": "nex-agi/nex-n2.5-mini",+ "name": "Nex AGI: Nex-N2.5-Mini",+ "provider": "nex-agi",+ "local_id": "nex-n2.5-mini",+ "context_length": 262144,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.025,+ "output_price_per_mtok": 0.1,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "logprobs",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "structured_outputs",+ "temperature",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "nex-agi/nex-n2.5-pro": {+ "id": "nex-agi/nex-n2.5-pro",+ "name": "Nex AGI: Nex-N2.5-Pro",+ "provider": "nex-agi",+ "local_id": "nex-n2.5-pro",+ "context_length": 262144,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.075,+ "output_price_per_mtok": 0.25,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "logprobs",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },"openai/gpt-6-astra": {"id": "openai/gpt-6-astra","name": "OpenAI: GPT-6 Astra",@@ -1730,8 +1850,10 @@"supported_parameters": ["frequency_penalty","include_reasoning",+ "logit_bias","max_completion_tokens","max_tokens",+ "min_p","presence_penalty","reasoning","reasoning_effort",@@ -1767,6 +1889,7 @@"frequency_penalty","include_reasoning","logit_bias",+ "logprobs","max_tokens","min_p","presence_penalty",@@ -1779,39 +1902,6 @@"tool_choice","tools","top_k",- "top_p"- ]- },- "inclusionai/ling-3.0-flash-fin:free": {- "id": "inclusionai/ling-3.0-flash-fin:free",- "name": "inclusionAI: Ling 3.0 Flash Fin (free)",- "provider": "inclusionai",- "local_id": "ling-3.0-flash-fin:free",- "context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.0,- "output_price_per_mtok": 0.0,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "logprobs",- "max_tokens",- "presence_penalty",- "reasoning",- "repetition_penalty",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k","top_logprobs","top_p"]@@ -1822,9 +1912,9 @@"provider": "z-ai","local_id": "glm-flash-latest","context_length": 1310720,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.04,- "output_price_per_mtok": 0.5,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.02,+ "output_price_per_mtok": 0.3,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1897,8 +1987,8 @@"provider": "z-ai","local_id": "glm-5.3-flash","context_length": 1310720,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.04,+ "max_output_tokens": 943717,+ "input_price_per_mtok": 0.15,"output_price_per_mtok": 0.5,"supports_thinking": false,"thinking_type": "none",@@ -2005,9 +2095,9 @@"provider": "deepseek","local_id": "deepseek-v4-flash-vision-exp","context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.22,- "output_price_per_mtok": 0.66,+ "max_output_tokens": 262144,+ "input_price_per_mtok": 0.2156,+ "output_price_per_mtok": 0.6468,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2093,8 +2183,8 @@"local_id": "glm-latest","context_length": 1310720,"max_output_tokens": 131072,- "input_price_per_mtok": 0.4746,- "output_price_per_mtok": 1.4916,+ "input_price_per_mtok": 0.19,+ "output_price_per_mtok": 4.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2234,9 +2324,9 @@"provider": "qwen","local_id": "qwen3.8-27b","context_length": 1000000,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.42,- "output_price_per_mtok": 3.0,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.0647,+ "output_price_per_mtok": 4.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2494,9 +2584,9 @@"provider": "deepseek","local_id": "deepseek-v4-pro-0813","context_length": 1048576,- "max_output_tokens": 384000,- "input_price_per_mtok": 0.264,- "output_price_per_mtok": 0.792,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.4,+ "output_price_per_mtok": 4.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2605,9 +2695,9 @@"provider": "nvidia","local_id": "nemotron-3.5-lightning","context_length": 1000000,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.08,- "output_price_per_mtok": 0.2,+ "max_output_tokens": 32768,+ "input_price_per_mtok": 0.06,+ "output_price_per_mtok": 0.16,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2742,7 +2832,6 @@"frequency_penalty","include_reasoning","logit_bias",- "logprobs","max_tokens","min_p","presence_penalty",@@ -2757,7 +2846,6 @@"tool_choice","tools","top_k",- "top_logprobs","top_p"]},@@ -2799,8 +2887,8 @@"local_id": "deepseek-v4-flash-latest","context_length": 1310720,"max_output_tokens": 943718,- "input_price_per_mtok": 0.021,- "output_price_per_mtok": 0.32,+ "input_price_per_mtok": 0.012,+ "output_price_per_mtok": 0.7,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2840,7 +2928,7 @@"local_id": "deepseek-v4-flash-0731","context_length": 1310720,"max_output_tokens": 943718,- "input_price_per_mtok": 0.021,+ "input_price_per_mtok": 0.018,"output_price_per_mtok": 0.32,"supports_thinking": false,"thinking_type": "none",@@ -3754,8 +3842,8 @@"local_id": "gpt-5.6-sol-pro","context_length": 1050000,"max_output_tokens": 128000,- "input_price_per_mtok": 2.0,- "output_price_per_mtok": 10.0,+ "input_price_per_mtok": 4.0,+ "output_price_per_mtok": 20.0,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -3900,8 +3988,8 @@"local_id": "grok-latest","context_length": 500000,"max_output_tokens": 450000,- "input_price_per_mtok": 1.6,- "output_price_per_mtok": 4.8,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 6.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -4274,9 +4362,9 @@"provider": "z-ai","local_id": "glm-5.2","context_length": 1048576,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.6496,- "output_price_per_mtok": 2.0416,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.3249,+ "output_price_per_mtok": 4.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5246,8 +5334,8 @@"local_id": "kimi-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 1.0301,- "output_price_per_mtok": 9.043,+ "input_price_per_mtok": 0.4,+ "output_price_per_mtok": 10.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5334,6 +5422,7 @@"response_format","stop","structured_outputs",+ "temperature","tool_choice","tools","verbosity"@@ -5640,8 +5729,8 @@"local_id": "deepseek-v4-pro","context_length": 1048576,"max_output_tokens": 384000,- "input_price_per_mtok": 0.4188,- "output_price_per_mtok": 0.8376,+ "input_price_per_mtok": 0.9553,+ "output_price_per_mtok": 1.9105,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5679,9 +5768,9 @@"provider": "deepseek","local_id": "deepseek-v4-flash","context_length": 1048576,- "max_output_tokens": 384000,- "input_price_per_mtok": 0.047,- "output_price_per_mtok": 0.0941,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.14,+ "output_price_per_mtok": 0.28,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5904,8 +5993,8 @@"local_id": "kimi-k2.6","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.95,- "output_price_per_mtok": 4.0,+ "input_price_per_mtok": 0.65,+ "output_price_per_mtok": 3.41,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6002,8 +6091,8 @@"local_id": "glm-5.1","context_length": 204800,"max_output_tokens": 131072,- "input_price_per_mtok": 0.9646,- "output_price_per_mtok": 3.0316,+ "input_price_per_mtok": 1.4,+ "output_price_per_mtok": 4.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6040,8 +6129,8 @@"local_id": "gemma-4-26b-a4b-it","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.0675,- "output_price_per_mtok": 0.225,+ "input_price_per_mtok": 0.0765,+ "output_price_per_mtok": 0.255,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6402,9 +6491,9 @@"provider": "minimax","local_id": "minimax-m2.7","context_length": 204800,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 1.2,+ "max_output_tokens": 176947,+ "input_price_per_mtok": 0.21,+ "output_price_per_mtok": 0.84,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7018,9 +7107,9 @@"provider": "qwen","local_id": "qwen3.5-35b-a3b","context_length": 262144,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.3125,- "output_price_per_mtok": 1.25,+ "max_output_tokens": 65536,+ "input_price_per_mtok": 0.1625,+ "output_price_per_mtok": 1.3,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7094,7 +7183,7 @@"provider": "qwen","local_id": "qwen3.5-122b-a10b","context_length": 262144,- "max_output_tokens": 65536,+ "max_output_tokens": 235929,"input_price_per_mtok": 0.26,"output_price_per_mtok": 2.08,"supports_thinking": false,@@ -8686,8 +8775,8 @@"local_id": "deepseek-v3.2","context_length": 163840,"max_output_tokens": 65536,- "input_price_per_mtok": 0.269,- "output_price_per_mtok": 0.4,+ "input_price_per_mtok": 0.28,+ "output_price_per_mtok": 0.42,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9623,7 +9712,7 @@"provider": "deepseek","local_id": "deepseek-v3.2-exp","context_length": 163840,- "max_output_tokens": 65536,+ "max_output_tokens": 147456,"input_price_per_mtok": 0.27,"output_price_per_mtok": 0.41,"supports_thinking": false,@@ -9854,8 +9943,8 @@"provider": "deepseek","local_id": "deepseek-v3.1-terminus","context_length": 163840,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.27,+ "max_output_tokens": 65536,+ "input_price_per_mtok": 0.3,"output_price_per_mtok": 1.0,"supports_thinking": false,"thinking_type": "none",@@ -10727,9 +10816,9 @@"provider": "qwen","local_id": "qwen3-30b-a3b-instruct-2507","context_length": 262144,- "max_output_tokens": 235929,- "input_price_per_mtok": 0.1,- "output_price_per_mtok": 0.3,+ "max_output_tokens": 32000,+ "input_price_per_mtok": 0.0481,+ "output_price_per_mtok": 0.193,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -11555,9 +11644,9 @@"provider": "qwen","local_id": "qwen3-30b-a3b","context_length": 131072,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.12,- "output_price_per_mtok": 0.5,+ "max_output_tokens": 8192,+ "input_price_per_mtok": 0.13,+ "output_price_per_mtok": 0.52,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -12101,8 +12190,8 @@"local_id": "deepseek-chat-v3-0324","context_length": 163840,"max_output_tokens": 147456,- "input_price_per_mtok": 0.25,- "output_price_per_mtok": 1.0,+ "input_price_per_mtok": 0.29,+ "output_price_per_mtok": 1.14,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -12725,36 +12814,6 @@"web_search_options"]},- "deepseek/deepseek-r1-distill-llama-70b": {- "id": "deepseek/deepseek-r1-distill-llama-70b",- "name": "DeepSeek: R1 Distill Llama 70B",- "provider": "deepseek",- "local_id": "deepseek-r1-distill-llama-70b",- "context_length": 8192,- "max_output_tokens": 7372,- "input_price_per_mtok": 0.8,- "output_price_per_mtok": 0.8,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "max_tokens",- "presence_penalty",- "reasoning",- "repetition_penalty",- "seed",- "stop",- "temperature",- "top_k",- "top_p"- ]- },"deepseek/deepseek-r1": {"id": "deepseek/deepseek-r1","name": "DeepSeek: R1",@@ -12848,9 +12907,9 @@"provider": "deepseek","local_id": "deepseek-chat","context_length": 163840,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.32,- "output_price_per_mtok": 0.89,+ "max_output_tokens": 16000,+ "input_price_per_mtok": 0.2574,+ "output_price_per_mtok": 1.0287,"supports_thinking": false,"thinking_type": "none","temperature_range": [diff --git a/server/config/pricing.json b/server/config/pricing.jsonindex e8a1b627..bfdcb148 100644--- a/server/config/pricing.json+++ b/server/config/pricing.json@@ -1,11 +1,11 @@{"version": "2026.09",- "last_updated": "2026-09-26",- "_llm_note": "LLM input and output prices follow the OpenRouter registry (model_registry.json, 2026-09-26) for every model it lists, USD per MTok. The registry carries no cache price, so cache_read keeps each vendor's published cache discount, applied to the registry input price. The hosts (groq, cerebras, sarvam) are not in the registry and keep their own documented prices.",+ "last_updated": "2026-09-29",+ "_llm_note": "LLM input and output prices follow the OpenRouter registry (model_registry.json, 2026-09-29) for every model it lists, USD per MTok. The registry carries no cache price, so cache_read keeps each vendor's published cache discount, applied to the registry input price. The hosts (groq, cerebras, sarvam) are not in the registry and keep their own documented prices.","llm": {"openai": {- "_note": "OpenRouter registry, 2026-09-26. cache_read is 10% of input, OpenAI's cached-input rate.",+ "_note": "OpenRouter registry, 2026-09-29. cache_read is 10% of input, OpenAI's cached-input rate.","gpt-6-astra": {"input": 10.00, "output": 50.00, "cache_read": 1.00},"gpt-6-astra-pro": {"input": 10.00, "output": 50.00, "cache_read": 1.00},"gpt-6-sol": {"input": 2.00, "output": 10.00, "cache_read": 0.20},@@ -13,7 +13,7 @@"gpt-6-luna": {"input": 0.10, "output": 0.50, "cache_read": 0.01},"gpt-6-luna-pro": {"input": 0.10, "output": 0.50, "cache_read": 0.01},"gpt-5.6-sol": {"input": 2.00, "output": 10.00, "cache_read": 0.20},- "gpt-5.6-sol-pro": {"input": 2.00, "output": 10.00, "cache_read": 0.20},+ "gpt-5.6-sol-pro": {"input": 4.00, "output": 20.00, "cache_read": 0.40},"gpt-5.6-terra": {"input": 2.00, "output": 12.00, "cache_read": 0.20},"gpt-5.6-terra-pro": {"input": 2.00, "output": 12.00, "cache_read": 0.20},"gpt-5.6-luna": {"input": 0.20, "output": 1.20, "cache_read": 0.02},@@ -26,7 +26,7 @@"_default": {"input": 2.50, "output": 15.00}},"anthropic": {- "_note": "OpenRouter registry, 2026-09-26. cache_read is Anthropic's cache-read rate, 10% of input (2.5% on claude-fable-5-1).",+ "_note": "OpenRouter registry, 2026-09-29. cache_read is Anthropic's cache-read rate, 10% of input (2.5% on claude-fable-5-1). claude-sonnet-5-5 is listed before claude-sonnet-5 because a lookup that misses the exact key takes the first key the id starts with.","claude-opus-5-5": {"input": 4.00, "output": 20.00, "cache_read": 0.40},"claude-opus-5": {"input": 5.00, "output": 25.00, "cache_read": 0.50},"claude-fable-5-1": {"input": 10.00, "output": 50.00, "cache_read": 0.25},@@ -34,6 +34,7 @@"claude-opus-4-8": {"input": 5.00, "output": 25.00, "cache_read": 0.50},"claude-opus-4-7": {"input": 5.00, "output": 25.00, "cache_read": 0.50},"claude-opus-4-6": {"input": 5.00, "output": 25.00, "cache_read": 0.50},+ "claude-sonnet-5-5": {"input": 2.00, "output": 10.00, "cache_read": 0.20},"claude-sonnet-5": {"input": 2.00, "output": 10.00, "cache_read": 0.20},"claude-sonnet-4-6": {"input": 3.00, "output": 15.00, "cache_read": 0.30},"claude-haiku-4-5": {"input": 1.00, "output": 5.00, "cache_read": 0.10},@@ -42,7 +43,7 @@"_default": {"input": 3.00, "output": 15.00, "cache_read": 0.30}},"gemini": {- "_note": "OpenRouter registry, 2026-09-26. For Gemma these are the registry's paid-route prices; Google's own API serves Gemma free, so Gemma usage through it is over-reported.",+ "_note": "OpenRouter registry, 2026-09-29. For Gemma these are the registry's paid-route prices; Google's own API serves Gemma free, so Gemma usage through it is over-reported.","gemini-3.8-flash": {"input": 0.75, "output": 3.75},"gemini-3.7-flash": {"input": 0.75, "output": 3.75},"gemini-3.6-flash": {"input": 0.75, "output": 3.75},@@ -55,7 +56,7 @@"gemini-2.5-flash-lite": {"input": 0.10, "output": 0.40},"gemini-2.5-flash": {"input": 0.30, "output": 2.50},"gemma-4-31b-it": {"input": 0.09, "output": 0.34},- "gemma-4-26b-a4b-it": {"input": 0.0675, "output": 0.225},+ "gemma-4-26b-a4b-it": {"input": 0.0765, "output": 0.255},"_default": {"input": 0.50, "output": 3.00}},"groq": {@@ -69,8 +70,8 @@"_default": {"input": 0.15, "output": 0.60}},"xai": {- "_note": "OpenRouter registry, 2026-09-26.",- "grok-4.7": {"input": 1.60, "output": 4.80},+ "_note": "OpenRouter registry, 2026-09-29.",+ "grok-4.7": {"input": 2.00, "output": 6.00},"grok-4.6": {"input": 2.00, "output": 6.00},"grok-4.5": {"input": 2.00, "output": 6.00},"grok-4.3": {"input": 1.25, "output": 2.50},@@ -87,22 +88,22 @@"_default": {"input": 1.00, "output": 5.00}},"deepseek": {- "_note": "OpenRouter registry, 2026-09-26. cache_read keeps DeepSeek's published cache-hit ratio (2% of input on Flash, 3.3% on Pro) applied to the registry input price. deepseek-flash is not a registry model and falls to _default.",- "deepseek-v4.1-flash": {"input": 0.14, "output": 0.42, "cache_read": 0.0028},- "deepseek-v4-flash": {"input": 0.047, "output": 0.0941, "cache_read": 0.00094},- "deepseek-v4-pro": {"input": 0.4188, "output": 0.8376, "cache_read": 0.014},+ "_note": "OpenRouter registry, 2026-09-29. cache_read keeps DeepSeek's published cache-hit ratio (2% of input on Flash, 3.3% on Pro) applied to the registry input price. deepseek-flash is not a registry model and falls to _default.",+ "deepseek-v4.1-flash": {"input": 0.30, "output": 1.20, "cache_read": 0.006},+ "deepseek-v4-flash": {"input": 0.14, "output": 0.28, "cache_read": 0.0028},+ "deepseek-v4-pro": {"input": 0.9553, "output": 1.9105, "cache_read": 0.0315},"_default": {"input": 0.15, "output": 0.60}},"kimi": {- "_note": "OpenRouter registry (under moonshotai/), 2026-09-26. cache_read keeps Moonshot's published cache-hit ratio applied to the registry input price. kimi-k2.7-code-highspeed and the moonshot-v1 models are not registry models; the highspeed id matches kimi-k2.7-code by prefix.",+ "_note": "OpenRouter registry (under moonshotai/), 2026-09-29. cache_read keeps Moonshot's published cache-hit ratio applied to the registry input price. kimi-k2.7-code-highspeed and the moonshot-v1 models are not registry models; the highspeed id matches kimi-k2.7-code by prefix.","kimi-k3": {"input": 3.00, "output": 15.00, "cache_read": 0.30},"kimi-k2.7-code": {"input": 0.6562, "output": 3.30, "cache_read": 0.1312},- "kimi-k2.6": {"input": 0.95, "output": 4.00, "cache_read": 0.16},+ "kimi-k2.6": {"input": 0.65, "output": 3.41, "cache_read": 0.1095},"kimi-k2-thinking": {"input": 0.60, "output": 2.50, "cache_read": 0.15},"_default": {"input": 0.95, "output": 4.00}},"mistral": {- "_note": "OpenRouter registry (under mistralai/), 2026-09-26. Each -latest alias takes the price of the model it names: mistral-large-2512, mistral-medium-3-5, mistral-small-2603 and codestral-2508. mistral-nemo also prices Mistral's open-mistral-nemo id, which contains it.",+ "_note": "OpenRouter registry (under mistralai/), 2026-09-29. Each -latest alias takes the price of the model it names: mistral-large-2512, mistral-medium-3-5, mistral-small-2603 and codestral-2508. mistral-nemo also prices Mistral's open-mistral-nemo id, which contains it.","mistral-large-latest": {"input": 0.50, "output": 1.50},"mistral-medium-latest": {"input": 1.50, "output": 7.50},"mistral-small-latest": {"input": 0.15, "output": 0.60},