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
trohitg30744fb7885c
diff --git a/docs-internal/native_llm_sdk.md b/docs-internal/native_llm_sdk.mdindex f42d4011..2f3a0acb 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 5.5 / 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, Haiku 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 |+| **Google** | Gemini 3.8-flash (default), 4-argon, 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; ~944K (4 Argon) | budget (`thinking_level` on 3.x when set explicitly; 4 Argon runs its default thinking until it is verified) | 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 | ~944K (V4.1 Flash); 384K (V4 Pro); 131K (V4 Flash) | thinking modes | 0-2 |+| **DeepSeek** | deepseek-v4.1-flash (default), deepseek-v4-pro, deepseek-v4-flash | 1M | ~944K (V4.1 Flash); 384K (V4 Pro); ~944K (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 |diff --git a/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md b/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.mdindex ca6e9442..d034a5e9 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 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`).+- **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 943,717 for `deepseek-v4-flash` (OpenRouter snapshot, 2026-10-19). 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 fea150b1..9052acd0 100644--- a/server/config/llm_defaults.json+++ b/server/config/llm_defaults.json@@ -1,6 +1,6 @@{- "version": "2026.09.29",- "last_updated": "2026-09-29",+ "version": "2026.10.23",+ "last_updated": "2026-10-23","_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. streaming: true marks a provider whose answers stream to the chat as they are written (ChatUnifier passes it the stream sink); declare it only once the provider's stream is shown to report what its finished response does, usage included (tests/llm/test_streaming.py).","agent": {@@ -46,7 +46,7 @@"_user_images_note": "user_images: images the owner attaches to a chat message go to the model as image input in that user message (services/llm/media.py provider_supports_user_images; the provider's encoder renders them). Separate from enabled, which covers images in tool results.","_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 (2026-09-29). 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.",+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-10-19). 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 (gpt-5.6-sol and gpt-5.6-sol-pro both cost $4/$20, twice gpt-6-sol, since the 2026-10-19 registry). 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,@@ -95,8 +95,8 @@"gateway": {"model_prefix": "", "base_path": "", "openai_prefix": "anthropic/"},"streaming": true,"default_model": "claude-opus-5-5",- "popular_models": ["claude-opus-5-5", "claude-fable-5-1", "claude-fable-5", "claude-opus-5", "claude-sonnet-5-5", "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.",+ "popular_models": ["claude-opus-5-5", "claude-fable-5-1", "claude-fable-5", "claude-opus-5", "claude-sonnet-5-5", "claude-sonnet-5", "claude-haiku-5-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-10-19), 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 and claude-sonnet-5 are both $2/$10. claude-haiku-5-5 is the current Haiku at $0.10/$0.50 (Anthropic bills prompts over 100K tokens at $0.50/$2.50, which a flat price cannot express); it takes the same request shape as Sonnet 5.5: adaptive thinking only, non-default sampling rejected, effort low to max. 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 / effort lists below match by prefix, so the claude-opus-5, claude-fable-5, claude-sonnet-5 and claude-haiku-5 entries cover Opus 5.5, Fable 5.1, Sonnet 5.5 and Haiku 5.5. claude-opus-5-fast and the registry's :batch variants are not curated.","detection_patterns": ["claude", "anthropic"],"base_url": "https://api.anthropic.com/v1","models_endpoint": "https://api.anthropic.com/v1/models",@@ -117,6 +117,7 @@"claude-sonnet-5-5": 128000,"claude-sonnet-5": 128000,"claude-sonnet-4-6": 128000,+ "claude-haiku-5-5": 128000,"claude-haiku-4-5": 64000,"_default": 8192},@@ -130,6 +131,7 @@"claude-sonnet-5-5": 1000000,"claude-sonnet-5": 1000000,"claude-sonnet-4-6": 1000000,+ "claude-haiku-5-5": 1000000,"claude-haiku-4-5": 200000,"_default": 200000},@@ -141,7 +143,8 @@"claude-opus-5","claude-opus-4-8","claude-opus-4-7",- "claude-sonnet-5"+ "claude-sonnet-5",+ "claude-haiku-5"],"sampling_params_removed": ["claude-fable-5",@@ -149,7 +152,8 @@"claude-opus-5","claude-opus-4-8","claude-opus-4-7",- "claude-sonnet-5"+ "claude-sonnet-5",+ "claude-haiku-5"],"_effort_models_note": "effort_models (prefix-matched): the models that take the chat picker's effort as output_config.effort, beside any adaptive thinking. The adaptive generations; the budget-thinking models have no effort setting.","effort_models": [@@ -158,7 +162,8 @@"claude-opus-5","claude-opus-4-8","claude-opus-4-7",- "claude-sonnet-5"+ "claude-sonnet-5",+ "claude-haiku-5"],"temperature_range": [0.0, 1.0]},@@ -166,7 +171,7 @@"display_name": "Gemini","gateway": {"model_prefix": "", "base_path": "", "openai_prefix": "gemini/"},"default_model": "gemini-3.8-flash",- "popular_models": ["gemini-3.8-flash", "gemini-3.7-flash", "gemini-3.6-flash", "gemini-3.5-flash", "gemini-3.5-flash-lite", "gemini-3.1-pro-preview", "gemini-3.1-flash-lite", "gemini-3-flash-preview", "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite"],+ "popular_models": ["gemini-3.8-flash", "gemini-4-argon", "gemini-3.7-flash", "gemini-3.6-flash", "gemini-3.5-flash", "gemini-3.5-flash-lite", "gemini-3.1-pro-preview", "gemini-3.1-flash-lite", "gemini-3-flash-preview", "gemini-2.5-pro", "gemini-2.5-flash", "gemini-2.5-flash-lite"],"detection_patterns": ["gemini", "google", "gemma"],"_detection_patterns_note": "'gemma' makes is_model_valid_for_provider accept the API-served Gemma models (gemma-4-*-it) on gemini nodes — without it the four agent-path call sites silently swap gemma to default_model. Cerebras keeps its own 'gemma-4' pattern for its gemma-4-31b (no -it suffix); is_model_valid_for_provider is per-provider so both coexist. Only the runtime-unused detect_provider_from_model classifier prefers gemini for gemma-* names (dict order).","base_url": "https://generativelanguage.googleapis.com/v1beta",@@ -179,9 +184,10 @@"_user_images_note": "user_images: images the owner attaches to a chat message go to the model as image input in that user message (services/llm/media.py provider_supports_user_images; the provider's encoder renders them). Separate from enabled, which covers images in tool results.","_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 (2026-09-29), 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 (2026-10-19), including Gemma's 262K context and 16K / 236K max output.","max_output_tokens": {"gemini-3.8-flash": 65536,+ "gemini-4-argon": 943718,"gemini-3.7-flash": 65536,"gemini-3.6-flash": 65536,"gemini-3.5-flash": 65536,@@ -198,6 +204,7 @@},"context_length": {"gemini-3.8-flash": 1048576,+ "gemini-4-argon": 1048576,"gemini-3.7-flash": 1048576,"gemini-3.6-flash": 1048576,"gemini-3.5-flash": 1048576,@@ -215,7 +222,7 @@"_vertex_incompatible_models_note": "Curated models that only exist on the Gemini Developer API, filtered out of fetch_models when the key is a Vertex / Agent Platform key (GeminiProvider._vertex). Gemma is Model Garden self-deploy on Vertex (the 26B MaaS variant needs a different '-maas' id on a different surface), so the plain ids 404 there.","vertex_incompatible_models": ["gemma-4-31b-it", "gemma-4-26b-a4b-it"],"thinking_models": ["gemini-2.5", "gemini-3"],- "_new_models_note": "gemini-3.8-flash is the default (registry 2026-09-26: 1,048,576 in / 65,536 out, $0.75/$3.75, the same as 3.7 and 3.6 Flash; gemini-3.5-flash is $1.50/$9.00, Flash-Lite $0.30/$2.50). It accepts thinking levels low/medium/high and rejects minimal. The 3.7/3.8 entries are NOT yet live-verified against Vertex / Agent Platform keys like the older entries — drop them into vertex_incompatible_models if a Vertex 404 shows up. The image, Lyria and -customtools models are different endpoints or variants and stay out of the chat list, as do the -preview ids of models that went GA (gemini-2.5-pro-preview, gemini-3.1-flash-lite-preview).",+ "_new_models_note": "gemini-3.8-flash is the default (registry 2026-10-19: 1,048,576 in / 65,536 out, $0.825/$4.125; 3.7 and 3.6 Flash $0.75/$3.75; gemini-3.5-flash $1.50/$9.00, Flash-Lite $0.30/$2.50). It accepts thinking levels low/medium/high and rejects minimal. gemini-4-argon is new in the 2026-10-19 registry (1,048,576 in / 943,718 out, $2/$10; gemini-pro-latest now names it). Its registry row offers the same reasoning parameters as Gemini 3, but it is not in thinking_models or effort_models yet, so it runs with the model's own default thinking: add gemini-4 to both once a live request shows it takes a thinking level. The 3.7/3.8 and gemini-4-argon entries are NOT yet live-verified against Vertex / Agent Platform keys like the older entries — drop them into vertex_incompatible_models if a Vertex 404 shows up. The image, Lyria and -customtools models are different endpoints or variants and stay out of the chat list, as do the -preview ids of models that went GA (gemini-2.5-pro-preview, gemini-3.1-flash-lite-preview).","thinking_type": "budget","_effort_models_note": "effort_models (prefix-matched): the models that take the chat picker's effort as thinking_level (low / high). Gemini 2.5 rejects a thinking level, so it is not listed.","effort_models": ["gemini-3"],@@ -226,8 +233,8 @@"openrouter": {"display_name": "OpenRouter","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.",+ "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-4-argon", "deepseek/deepseek-v4.1-flash", "moonshotai/kimi-k3", "x-ai/grok-4.20"],+ "_popular_note": "Registry ids verbatim (OpenRouter registry, 2026-10-19), 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, and Gemini 4 Argon replaced Gemini 3.5 Flash on 2026-10-23; 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",@@ -317,7 +324,7 @@"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 (2026-09-29): 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).",+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-10-19): 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,@@ -343,7 +350,7 @@"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 (2026-09-29): 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.",+ "_models_note": "Ids, context, max output and prices follow the OpenRouter registry (2026-10-19): deepseek-v4.1-flash (default) has 1M context and 943,718 max output at $0.0344/$0.08 per MTok (it was $0.30/$1.20 in the 2026-09-29 registry); deepseek-v4-pro 1M and 384K at $0.4343/$0.8686; deepseek-v4-flash 1M and 943,717 at $0.091/$0.182. 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",@@ -353,7 +360,7 @@"max_output_tokens": {"deepseek-v4.1-flash": 943718,"deepseek-v4-pro": 384000,- "deepseek-v4-flash": 131072,+ "deepseek-v4-flash": 943717,"_default": 8192},"context_length": {@@ -371,7 +378,7 @@"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 (2026-09-29), 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.",+ "_models_note": "Ids, context and prices follow the OpenRouter registry (2026-10-19), which files these models under moonshotai/: kimi-k3 has 1M context at $0.239/$11.936 per MTok (it was $3/$15 in the 2026-09-29 registry); kimi-k2.6 ($0.65/$3.41) and kimi-k2.7-code ($0.6712/$3.35) 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",@@ -400,7 +407,7 @@"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, 2026-09-29, 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.",+ "_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, 2026-10-19, 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 0874edf5..098cdae2 100644--- a/server/config/model_registry.json+++ b/server/config/model_registry.json@@ -1,14 +1,593 @@{- "_generated": "2026-10-09T08:22:06.255463+00:00",+ "_generated": "2026-10-19T14:49:01.006922+00:00","_source": "openrouter","_model_count": 469,"models": {+ "minimax/minimax-m3.1-flash:free": {+ "id": "minimax/minimax-m3.1-flash:free",+ "name": "MiniMax: MiniMax M3.1 Flash (free)",+ "provider": "minimax",+ "local_id": "minimax-m3.1-flash:free",+ "context_length": 1000000,+ "max_output_tokens": 524288,+ "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": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "deepseek/deepseek-v4.1-flash-1017": {+ "id": "deepseek/deepseek-v4.1-flash-1017",+ "name": "DeepSeek: DeepSeek V4.1 Flash 1017",+ "provider": "deepseek",+ "local_id": "deepseek-v4.1-flash-1017",+ "context_length": 1048576,+ "max_output_tokens": 393216,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 0.6,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_completion_tokens",+ "max_tokens",+ "min_p",+ "parallel_tool_calls",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "elorian/glimpse": {+ "id": "elorian/glimpse",+ "name": "Elorian: Glimpse",+ "provider": "elorian",+ "local_id": "glimpse",+ "context_length": 262144,+ "max_output_tokens": 256000,+ "input_price_per_mtok": 0.6,+ "output_price_per_mtok": 3.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "repetition_penalty",+ "response_format",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "xingchen-agi/xing4.0-29b-a4b:free": {+ "id": "xingchen-agi/xing4.0-29b-a4b:free",+ "name": "XingChen: Xing4.0 29B A4B (free)",+ "provider": "xingchen-agi",+ "local_id": "xing4.0-29b-a4b:free",+ "context_length": 262144,+ "max_output_tokens": 235929,+ "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",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_p"+ ]+ },+ "reflection/beam-1.0-501b-a23b": {+ "id": "reflection/beam-1.0-501b-a23b",+ "name": "Reflection: Beam 1.0 501B A23B",+ "provider": "reflection",+ "local_id": "beam-1.0-501b-a23b",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 3.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "moondream/moondream3-preview": {+ "id": "moondream/moondream3-preview",+ "name": "Moondream: Moondream 3 Preview",+ "provider": "moondream",+ "local_id": "moondream3-preview",+ "context_length": 32000,+ "max_output_tokens": 4096,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 2.5,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "temperature",+ "top_p"+ ]+ },+ "moondream/moondream3.1-9b-a2b": {+ "id": "moondream/moondream3.1-9b-a2b",+ "name": "Moondream: Moondream 3.1",+ "provider": "moondream",+ "local_id": "moondream3.1-9b-a2b",+ "context_length": 32000,+ "max_output_tokens": 4096,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 2.5,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "temperature",+ "top_p"+ ]+ },+ "meta/muse-spark-open": {+ "id": "meta/muse-spark-open",+ "name": "Meta: Muse Spark Open",+ "provider": "meta",+ "local_id": "muse-spark-open",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 1.25,+ "output_price_per_mtok": 4.25,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "nvidia/nemotron-3.5-super-vl": {+ "id": "nvidia/nemotron-3.5-super-vl",+ "name": "NVIDIA: Nemotron 3.5 Super VL",+ "provider": "nvidia",+ "local_id": "nemotron-3.5-super-vl",+ "context_length": 1048576,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.1,+ "output_price_per_mtok": 0.4,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "nvidia/nemotron-3.5-super-vl:free": {+ "id": "nvidia/nemotron-3.5-super-vl:free",+ "name": "NVIDIA: Nemotron 3.5 Super VL (free)",+ "provider": "nvidia",+ "local_id": "nemotron-3.5-super-vl:free",+ "context_length": 1000000,+ "max_output_tokens": 131072,+ "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": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "response_format",+ "seed",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "unbiased/pareto-26.10": {+ "id": "unbiased/pareto-26.10",+ "name": "Pareto 26.10",+ "provider": "unbiased",+ "local_id": "pareto-26.10",+ "context_length": 1048576,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.8,+ "output_price_per_mtok": 3.2,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "max_tokens",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "unbiased/pareto-latest": {+ "id": "~unbiased/pareto-latest",+ "name": "Pareto Latest",+ "provider": "unbiased",+ "local_id": "pareto-latest",+ "context_length": 1048576,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.8,+ "output_price_per_mtok": 3.2,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "max_tokens",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "unbiased/pareto-26.9": {+ "id": "unbiased/pareto-26.9",+ "name": "Pareto 26.9",+ "provider": "unbiased",+ "local_id": "pareto-26.9",+ "context_length": 262144,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 2.5,+ "output_price_per_mtok": 7.5,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "max_tokens",+ "response_format",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "liquid/lfm-2.5-24b-a2b": {+ "id": "liquid/lfm-2.5-24b-a2b",+ "name": "LiquidAI: LFM2.5-24B-A2B",+ "provider": "liquid",+ "local_id": "lfm-2.5-24b-a2b",+ "context_length": 128000,+ "max_output_tokens": 8192,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.7,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logprobs",+ "max_completion_tokens",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs"+ ]+ },+ "gemini/gemini-4-argon": {+ "id": "google/gemini-4-argon",+ "name": "Google: Gemini 4 Argon",+ "provider": "gemini",+ "local_id": "gemini-4-argon",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 10.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "gemini/gemini-4-argon:batch": {+ "id": "google/gemini-4-argon:batch",+ "name": "Google: Gemini 4 Argon (batch)",+ "provider": "gemini",+ "local_id": "gemini-4-argon:batch",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 5.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "scaledown/summarize": {+ "id": "scaledown/summarize",+ "name": "ScaleDown: Summarize",+ "provider": "scaledown",+ "local_id": "summarize",+ "context_length": 1000000,+ "max_output_tokens": 4000,+ "input_price_per_mtok": 0.04,+ "output_price_per_mtok": 0.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "max_tokens"+ ]+ },+ "scaledown/extract": {+ "id": "scaledown/extract",+ "name": "ScaleDown: Extract",+ "provider": "scaledown",+ "local_id": "extract",+ "context_length": 1000000,+ "max_output_tokens": 900000,+ "input_price_per_mtok": 0.04,+ "output_price_per_mtok": 0.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "max_tokens"+ ]+ },+ "meta/muse-wonder": {+ "id": "meta/muse-wonder",+ "name": "Meta: Muse Wonder",+ "provider": "meta",+ "local_id": "muse-wonder",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 4.0,+ "output_price_per_mtok": 20.0,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_p"+ ]+ },"stepfun/step-5-preview": {"id": "stepfun/step-5-preview","name": "StepFun: Step 5 Preview","provider": "stepfun","local_id": "step-5-preview",- "context_length": 1000000,+ "context_length": 1048576,"max_output_tokens": 64000,"input_price_per_mtok": 1.0,"output_price_per_mtok": 2.7,@@ -22,15 +601,22 @@"supported_parameters": ["frequency_penalty","include_reasoning",+ "logit_bias","logprobs","max_tokens",+ "min_p",+ "presence_penalty","reasoning","reasoning_effort",+ "repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature",+ "tool_choice","tools",+ "top_k","top_logprobs","top_p"]@@ -165,43 +751,9 @@"provider": "inclusionai","local_id": "ling-3.1-flash","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"- ]- },- "apodex/apodex-1.1-mini:free": {- "id": "apodex/apodex-1.1-mini:free",- "name": "Apodex: Apodex 1.1 Mini (free)",- "provider": "apodex",- "local_id": "apodex-1.1-mini:free",- "context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.0,- "output_price_per_mtok": 0.0,+ "input_price_per_mtok": 0.075,+ "output_price_per_mtok": 0.225,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -212,7 +764,10 @@"supported_parameters": ["frequency_penalty","include_reasoning",+ "logit_bias",+ "logprobs","max_tokens",+ "min_p","presence_penalty","reasoning","repetition_penalty",@@ -224,30 +779,7 @@"tool_choice","tools","top_k",- "top_p"- ]- },- "unbiased/pareto-26.10-preview": {- "id": "unbiased/pareto-26.10-preview",- "name": "Pareto 26.10 Preview",- "provider": "unbiased",- "local_id": "pareto-26.10-preview",- "context_length": 1048576,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.8,- "output_price_per_mtok": 3.2,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "max_tokens",- "temperature",- "tool_choice",- "tools",+ "top_logprobs","top_p"]},@@ -1258,38 +1790,9 @@"provider": "z-ai","local_id": "glm-5.3-flashx","context_length": 1048576,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.37,- "output_price_per_mtok": 1.25,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "include_reasoning",- "max_tokens",- "reasoning",- "reasoning_effort",- "response_format",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },- "unbiased/pareto": {- "id": "unbiased/pareto",- "name": "Pareto",- "provider": "unbiased",- "local_id": "pareto",- "context_length": 262144,- "max_output_tokens": 131072,- "input_price_per_mtok": 2.5,- "output_price_per_mtok": 7.5,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.37,+ "output_price_per_mtok": 1.25,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1298,11 +1801,15 @@],"is_reasoning_model": false,"supported_parameters": [+ "include_reasoning","max_tokens",+ "reasoning",+ "reasoning_effort","response_format","temperature","tool_choice","tools",+ "top_k","top_p"]},@@ -1313,7 +1820,7 @@"local_id": "deepseek-pro-latest","context_length": 1048576,"max_output_tokens": 393216,- "input_price_per_mtok": 0.198,+ "input_price_per_mtok": 0.1307,"output_price_per_mtok": 8.0,"supports_thinking": false,"thinking_type": "none",@@ -1352,8 +1859,8 @@"local_id": "deepseek-flash-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.016,- "output_price_per_mtok": 1.2,+ "input_price_per_mtok": 0.041,+ "output_price_per_mtok": 0.6,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1366,8 +1873,10 @@"include_reasoning","logit_bias","logprobs",+ "max_completion_tokens","max_tokens","min_p",+ "parallel_tool_calls","presence_penalty","reasoning","reasoning_effort",@@ -1625,10 +2134,10 @@"name": "inclusionAI: Ling 3.0 Flash VL","provider": "inclusionai","local_id": "ling-3.0-flash-vl",- "context_length": 262144,+ "context_length": 131072,"max_output_tokens": 32768,- "input_price_per_mtok": 0.021,- "output_price_per_mtok": 0.0616,+ "input_price_per_mtok": 0.06,+ "output_price_per_mtok": 0.18,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1640,7 +2149,6 @@"frequency_penalty","include_reasoning","logit_bias",- "logprobs","max_tokens","min_p","presence_penalty",@@ -1654,7 +2162,6 @@"tool_choice","tools","top_k",- "top_logprobs","top_p"]},@@ -1665,8 +2172,8 @@"local_id": "deepseek-v4.1-flash","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 1.2,+ "input_price_per_mtok": 0.0344,+ "output_price_per_mtok": 0.08,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1703,9 +2210,9 @@"provider": "deepseek","local_id": "deepseek-v4.1-flash:batch","context_length": 1048576,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.112,- "output_price_per_mtok": 0.336,+ "max_output_tokens": 384000,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.15,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1717,6 +2224,7 @@"frequency_penalty","include_reasoning","logit_bias",+ "logprobs","max_tokens","min_p","presence_penalty",@@ -1731,6 +2239,7 @@"tool_choice","tools","top_k",+ "top_logprobs","top_p"]},@@ -1941,40 +2450,6 @@"verbosity"]},- "inclusionai/ling-3.0-flash-sante": {- "id": "inclusionai/ling-3.0-flash-sante",- "name": "inclusionAI: Ling 3.0 Flash Sante",- "provider": "inclusionai",- "local_id": "ling-3.0-flash-sante",- "context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.042,- "output_price_per_mtok": 0.1232,- "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"- ]- },"qwen/qwen3.8-max-0902": {"id": "qwen/qwen3.8-max-0902","name": "Qwen: Qwen3.8 Max (0902)",@@ -2080,8 +2555,8 @@"local_id": "gemini-3.8-flash","context_length": 1048576,"max_output_tokens": 65536,- "input_price_per_mtok": 0.75,- "output_price_per_mtok": 3.75,+ "input_price_per_mtok": 0.825,+ "output_price_per_mtok": 4.125,"supports_thinking": true,"thinking_type": "budget","temperature_range": [@@ -2269,43 +2744,6 @@"top_p"]},- "inclusionai/ling-3.0-flash-fin": {- "id": "inclusionai/ling-3.0-flash-fin",- "name": "inclusionAI: Ling 3.0 Flash Fin",- "provider": "inclusionai",- "local_id": "ling-3.0-flash-fin",- "context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.042,- "output_price_per_mtok": 0.1232,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "logit_bias",- "logprobs",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "repetition_penalty",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"z-ai/glm-flash-latest": {"id": "~z-ai/glm-flash-latest","name": "Z.ai: GLM Flash Latest",@@ -2313,8 +2751,8 @@"local_id": "glm-flash-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.032,- "output_price_per_mtok": 1.1571,+ "input_price_per_mtok": 0.048,+ "output_price_per_mtok": 0.16,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2387,9 +2825,9 @@"provider": "z-ai","local_id": "glm-5.3-flash","context_length": 1048576,- "max_output_tokens": 943717,- "input_price_per_mtok": 0.15,- "output_price_per_mtok": 0.5,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.048,+ "output_price_per_mtok": 0.16,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2428,8 +2866,8 @@"local_id": "glm-5.3-flash:batch","context_length": 1048576,"max_output_tokens": 131072,- "input_price_per_mtok": 0.06,- "output_price_per_mtok": 0.2,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.18,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2441,6 +2879,7 @@"frequency_penalty","include_reasoning","logit_bias",+ "logprobs","max_tokens","min_p","presence_penalty",@@ -2455,6 +2894,7 @@"tool_choice","tools","top_k",+ "top_logprobs","top_p"]},@@ -2582,9 +3022,9 @@"provider": "z-ai","local_id": "glm-latest","context_length": 1048576,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.0312,- "output_price_per_mtok": 4.4,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.053,+ "output_price_per_mtok": 6.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2648,8 +3088,8 @@"local_id": "glm-5.3","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.039,- "output_price_per_mtok": 7.0,+ "input_price_per_mtok": 0.079,+ "output_price_per_mtok": 1.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2724,9 +3164,9 @@"provider": "qwen","local_id": "qwen3.8-27b","context_length": 1000000,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.425,- "output_price_per_mtok": 2.55,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.24,+ "output_price_per_mtok": 2.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2952,9 +3392,9 @@"provider": "deepseek","local_id": "deepseek-v4-pro-0813","context_length": 1048576,- "max_output_tokens": 393216,- "input_price_per_mtok": 1.32,- "output_price_per_mtok": 3.96,+ "max_output_tokens": 384000,+ "input_price_per_mtok": 0.66,+ "output_price_per_mtok": 1.98,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3053,8 +3493,7 @@"tool_choice","tools","top_k",- "top_logprobs",- "top_p"+ "top_logprobs"]},"nvidia/nemotron-3.5-lightning": {@@ -3063,9 +3502,9 @@"provider": "nvidia","local_id": "nemotron-3.5-lightning","context_length": 262144,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.0469,- "output_price_per_mtok": 0.134,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.07,+ "output_price_per_mtok": 0.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3255,8 +3694,8 @@"local_id": "deepseek-v4-flash-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.0083,- "output_price_per_mtok": 0.1086,+ "input_price_per_mtok": 0.0065,+ "output_price_per_mtok": 0.45,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3296,8 +3735,8 @@"local_id": "deepseek-v4-flash-0731","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.0104,- "output_price_per_mtok": 1.28,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 0.15,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3840,8 +4279,8 @@"local_id": "kimi-k3","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.5,- "output_price_per_mtok": 12.0,+ "input_price_per_mtok": 0.239,+ "output_price_per_mtok": 11.936,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -4183,8 +4622,8 @@"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": [@@ -4213,8 +4652,8 @@"local_id": "gpt-5.6-sol-pro:batch","context_length": 1050000,"max_output_tokens": 128000,- "input_price_per_mtok": 1.0,- "output_price_per_mtok": 5.0,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 10.0,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -4242,8 +4681,8 @@"local_id": "gpt-5.6-sol","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": [@@ -4272,8 +4711,8 @@"local_id": "gpt-5.6-sol:batch","context_length": 1050000,"max_output_tokens": 128000,- "input_price_per_mtok": 1.0,- "output_price_per_mtok": 5.0,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 10.0,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -4708,8 +5147,8 @@"local_id": "glm-5.2","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.06,- "output_price_per_mtok": 4.2,+ "input_price_per_mtok": 0.62,+ "output_price_per_mtok": 2.42,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -4950,9 +5389,9 @@"provider": "nvidia","local_id": "nemotron-3-ultra-550b-a55b","context_length": 262144,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.5,- "output_price_per_mtok": 2.2,+ "max_output_tokens": 182520,+ "input_price_per_mtok": 0.6,+ "output_price_per_mtok": 2.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5044,6 +5483,41 @@"top_p"]},+ "qwen/qwen3.7-plus:batch": {+ "id": "qwen/qwen3.7-plus:batch",+ "name": "Qwen: Qwen3.7 Plus (batch)",+ "provider": "qwen",+ "local_id": "qwen3.7-plus:batch",+ "context_length": 262144,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.23,+ "output_price_per_mtok": 0.92,+ "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",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },"minimax/minimax-m3": {"id": "minimax/minimax-m3","name": "MiniMax: MiniMax M3",@@ -5644,9 +6118,9 @@"provider": "gemini","local_id": "gemini-pro-latest","context_length": 1048576,- "max_output_tokens": 65536,+ "max_output_tokens": 943718,"input_price_per_mtok": 2.0,- "output_price_per_mtok": 12.0,+ "output_price_per_mtok": 10.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5676,7 +6150,7 @@"local_id": "kimi-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 0.49,+ "input_price_per_mtok": 0.238,"output_price_per_mtok": 13.0,"supports_thinking": false,"thinking_type": "none",@@ -5877,41 +6351,6 @@"top_p"]},- "qwen/qwen3.6-max-preview": {- "id": "qwen/qwen3.6-max-preview",- "name": "Qwen: Qwen3.6 Max Preview",- "provider": "qwen",- "local_id": "qwen3.6-max-preview",- "context_length": 262144,- "max_output_tokens": 65536,- "input_price_per_mtok": 1.027,- "output_price_per_mtok": 6.162,- "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",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"qwen/qwen3.6-27b": {"id": "qwen/qwen3.6-27b","name": "Qwen: Qwen3.6 27B",@@ -5919,8 +6358,8 @@"local_id": "qwen3.6-27b","context_length": 262144,"max_output_tokens": 65536,- "input_price_per_mtok": 0.45,- "output_price_per_mtok": 2.7,+ "input_price_per_mtok": 0.25,+ "output_price_per_mtok": 2.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6074,8 +6513,8 @@"local_id": "deepseek-v4-pro","context_length": 1048576,"max_output_tokens": 384000,- "input_price_per_mtok": 0.9553,- "output_price_per_mtok": 1.9105,+ "input_price_per_mtok": 0.4343,+ "output_price_per_mtok": 0.8686,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6113,9 +6552,9 @@"provider": "deepseek","local_id": "deepseek-v4-flash","context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.0099,- "output_price_per_mtok": 1.28,+ "max_output_tokens": 943717,+ "input_price_per_mtok": 0.091,+ "output_price_per_mtok": 0.182,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6321,7 +6760,32 @@2.0],"is_reasoning_model": false,- "supported_parameters": []+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "logprobs",+ "max_completion_tokens",+ "max_tokens",+ "min_p",+ "parallel_tool_calls",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_a",+ "top_k",+ "top_logprobs",+ "top_p",+ "verbosity"+ ]},"moonshotai/kimi-k2.6": {"id": "moonshotai/kimi-k2.6",@@ -6330,8 +6794,8 @@"local_id": "kimi-k2.6","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.465,- "output_price_per_mtok": 2.45,+ "input_price_per_mtok": 0.65,+ "output_price_per_mtok": 3.41,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6532,8 +6996,8 @@"local_id": "gemma-4-31b-it","context_length": 262144,"max_output_tokens": 16384,- "input_price_per_mtok": 0.09,- "output_price_per_mtok": 0.34,+ "input_price_per_mtok": 0.2,+ "output_price_per_mtok": 0.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6828,9 +7292,9 @@"provider": "minimax","local_id": "minimax-m2.7","context_length": 204800,- "max_output_tokens": 176947,- "input_price_per_mtok": 0.21,- "output_price_per_mtok": 0.84,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 1.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7447,11 +7911,11 @@"id": "qwen/qwen3.5-35b-a3b","name": "Qwen: Qwen3.5-35B-A3B","provider": "qwen",- "local_id": "qwen3.5-35b-a3b",- "context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.08,- "output_price_per_mtok": 0.75,+ "local_id": "qwen3.5-35b-a3b",+ "context_length": 262144,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 1.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7487,9 +7951,9 @@"provider": "qwen","local_id": "qwen3.5-27b","context_length": 262144,- "max_output_tokens": 81920,- "input_price_per_mtok": 0.26,- "output_price_per_mtok": 2.6,+ "max_output_tokens": 65536,+ "input_price_per_mtok": 0.27,+ "output_price_per_mtok": 2.16,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7845,8 +8309,8 @@"local_id": "qwen3.5-397b-a17b","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.55,- "output_price_per_mtok": 3.5,+ "input_price_per_mtok": 0.5,+ "output_price_per_mtok": 3.6,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7882,9 +8346,9 @@"provider": "minimax","local_id": "minimax-m2.5","context_length": 204800,- "max_output_tokens": 128000,+ "max_output_tokens": 32768,"input_price_per_mtok": 0.27,- "output_price_per_mtok": 1.08,+ "output_price_per_mtok": 0.95,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7920,9 +8384,9 @@"provider": "z-ai","local_id": "glm-5","context_length": 204800,- "max_output_tokens": 128000,- "input_price_per_mtok": 0.6,- "output_price_per_mtok": 1.92,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 3.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -7950,41 +8414,6 @@"top_p"]},- "qwen/qwen3-max-thinking": {- "id": "qwen/qwen3-max-thinking",- "name": "Qwen: Qwen3 Max Thinking",- "provider": "qwen",- "local_id": "qwen3-max-thinking",- "context_length": 262144,- "max_output_tokens": 65536,- "input_price_per_mtok": 0.78,- "output_price_per_mtok": 3.9,- "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",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"anthropic/claude-opus-4.6": {"id": "anthropic/claude-opus-4.6","name": "Anthropic: Claude Opus 4.6",@@ -8158,8 +8587,8 @@"local_id": "kimi-k2.5","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.45,- "output_price_per_mtok": 2.25,+ "input_price_per_mtok": 0.5,+ "output_price_per_mtok": 2.5,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -8494,8 +8923,8 @@"local_id": "glm-4.7","context_length": 204800,"max_output_tokens": 131072,- "input_price_per_mtok": 0.6,- "output_price_per_mtok": 2.2,+ "input_price_per_mtok": 0.54,+ "output_price_per_mtok": 1.98,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9117,8 +9546,8 @@"provider": "deepseek","local_id": "deepseek-v3.2","context_length": 163840,- "max_output_tokens": 147456,- "input_price_per_mtok": 0.259,+ "max_output_tokens": 65536,+ "input_price_per_mtok": 0.28,"output_price_per_mtok": 0.42,"supports_thinking": false,"thinking_type": "none",@@ -9360,7 +9789,7 @@"provider": "moonshotai","local_id": "kimi-k2-thinking","context_length": 262144,- "max_output_tokens": 235929,+ "max_output_tokens": 98304,"input_price_per_mtok": 0.6,"output_price_per_mtok": 2.5,"supports_thinking": false,@@ -9510,9 +9939,9 @@"provider": "minimax","local_id": "minimax-m2","context_length": 204800,- "max_output_tokens": 176947,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 1.2,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.255,+ "output_price_per_mtok": 1.02,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9540,39 +9969,6 @@"top_p"]},- "qwen/qwen3-vl-32b-instruct": {- "id": "qwen/qwen3-vl-32b-instruct",- "name": "Qwen: Qwen3 VL 32B Instruct",- "provider": "qwen",- "local_id": "qwen3-vl-32b-instruct",- "context_length": 131072,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.104,- "output_price_per_mtok": 0.416,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "logprobs",- "max_tokens",- "presence_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"ibm-granite/granite-4.0-h-micro": {"id": "ibm-granite/granite-4.0-h-micro","name": "IBM: Granite 4.0 Micro",@@ -9697,50 +10093,15 @@"top_p"]},- "qwen/qwen3-vl-8b-thinking": {- "id": "qwen/qwen3-vl-8b-thinking",- "name": "Qwen: Qwen3 VL 8B Thinking",- "provider": "qwen",- "local_id": "qwen3-vl-8b-thinking",- "context_length": 131072,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.18,- "output_price_per_mtok": 2.1,- "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",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"qwen/qwen3-vl-8b-instruct": {"id": "qwen/qwen3-vl-8b-instruct","name": "Qwen: Qwen3 VL 8B Instruct","provider": "qwen","local_id": "qwen3-vl-8b-instruct","context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.117,- "output_price_per_mtok": 0.455,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.25,+ "output_price_per_mtok": 0.75,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9829,9 +10190,9 @@"provider": "qwen","local_id": "qwen3-vl-30b-a3b-thinking","context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.2,- "output_price_per_mtok": 2.4,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.29,+ "output_price_per_mtok": 1.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9842,19 +10203,14 @@"supported_parameters": ["frequency_penalty","include_reasoning",- "logprobs","max_tokens",- "presence_penalty","reasoning","response_format",- "seed",- "stop","structured_outputs","temperature","tool_choice","tools","top_k",- "top_logprobs","top_p"]},@@ -9958,9 +10314,9 @@"provider": "z-ai","local_id": "glm-4.6","context_length": 204800,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.43,- "output_price_per_mtok": 1.75,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.55,+ "output_price_per_mtok": 2.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10134,41 +10490,6 @@"stop"]},- "qwen/qwen3-vl-235b-a22b-thinking": {- "id": "qwen/qwen3-vl-235b-a22b-thinking",- "name": "Qwen: Qwen3 VL 235B A22B Thinking",- "provider": "qwen",- "local_id": "qwen3-vl-235b-a22b-thinking",- "context_length": 131072,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.4,- "output_price_per_mtok": 4.0,- "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",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"qwen/qwen3-vl-235b-a22b-instruct": {"id": "qwen/qwen3-vl-235b-a22b-instruct","name": "Qwen: Qwen3 VL 235B A22B Instruct",@@ -10205,72 +10526,6 @@"top_p"]},- "qwen/qwen3-max": {- "id": "qwen/qwen3-max",- "name": "Qwen: Qwen3 Max",- "provider": "qwen",- "local_id": "qwen3-max",- "context_length": 262144,- "max_output_tokens": 65536,- "input_price_per_mtok": 0.78,- "output_price_per_mtok": 3.9,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "logprobs",- "max_tokens",- "presence_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },- "qwen/qwen3-coder-plus": {- "id": "qwen/qwen3-coder-plus",- "name": "Qwen: Qwen3 Coder Plus",- "provider": "qwen",- "local_id": "qwen3-coder-plus",- "context_length": 1000000,- "max_output_tokens": 65536,- "input_price_per_mtok": 0.65,- "output_price_per_mtok": 3.25,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "logprobs",- "max_tokens",- "presence_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"deepseek/deepseek-v3.1-terminus": {"id": "deepseek/deepseek-v3.1-terminus","name": "DeepSeek: DeepSeek V3.1 Terminus",@@ -10334,51 +10589,15 @@"top_p"]},- "qwen/qwen3-next-80b-a3b-thinking": {- "id": "qwen/qwen3-next-80b-a3b-thinking",- "name": "Qwen: Qwen3 Next 80B A3B Thinking",- "provider": "qwen",- "local_id": "qwen3-next-80b-a3b-thinking",- "context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.15,- "output_price_per_mtok": 1.2,- "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",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },- "qwen/qwen3-next-80b-a3b-instruct": {- "id": "qwen/qwen3-next-80b-a3b-instruct",- "name": "Qwen: Qwen3 Next 80B A3B Instruct",+ "qwen/qwen3-next-80b-a3b-thinking": {+ "id": "qwen/qwen3-next-80b-a3b-thinking",+ "name": "Qwen: Qwen3 Next 80B A3B Thinking","provider": "qwen",- "local_id": "qwen3-next-80b-a3b-instruct",+ "local_id": "qwen3-next-80b-a3b-thinking","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.1,- "output_price_per_mtok": 1.1,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 1.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10388,11 +10607,11 @@"is_reasoning_model": false,"supported_parameters": ["frequency_penalty",- "logit_bias",+ "include_reasoning","logprobs","max_tokens",- "min_p","presence_penalty",+ "reasoning","repetition_penalty","response_format","seed",@@ -10406,15 +10625,15 @@"top_p"]},- "qwen/qwen-plus-2025-07-28": {- "id": "qwen/qwen-plus-2025-07-28",- "name": "Qwen: Qwen Plus 0728",+ "qwen/qwen3-next-80b-a3b-instruct": {+ "id": "qwen/qwen3-next-80b-a3b-instruct",+ "name": "Qwen: Qwen3 Next 80B A3B Instruct","provider": "qwen",- "local_id": "qwen-plus-2025-07-28",- "context_length": 1000000,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.26,- "output_price_per_mtok": 0.78,+ "local_id": "qwen3-next-80b-a3b-instruct",+ "context_length": 262144,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.09,+ "output_price_per_mtok": 1.1,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10424,9 +10643,12 @@"is_reasoning_model": false,"supported_parameters": ["frequency_penalty",+ "logit_bias","logprobs","max_tokens",+ "min_p","presence_penalty",+ "repetition_penalty","response_format","seed","stop",@@ -10471,38 +10693,6 @@"top_p"]},- "qwen/qwen3-30b-a3b-thinking-2507": {- "id": "qwen/qwen3-30b-a3b-thinking-2507",- "name": "Qwen: Qwen3 30B A3B Thinking 2507",- "provider": "qwen",- "local_id": "qwen3-30b-a3b-thinking-2507",- "context_length": 81920,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.2,- "output_price_per_mtok": 2.4,- "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",- "response_format",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"nousresearch/hermes-4-405b": {"id": "nousresearch/hermes-4-405b","name": "Nous: Hermes 4 405B",@@ -10522,13 +10712,16 @@"supported_parameters": ["frequency_penalty","include_reasoning",+ "logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format",+ "structured_outputs","temperature","top_k",+ "top_logprobs","top_p"]},@@ -10846,9 +11039,9 @@"provider": "openai","local_id": "gpt-oss-120b","context_length": 131072,- "max_output_tokens": 117964,- "input_price_per_mtok": 0.037,- "output_price_per_mtok": 0.17,+ "max_output_tokens": 65536,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 0.6,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -11129,18 +11322,14 @@"is_reasoning_model": false,"supported_parameters": ["frequency_penalty",- "logprobs","max_tokens",- "presence_penalty","response_format",- "seed","stop","structured_outputs","temperature","tool_choice","tools","top_k",- "top_logprobs","top_p"]},@@ -11151,7 +11340,7 @@"local_id": "qwen3-30b-a3b-instruct-2507","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.1,+ "input_price_per_mtok": 0.09,"output_price_per_mtok": 0.3,"supports_thinking": false,"thinking_type": "none",@@ -11244,10 +11433,10 @@"name": "Qwen: Qwen3 235B A22B Thinking 2507","provider": "qwen","local_id": "qwen3-235b-a22b-thinking-2507",- "context_length": 131072,- "max_output_tokens": 117964,- "input_price_per_mtok": 0.23,- "output_price_per_mtok": 2.3,+ "context_length": 128000,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.45,+ "output_price_per_mtok": 3.5,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -11261,8 +11450,6 @@"max_tokens","presence_penalty","reasoning",- "response_format",- "seed","stop","temperature","tool_choice",@@ -11551,8 +11738,8 @@"name": "Morph: Morph V3 Fast","provider": "morph","local_id": "morph-v3-fast",- "context_length": 81920,- "max_output_tokens": 38000,+ "context_length": 262144,+ "max_output_tokens": 131072,"input_price_per_mtok": 0.8,"output_price_per_mtok": 1.2,"supports_thinking": false,@@ -11563,9 +11750,13 @@],"is_reasoning_model": false,"supported_parameters": [+ "logprobs","max_tokens",+ "response_format","stop",- "temperature"+ "structured_outputs",+ "temperature",+ "top_logprobs"]},"mistralai/mistral-small-3.2-24b-instruct": {@@ -11851,34 +12042,6 @@"top_p"]},- "anthropic/claude-sonnet-4": {- "id": "anthropic/claude-sonnet-4",- "name": "Anthropic: Claude Sonnet 4",- "provider": "anthropic",- "local_id": "claude-sonnet-4",- "context_length": 200000,- "max_output_tokens": 64000,- "input_price_per_mtok": 3.0,- "output_price_per_mtok": 15.0,- "supports_thinking": true,- "thinking_type": "budget",- "temperature_range": [- 0.0,- 1.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "include_reasoning",- "max_tokens",- "reasoning",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"mistralai/mistral-medium-3": {"id": "mistralai/mistral-medium-3","name": "Mistral: Mistral Medium 3",@@ -11944,7 +12107,7 @@"name": "Qwen: Qwen3 30B A3B","provider": "qwen","local_id": "qwen3-30b-a3b",- "context_length": 131072,+ "context_length": 40960,"max_output_tokens": 16384,"input_price_per_mtok": 0.12,"output_price_per_mtok": 0.5,@@ -11975,44 +12138,12 @@"top_p"]},- "qwen/qwen3-8b": {- "id": "qwen/qwen3-8b",- "name": "Qwen: Qwen3 8B",- "provider": "qwen",- "local_id": "qwen3-8b",- "context_length": 131072,- "max_output_tokens": 8192,- "input_price_per_mtok": 0.117,- "output_price_per_mtok": 0.455,- "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",- "response_format",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"qwen/qwen3-14b": {"id": "qwen/qwen3-14b","name": "Qwen: Qwen3 14B","provider": "qwen","local_id": "qwen3-14b",- "context_length": 131072,+ "context_length": 40960,"max_output_tokens": 16384,"input_price_per_mtok": 0.12,"output_price_per_mtok": 0.24,@@ -12084,38 +12215,6 @@"top_p"]},- "qwen/qwen3-235b-a22b": {- "id": "qwen/qwen3-235b-a22b",- "name": "Qwen: Qwen3 235B A22B",- "provider": "qwen",- "local_id": "qwen3-235b-a22b",- "context_length": 131072,- "max_output_tokens": 8192,- "input_price_per_mtok": 0.455,- "output_price_per_mtok": 1.82,- "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",- "response_format",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"openai/o4-mini-high": {"id": "openai/o4-mini-high","name": "OpenAI: o4 Mini High",@@ -12422,7 +12521,7 @@"name": "Meta: Llama 4 Maverick","provider": "meta","local_id": "llama-4-maverick",- "context_length": 1048576,+ "context_length": 524288,"max_output_tokens": 16384,"input_price_per_mtok": 0.1875,"output_price_per_mtok": 0.6525,@@ -12596,6 +12695,7 @@"supported_parameters": ["frequency_penalty","logit_bias",+ "logprobs","max_tokens","min_p","presence_penalty",@@ -12606,6 +12706,7 @@"structured_outputs","temperature","top_k",+ "top_logprobs","top_p"]},@@ -12712,7 +12813,7 @@"context_length": 131072,"max_output_tokens": 117964,"input_price_per_mtok": 0.08,- "output_price_per_mtok": 0.45,+ "output_price_per_mtok": 0.35,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -13113,39 +13214,6 @@"web_search_options"]},- "deepseek/deepseek-r1": {- "id": "deepseek/deepseek-r1",- "name": "DeepSeek: R1",- "provider": "deepseek",- "local_id": "deepseek-r1",- "context_length": 64000,- "max_output_tokens": 16000,- "input_price_per_mtok": 0.7,- "output_price_per_mtok": 2.5,- "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",- "response_format",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"minimax/minimax-01": {"id": "minimax/minimax-01","name": "MiniMax: MiniMax-01",@@ -13234,37 +13302,6 @@"top_p"]},- "sao10k/l3.3-euryale-70b": {- "id": "sao10k/l3.3-euryale-70b",- "name": "Sao10K: Llama 3.3 Euryale 70B",- "provider": "sao10k",- "local_id": "l3.3-euryale-70b",- "context_length": 131072,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.65,- "output_price_per_mtok": 0.75,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "logprobs",- "max_tokens",- "presence_penalty",- "repetition_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "top_logprobs",- "top_p"- ]- },"openai/o1": {"id": "openai/o1","name": "OpenAI: o1",@@ -13328,8 +13365,8 @@"local_id": "llama-3.3-70b-instruct","context_length": 131072,"max_output_tokens": 16384,- "input_price_per_mtok": 0.22,- "output_price_per_mtok": 0.5,+ "input_price_per_mtok": 0.1,+ "output_price_per_mtok": 0.32,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -13664,9 +13701,9 @@"provider": "meta","local_id": "llama-3.2-3b-instruct","context_length": 131072,- "max_output_tokens": 117964,- "input_price_per_mtok": 0.05,- "output_price_per_mtok": 0.33,+ "max_output_tokens": 72000,+ "input_price_per_mtok": 0.0509,+ "output_price_per_mtok": 0.335,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -14329,35 +14366,6 @@"top_p"]},- "microsoft/wizardlm-2-8x22b": {- "id": "microsoft/wizardlm-2-8x22b",- "name": "WizardLM-2 8x22B",- "provider": "microsoft",- "local_id": "wizardlm-2-8x22b",- "context_length": 65535,- "max_output_tokens": 8000,- "input_price_per_mtok": 0.62,- "output_price_per_mtok": 0.62,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "max_tokens",- "presence_penalty",- "repetition_penalty",- "response_format",- "seed",- "stop",- "temperature",- "top_k",- "top_p"- ]- },"openai/gpt-4-turbo": {"id": "openai/gpt-4-turbo","name": "OpenAI: GPT-4 Turbo",diff --git a/server/config/pricing.json b/server/config/pricing.jsonindex bfdcb148..8704fd03 100644--- a/server/config/pricing.json+++ b/server/config/pricing.json@@ -1,18 +1,18 @@{- "version": "2026.09",- "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.",+ "version": "2026.10",+ "last_updated": "2026-10-23",+ "_llm_note": "LLM input and output prices follow the OpenRouter registry (model_registry.json, 2026-10-19) 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, 2026-09-29. cache_read is 10% of input, OpenAI's cached-input rate.",+ "_note": "OpenRouter registry, 2026-10-19. 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},"gpt-6-sol-pro": {"input": 2.00, "output": 10.00, "cache_read": 0.20},"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": {"input": 4.00, "output": 20.00, "cache_read": 0.40},"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},@@ -26,7 +26,7 @@"_default": {"input": 2.50, "output": 15.00}},"anthropic": {- "_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.",+ "_note": "OpenRouter registry, 2026-10-19. 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-haiku-5-5 bills prompts over 100K tokens at $0.50/$2.50, which this flat price under-reports. claude-sonnet-4 left the registry; claude-sonnet-4-5, which its prefix used to price, has its own row.","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},@@ -34,17 +34,20 @@"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-opus-4-5": {"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-haiku-5-5": {"input": 0.10, "output": 0.50, "cache_read": 0.01},"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},- "claude-sonnet-4": {"input": 3.00, "output": 15.00, "cache_read": 0.30},+ "claude-sonnet-4-5": {"input": 3.00, "output": 15.00, "cache_read": 0.30},"claude-opus-4-1": {"input": 15.00, "output": 75.00, "cache_read": 1.50},"_default": {"input": 3.00, "output": 15.00, "cache_read": 0.30}},"gemini": {- "_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},+ "_note": "OpenRouter registry, 2026-10-19. 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": 0.825, "output": 4.125},+ "gemini-4-argon": {"input": 2.00, "output": 10.00},"gemini-3.7-flash": {"input": 0.75, "output": 3.75},"gemini-3.6-flash": {"input": 0.75, "output": 3.75},"gemini-3.5-flash-lite": {"input": 0.30, "output": 2.50},@@ -55,8 +58,8 @@"gemini-2.5-pro": {"input": 1.25, "output": 10.00},"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": 0.0765, "output": 0.255},+ "gemma-4-31b-it": {"input": 0.20, "output": 0.40},+ "gemma-4-26b-a4b-it": {"input": 0.09, "output": 0.30},"_default": {"input": 0.50, "output": 3.00}},"groq": {@@ -70,7 +73,7 @@"_default": {"input": 0.15, "output": 0.60}},"xai": {- "_note": "OpenRouter registry, 2026-09-29.",+ "_note": "OpenRouter registry, 2026-10-19.","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},@@ -88,27 +91,27 @@"_default": {"input": 1.00, "output": 5.00}},"deepseek": {- "_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},+ "_note": "OpenRouter registry, 2026-10-19. 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": 0.0344, "output": 0.08, "cache_read": 0.0007},+ "deepseek-v4-flash": {"input": 0.091, "output": 0.182, "cache_read": 0.0018},+ "deepseek-v4-pro": {"input": 0.4343, "output": 0.8686, "cache_read": 0.0143},"_default": {"input": 0.15, "output": 0.60}},"kimi": {- "_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},+ "_note": "OpenRouter registry (under moonshotai/), 2026-10-19. 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": 0.239, "output": 11.936, "cache_read": 0.0239},+ "kimi-k2.7-code": {"input": 0.6712, "output": 3.35, "cache_read": 0.1342},"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/), 2026-09-29. 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.",+ "_note": "OpenRouter registry (under mistralai/), 2026-10-19. 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},"codestral-latest": {"input": 0.30, "output": 0.90},- "mistral-nemo": {"input": 0.019, "output": 0.03},+ "mistral-nemo": {"input": 0.029, "output": 0.03},"_default": {"input": 0.15, "output": 0.60}},"sarvam": {