Self-improving AI Employees for everyone
Python ai-agentsai-employeeai-employeesassistantautonomous-agentsco-employeescompanygrok-botinstinctloop-agentsmuseown-your-datapersonalself-hosted
chore(config): curate models and prices from the 2026-09-15 registry and vendor docs
trohitg8705dbf1fa17
diff --git a/docs-internal/native_llm_sdk.md b/docs-internal/native_llm_sdk.mdindex 44e37d53..f5b5bf50 100644--- a/docs-internal/native_llm_sdk.md+++ b/docs-internal/native_llm_sdk.md@@ -100,13 +100,13 @@ Source of truth for this list: `server/config/llm_defaults.json` (the `providers| **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, 4.5, 4.3, 3 | 131K-2M | 131K | model/provider dependent | 0-2 |-| **DeepSeek** | deepseek-v4-flash (default), deepseek-v4.1-flash, deepseek-v4-pro (deepseek-chat/reasoner legacy) | 1M | 64K | thinking modes | 0-2 |-| **Kimi** | kimi-k3 (default), kimi-k2.6, kimi-k2.5, kimi-k2.7-code | 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, codestral-latest | 256K | 131K | none | 0-1.5 |-| **Groq** | GPT-OSS-120b/20b, Qwen3-32b, legacy Llama 3.x tiers | 131K | 32K-131K | effort (GPT-OSS), format (Qwen3) | 0-2 |-| **OpenRouter** | 200+ models from multiple providers | varies | varies | varies | 0-2 |-| **Cerebras** | GPT-OSS-120b (default; only production model), zai-glm-4.7 + gemma-4-31b (preview) | 131K | 40K | budget (`zai-glm-4.7` only — `thinking_models`) | 0-1.5 |+| **xAI** | Grok 4.20/4.20-multi-agent, 4.6, 4.5, 4.3, 3 | 131K-1M | 131K | model/provider dependent | 0-2 |+| **DeepSeek** | deepseek-flash (default; V4.1-Flash), deepseek-v4.1-flash, deepseek-v4-pro (deepseek-v4-flash is a retired alias served by V4.1-Flash; chat/reasoner discontinued) | 1M | 384K | 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 |+| **OpenRouter** | 400+ models from multiple providers | varies | varies | varies | 0-2 |+| **Cerebras** | GPT-OSS-120b (default), qwen-3.8-27b — the only two public-endpoint models | 131K | 40K | none (`thinking_models` empty since zai-glm-4.7 left the public endpoints) | 0-1.5 || **Ollama** | Whatever the user has pulled (qwen2.5, llama3.x, phi-3, deepseek-r1, ...) | per-loaded-model (typed via `ps()`) | ctx ÷ 4 (capped 4096) | none (per-model) | 0-2 || **LM Studio** | Whatever the user has loaded in the LM Studio UI | per-loaded-model (typed via `LlmInstanceInfo.context_length`) | ctx ÷ 4 (capped 4096) | none (per-model) | 0-2 |@@ -231,7 +231,7 @@ Adding a new OpenAI-compatible provider requires a config entry:```json"deepseek": {- "default_model": "deepseek-v4-flash",+ "default_model": "deepseek-flash","detection_patterns": ["deepseek"],"models_endpoint": "https://api.deepseek.com/models","base_url": "https://api.deepseek.com",@@ -297,8 +297,8 @@ Each provider's `chat()` method reads only the fields it supports. The extracted| **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. || **OpenAI** | GPT-5.6 sol/terra/luna (+ `-pro`), GPT-5.5, GPT-5.4 (`thinking_models: ["gpt-5"]`) | `reasoningEffort` (low/medium/high/xhigh) | effort | Hybrid reasoning: can operate with or without thinking. |-| **Groq** | qwen3-32b (`thinking_models: ["qwen3"]`) | `reasoningFormat` ('parsed' or 'hidden') | format | 'parsed' returns reasoning, 'hidden' returns only final answer. GPT-OSS models on Groq use `reasoning_effort` instead (`openai.py:671-675`). |-| **Cerebras** | zai-glm-4.7 (`thinking_models`) | `thinkingBudget` | budget | Sent as `extra_body.thinking_budget` (`openai.py:111-114`). The qwen-3-235b variants are shut down upstream. |+| **Groq** | qwen/qwen3.8-27b (`thinking_models: ["qwen3"]`, prefix match) | `reasoningFormat` ('parsed' or 'hidden') | format | 'parsed' returns reasoning, 'hidden' returns only final answer. GPT-OSS models on Groq use `reasoning_effort` instead (`openai.py:671-675`). |+| **Cerebras** | none — `thinking_models` is empty since zai-glm-4.7 left the public endpoints (2026-09) | `thinkingBudget` | budget | Would be sent as `extra_body.thinking_budget` (`openai.py:111-114`) if a thinking model were curated again. The qwen-3-235b variants are shut down upstream. |The thinking/reasoning fields (`thinkingEnabled`, `thinkingBudget`, `reasoningEffort`, `reasoningFormat`) live in the backend NodeSpec for each chat model (`server/nodes/model/<provider>_chat_model/`) and are declared once on the shared `ChatModelParams` model in `server/nodes/model/_base.py:24`. The frontend renders them automatically via the universal parameter panel.@@ -340,8 +340,8 @@ The `thinking` field is exposed to downstream nodes via the backend output schem- **OpenAI o-series**: Reasoning summaries are only available to organizations that have completed verification at platform.openai.com. Without verification, `thinking` is `null`.- **Claude (budget models)**: `max_tokens` must be greater than `thinkingBudget`; the provider raises `max_tokens` to `budget + 1024` when it is not. Temperature is automatically set to 1 when thinking is enabled.- **Claude (adaptive models)**: `thinkingBudget` is ignored — the model picks its own depth. No sampling parameters are sent; a user-set temperature is silently dropped for these models rather than rejected.-- **Groq**: Only Qwen3-32b supports format-based reasoning (QwQ removed from Groq). Format `hidden` suppresses reasoning output. GPT-OSS models take `reasoning_effort`.-- **Cerebras**: Only `zai-glm-4.7` (preview) is a thinking model, via `thinking_budget`.+- **Groq**: Only the Qwen3 family (`qwen/qwen3.8-27b` today; qwen3-32b was retired) supports format-based reasoning. Format `hidden` suppresses reasoning output. GPT-OSS models take `reasoning_effort`.+- **Cerebras**: No curated thinking model since `zai-glm-4.7` left the public endpoints; `thinking_budget` support stays in the provider for when one returns.See [memory_compaction.md](memory_compaction.md) for how thinking token counts are tracked separately from output tokens.diff --git a/docs-internal/node-logic-flows/ai_chat_models/cerebrasChatModel.md b/docs-internal/node-logic-flows/ai_chat_models/cerebrasChatModel.mdindex a8b20edf..c9e3c1fb 100644--- a/docs-internal/node-logic-flows/ai_chat_models/cerebrasChatModel.md+++ b/docs-internal/node-logic-flows/ai_chat_models/cerebrasChatModel.md@@ -87,7 +87,7 @@ flowchart TD- **Native OpenAI-compatible path**: `ChatUnifier` resolves the `cerebras`spec registered in `providers/_compat.py` (reuses `OpenAIProvider` with theCerebras `base_url`) for both chat and agent requests.-- **Reasoning**: the curated reasoning-capable model is `zai-glm-4.7`; other current Cerebras models ignore the shared thinking controls.+- **Reasoning**: no curated reasoning-capable model since `zai-glm-4.7` left Cerebras' public endpoints (2026-09); the two current models (`gpt-oss-120b`, `qwen-3.8-27b`) ignore the shared thinking controls.- **Temperature range**: narrower (0-1.5 clamp) than OpenAI/Groq. `_resolve_temperature` applies the clamp.## Side Effectsdiff --git a/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md b/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.mdindex 432cdd45..9ee1f091 100644--- a/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md+++ b/docs-internal/node-logic-flows/ai_chat_models/deepseekChatModel.md@@ -11,7 +11,7 @@## Purpose-DeepSeek V4 models (`deepseek-v4-flash`, `deepseek-v4-pro`); `deepseek-chat` / `deepseek-reasoner` remain as legacy aliases (deprecate 2026-07-24). Uses the OpenAI-compatible DeepSeek endpoint via the `services/llm/providers` layer (native path). The `ChatModelBase.chat` operation calls `AIService.execute_chat`. The plugin docstring describes `deepseek-chat`/`deepseek-reasoner` (V3) but the registry description in `__init__.py` predates the V4 rename - the card's V4 listing reflects current `llm_defaults.json`.+DeepSeek V4.1 models (`deepseek-flash`, `deepseek-v4.1-flash`, `deepseek-v4-pro`); `deepseek-v4-flash` is a retired alias still served by V4.1-Flash, and `deepseek-chat` / `deepseek-reasoner` were discontinued in July 2026. Uses the OpenAI-compatible DeepSeek endpoint via the `services/llm/providers` layer (native path). The `ChatModelBase.chat` operation calls `AIService.execute_chat`. The plugin docstring describes `deepseek-chat`/`deepseek-reasoner` (V3) but the registry description in `__init__.py` predates the V4 rename - the card's V4 listing reflects current `llm_defaults.json`.## Inputs (handles)@@ -25,7 +25,7 @@ DeepSeek V4 models (`deepseek-v4-flash`, `deepseek-v4-pro`); `deepseek-chat` / `|------|------|---------|----------|---------------------|-------------|| `prompt` | string | `""` | yes | - | User message || `system_prompt` | string | `""` | no | - | System prompt |-| `model` | string | `""` (injected) | no | - | `deepseek-v4-flash` / `deepseek-v4-pro`; `deepseek-chat` / `deepseek-reasoner` legacy aliases (reasoner = always-on CoT) |+| `model` | string | `""` (injected) | no | - | `deepseek-flash` / `deepseek-v4.1-flash` / `deepseek-v4-pro`; `deepseek-v4-flash` retired alias (served by V4.1-Flash) || `temperature` | number\|null | `null` | no | - | 0-2 || `max_tokens` | number\|null | `null` (8-64K) | no | - | 1-200000 || `top_p` | number\|null | `1.0` | no | - | |diff --git a/docs-internal/node-logic-flows/ai_chat_models/groqChatModel.md b/docs-internal/node-logic-flows/ai_chat_models/groqChatModel.mdindex 36e5768c..17b39681 100644--- a/docs-internal/node-logic-flows/ai_chat_models/groqChatModel.md+++ b/docs-internal/node-logic-flows/ai_chat_models/groqChatModel.md@@ -29,7 +29,7 @@ Bare chat and current agent executions share this native provider path.|------|------|---------|----------|---------------------|-------------|| `prompt` | string | `""` | yes | - | User message || `system_prompt` | string | `""` | no | - | System prompt |-| `model` | string | `""` (injected) | no | - | e.g. `llama-3.1-70b-versatile`, `qwen/qwen3-32b`, `groq/compound-beta` |+| `model` | string | `""` (injected) | no | - | e.g. `llama-3.1-70b-versatile`, `qwen/qwen3.8-27b`, `groq/compound-beta` || `temperature` | number\|null | `null` | no | - | 0-2 || `max_tokens` | number\|null | `null` (8-131K per model) | no | - | 1-200000 || `top_p` | number\|null | `1.0` | no | - | |@@ -85,7 +85,7 @@ flowchart TDregistered in `providers/_compat.py` (reuses `OpenAIProvider` with the`base_url` from `llm_defaults.json`) for both chat and agent requests.- **Reasoning**: only Qwen3-32b actually honors `reasoningFormat`. Non-Qwen models ignore the flag.-- **Model ID handling**: only the UI-only `[FREE] ` decoration is stripped. Owner-qualified IDs such as `openai/gpt-oss-120b` and `qwen/qwen3-32b` are preserved because Groq requires them.+- **Model ID handling**: only the UI-only `[FREE] ` decoration is stripped. Owner-qualified IDs such as `openai/gpt-oss-120b` and `qwen/qwen3.8-27b` are preserved because Groq requires them.## Side Effectsdiff --git a/docs-internal/workflow-schema.md b/docs-internal/workflow-schema.mdindex c0d08c9a..b3d830f5 100644--- a/docs-internal/workflow-schema.md+++ b/docs-internal/workflow-schema.md@@ -91,7 +91,7 @@ A workflow JSON document contains:- `openrouterChatModel` - OpenRouter unified API (200+ models)- `groqChatModel` - Groq ultra-fast inference (Llama, Qwen3, GPT-OSS)- `cerebrasChatModel` - Cerebras custom AI hardware (Llama, Qwen)-- `deepseekChatModel` - DeepSeek V4 (deepseek-v4-flash / deepseek-v4.1-flash / deepseek-v4-pro; chat/reasoner legacy aliases)+- `deepseekChatModel` - DeepSeek V4.1 (deepseek-flash / deepseek-v4.1-flash / deepseek-v4-pro; deepseek-v4-flash is a retired alias served by V4.1-Flash, chat/reasoner discontinued)- `kimiChatModel` - Moonshot Kimi K2.6 / K2.5 / K2.7-code- `mistralChatModel` - Mistral Large / Small / Codestral- `ollamaChatModel` - Local Ollama server (OpenAI-compat via `{provider}_proxy` URL)diff --git a/server/config/llm_defaults.json b/server/config/llm_defaults.jsonindex be803778..20d4380e 100644--- a/server/config/llm_defaults.json+++ b/server/config/llm_defaults.json@@ -1,6 +1,6 @@{- "version": "2026.09.11",- "last_updated": "2026-09-11",+ "version": "2026.09.15",+ "last_updated": "2026-09-15","_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). 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 (OpenRouter cache).","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": "GPT-6 Astra (+ -pro) appear in the 2026-09-11 registry refresh ($10/$50 per MTok, 1.05M context, 128K max output, effort thinking) and are curated as the top tier; the default stays gpt-5.6-sol ($2/$10), the same price-over-flagship call as anthropic keeping claude-opus-5 over claude-fable-5-1. 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-5.6 family (sol/terra/luna) GA 2026-07-09. gpt-5.5 / gpt-5.4 remain GA as legacy tiers. Dropped: gpt-5.2 (new requests blocked 2026-06-30), o3 (API shutdown 2026-12-11), o4-mini (API shutdown 2026-10-23) — they fall back to _default constraints if still selected before shutdown.",+ "_models_note": "GPT-6 Astra (+ -pro) appear in the 2026-09-11 registry refresh ($10/$50 per MTok, 1.05M context, 128K max output, effort thinking) and are curated as the top tier; the default stays gpt-5.6-sol ($4/$20 per developers.openai.com/api/docs/pricing on 2026-09-15 — terra $2/$12, luna $0.20/$1.20; the router cache under-reports sol at $2/$10), the same price-over-flagship call as anthropic keeping claude-opus-5 over claude-fable-5-1. The rolling -latest aliases (gpt-astra-latest, gpt-sol-latest, gpt-terra-latest, gpt-luna-latest) and the gpt-5.6 alias for Sol are deliberately not curated: real model names only, like gemini. GPT-5.6 family (sol/terra/luna) GA 2026-07-09. gpt-5.5 / gpt-5.4 remain GA as legacy tiers. Dropped: gpt-5.2 (new requests blocked 2026-06-30), o3 (API shutdown 2026-12-11), o4-mini (API shutdown 2026-10-23) — they fall back to _default constraints if still selected before shutdown.","max_output_tokens": {"gpt-5.6-sol": 128000,"gpt-6-astra": 128000,@@ -64,7 +64,7 @@"display_name": "Anthropic","default_model": "claude-opus-5","popular_models": ["claude-opus-5", "claude-fable-5-1", "claude-fable-5", "claude-sonnet-5", "claude-opus-4-8", "claude-opus-4-7", "claude-sonnet-4-6"],- "_models_note": "claude-opus-5 (released 2026-07-24) is the Opus flagship and default: near-Fable intelligence at Opus pricing ($5/$25), 1M context, 128K max output. claude-fable-5-1 (registry 2026-09-03: $10/$50, 1M context, 128K max output) is the most capable generally available model and supersedes claude-fable-5, which stays curated as the cheaper prior tier. The adaptive-thinking / sampling-removed lists below match by prefix, so the existing claude-fable-5 entries cover 5.1. The claude-opus-5-fast variant (2x pricing) is deliberately not curated here; select it via the live dropdown if needed.",+ "_models_note": "claude-opus-5 (released 2026-07-24) is the Opus flagship and default: near-Fable intelligence at Opus pricing ($5/$25), 1M context, 128K max output. claude-fable-5-1 (registry 2026-09-03: $10/$50, 1M context, 128K max output) is the most capable generally available model (platform.claude.com/docs/en/models/overview on 2026-09-15: cache reads are 2.5% of input on 5.1 versus 10% elsewhere; claude-sonnet-5 is $2/$10) and supersedes claude-fable-5, which stays curated as the same-priced prior tier. The adaptive-thinking / sampling-removed lists below match by prefix, so the existing claude-fable-5 entries cover 5.1. The claude-opus-5-fast variant (2x pricing) is deliberately not curated here; select it via the live dropdown if needed.","detection_patterns": ["claude", "anthropic"],"base_url": "https://api.anthropic.com/v1","models_endpoint": "https://api.anthropic.com/v1/models",@@ -165,7 +165,7 @@"_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 (new default) and gemini-3.7-flash appear in the 2026-09-03 registry refresh with the same shape as 3.6 Flash (1M context / 65536 max output, $0.75/$3.75 per the OpenRouter cache); they are curated from the registry and 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. gemini-3.6-flash and gemini-3.5-flash-lite launched 2026-07-21; Flash-Lite is $0.30/$2.50. gemini-3.5-pro is still not GA on the public API (enterprise Vertex preview only) so it stays out of the curated list.",+ "_new_models_note": "gemini-3.8-flash (default) is stable on the Gemini API per ai.google.dev/gemini-api/docs/models/gemini-3.8-flash (2026-09-15: 1,048,576 in / 65,536 out, thinking levels low/medium/high, minimal rejected); gemini-3.7-flash shares the shape. 3.6/3.7/3.8 Flash are $0.75/$3.75 until 2027-01-01, then $1.50/$7.50 (Gemini pricing page); gemini-3.5-flash is $1.50/$9.00, Flash-Lite $0.30/$2.50. 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. gemini-3.8-live and the transcribe / TTS / image models are different endpoints and stay out of the chat list. gemini-3.5-pro is still not GA on the public API (enterprise Vertex preview only) so it stays out of the curated list.","thinking_type": "budget","temperature_range": [0.0, 2.0],"_incompatible_models_note": "Models that the dropdown should hide because they need a different API endpoint than `generate_content`. antigravity-preview-05-2026 requires the Interactions API; selecting it currently surfaces a `google.genai.errors.APIError`. ChatUnifier reads this list in fetch_models and filters before returning. Drop entries here when the unifier gains routing support for the alternate endpoint.",@@ -174,7 +174,7 @@"openrouter": {"display_name": "OpenRouter","default_model": "anthropic/claude-sonnet-5",- "popular_models": ["anthropic/claude-sonnet-5", "openai/gpt-5.6-terra", "openai/gpt-5.6-sol", "openai/gpt-6-astra", "google/gemini-3.5-flash", "moonshotai/kimi-k3", "x-ai/grok-4.20"],+ "popular_models": ["anthropic/claude-sonnet-5", "anthropic/claude-opus-5", "openai/gpt-5.6-terra", "openai/gpt-5.6-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"],"detection_patterns": ["openrouter"],"base_url": "https://openrouter.ai/api/v1","models_endpoint": "https://openrouter.ai/api/v1/models",@@ -199,13 +199,14 @@"models_endpoint": "https://api.groq.com/openai/v1/models","api_key_param": "api_key","max_tokens_param": "max_tokens",- "_models_note": "Default moved to openai/gpt-oss-120b (production route). Groq announced deprecation of llama-3.3-70b-versatile and llama-3.1-8b-instant on 2026-06-17 (console.groq.com/docs/deprecations); kept in the list while still served — they fall back to _default constraints after removal.",+ "_models_note": "Default moved to openai/gpt-oss-120b (production route). console.groq.com/docs/models on 2026-09-15 lists the production text models as llama-3.1-8b-instant, llama-3.3-70b-versatile and the two GPT-OSS sizes (Groq had announced the Llama deprecations on 2026-06-17; they are still served). qwen/qwen3-32b is gone; the preview text models are qwen/qwen3.8-27b (131072 context, 16384 max completion) and minimaxai/minimax-m2.7 (196608 / 131072), curated with those documented caps.","max_output_tokens": {"openai/gpt-oss-120b": 65536,"openai/gpt-oss-20b": 65536,"llama-3.3-70b-versatile": 32768,"llama-3.1-8b-instant": 131072,- "qwen/qwen3-32b": 40960,+ "qwen/qwen3.8-27b": 16384,+ "minimaxai/minimax-m2.7": 131072,"_default": 8192},"context_length": {@@ -213,7 +214,8 @@"openai/gpt-oss-20b": 131072,"llama-3.3-70b-versatile": 131072,"llama-3.1-8b-instant": 131072,- "qwen/qwen3-32b": 131072,+ "qwen/qwen3.8-27b": 131072,+ "minimaxai/minimax-m2.7": 196608,"_default": 131072},"thinking_models": ["qwen3"],@@ -225,25 +227,24 @@"default_model": "gpt-oss-120b","popular_models": [],"_popular_note": "Empty per the 1M-context policy — no Cerebras model reaches 1M (all 131072). Models remain reachable via live fetch_models.",- "detection_patterns": ["cerebras", "gpt-oss", "zai-glm", "gemma-4"],+ "detection_patterns": ["cerebras", "gpt-oss", "qwen-3", "zai-glm", "gemma-4"],"base_url": "https://api.cerebras.ai/v1","models_endpoint": "https://api.cerebras.ai/v1/models","api_key_param": "api_key","max_tokens_param": "max_tokens",- "_models_note": "Per inference-docs.cerebras.ai 2026-07-11: gpt-oss-120b is the only production model (paid tier 131k context / 40k max completion); zai-glm-4.7 and gemma-4-31b are preview. qwen-3-235b* variants are shut down (migration target: gpt-oss-120b).",+ "_models_note": "Per inference-docs.cerebras.ai/models/overview on 2026-09-15 the public endpoints serve exactly two models: gpt-oss-120b (65K free / 131K paid context) and qwen-3.8-27b (64K free / 128K paid). zai-glm-4.7 and gemma-4-31b are no longer listed and were dropped from the curated maps (the zai-glm / gemma-4 detection patterns stay so an old node parameter is still recognised rather than silently swapped); other families exist only on Dedicated Endpoints. Max completion is undocumented for qwen-3.8-27b; the curated 40960 mirrors gpt-oss-120b and the registry cache wins when present. qwen-3-235b* variants are shut down.","max_output_tokens": {"gpt-oss-120b": 40960,- "zai-glm-4.7": 40960,- "gemma-4-31b": 40960,+ "qwen-3.8-27b": 40960,"_default": 8192},"context_length": {"gpt-oss-120b": 131072,- "zai-glm-4.7": 131072,- "gemma-4-31b": 131072,+ "qwen-3.8-27b": 131072,"_default": 131072},- "thinking_models": ["zai-glm-4.7"],+ "thinking_models": [],+ "_thinking_note": "Empty since zai-glm-4.7 left the public endpoints: Cerebras documents no thinking control for gpt-oss-120b or qwen-3.8-27b, so nothing is sent.","thinking_type": "budget","temperature_range": [0.0, 1.5]},@@ -251,13 +252,13 @@"display_name": "xAI","default_model": "grok-4.20","popular_models": ["grok-4.20", "grok-4.20-multi-agent", "grok-4.3"],- "_popular_note": "grok-4.6 (registry 2026-09-03, 500K context, $2/$6), grok-4.5 (released 2026-07-08) and grok-3 excluded per the 1M-context policy (500K / 500K / 131072); reachable via live fetch_models. Default stays grok-4.20 (2M) so the default is selectable from the global list.",+ "_popular_note": "grok-4.6 (registry 2026-09-03, 500K context, $2/$6), grok-4.5 (released 2026-07-08) and grok-3 excluded per the 1M-context policy (500K / 500K / 131072); reachable via live fetch_models. Default stays grok-4.20 (1M) so the default is selectable from the global list.","detection_patterns": ["grok", "xai"],"base_url": "https://api.x.ai/v1","models_endpoint": "https://api.x.ai/v1/models","api_key_param": "api_key","max_tokens_param": "max_tokens",- "_models_note": "grok-4.5 (released 2026-07-08): 500K context, configurable reasoning effort (default high), $2/$6 per MTok. Output cap undocumented by xAI — curated 131072 matches the rest of the grok family; registry cache wins when present.",+ "_models_note": "grok-4.20 is documented at 1,000,000 context on docs.x.ai/docs/models/grok-4.20 (2026-09-15; the router cache says 2M, the vendor number wins) at $1.25/$2.50, tiered to $2.50/$5.00 once the prompt passes 200K tokens; the bare grok-4.20 id is accepted alongside the dated grok-4.20-0309-reasoning ids and grok-4.20-multi-agent-0309. grok-4.6 and grok-4.5: 500K context, reasoning effort low/medium/high/xhigh (default high), $2/$6 tiered to $4/$12. Output cap undocumented by xAI — curated 131072 matches the rest of the grok family; registry cache wins when present.","max_output_tokens": {"grok-4.6": 131072,"grok-4.5": 131072,@@ -267,8 +268,8 @@"_default": 8192},"context_length": {- "grok-4.20": 2000000,- "grok-4.20-multi-agent": 2000000,+ "grok-4.20": 1000000,+ "grok-4.20-multi-agent": 1000000,"grok-4.6": 500000,"grok-4.5": 500000,"grok-4.3": 1000000,@@ -279,10 +280,10 @@},"deepseek": {"display_name": "DeepSeek",- "default_model": "deepseek-v4-flash",- "popular_models": ["deepseek-v4-flash", "deepseek-v4.1-flash", "deepseek-v4-pro"],- "_popular_note": "deepseek-chat / deepseek-reasoner dropped from the global list per the 1M-context policy (131072); reachable via live fetch_models.",- "_models_note": "deepseek-v4.1-flash appears in the 2026-09-11 registry refresh ($0.15/$0.60 per MTok, 1M context; the router cache reports a 384K max output, curated at the same 65536 as v4-flash until DeepSeek documents the cap). Default stays deepseek-v4-flash ($0.085/$0.17). Dated snapshots (-0731 / -0813), the vision-exp preview and the -latest alias are deliberately not curated.",+ "default_model": "deepseek-flash",+ "popular_models": ["deepseek-flash", "deepseek-v4.1-flash", "deepseek-v4-pro"],+ "_popular_note": "All three curated ids are 1M-context; deepseek-v4-flash stays in the maps only as the retired alias DeepSeek still accepts.",+ "_models_note": "Per api-docs.deepseek.com (updates + pricing, 2026-09-15): DeepSeek-V4.1-Flash shipped 2026-09-10 as deepseek-flash (native multimodal, 1M context, 384K max output, $0.15/$0.60 per MTok off-peak, cache hit $0.003; peak hours 01:00-04:00 and 06:00-10:00 UTC Mon-Fri double it). deepseek-v4-flash and deepseek-v4-flash-vision-exp are retired names that still resolve to V4.1-Flash at the Flash price, so the default moved to deepseek-flash. deepseek-v4-pro (GA 2026-08-13, kept past 2026-09-14) is 1M / 384K at $0.66/$1.98 off-peak. deepseek-chat and deepseek-reasoner were discontinued three months after the 2026-04-24 V4 launch and are no longer curated. Dated snapshots (-0731 / -0813) and the -latest aliases are deliberately not curated.","detection_patterns": ["deepseek"],"base_url": "https://api.deepseek.com","models_endpoint": "https://api.deepseek.com/models",@@ -290,22 +291,20 @@"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-flash": 65536,- "deepseek-v4.1-flash": 65536,- "deepseek-v4-pro": 65536,- "deepseek-chat": 8192,- "deepseek-reasoner": 65536,+ "deepseek-flash": 384000,+ "deepseek-v4.1-flash": 384000,+ "deepseek-v4-pro": 384000,+ "deepseek-v4-flash": 384000,"_default": 8192},"context_length": {- "deepseek-v4-flash": 1048576,+ "deepseek-flash": 1048576,"deepseek-v4.1-flash": 1048576,"deepseek-v4-pro": 1048576,- "deepseek-chat": 131072,- "deepseek-reasoner": 131072,+ "deepseek-v4-flash": 1048576,"_default": 131072},- "reasoning_models": ["deepseek-reasoner"],+ "reasoning_models": [],"temperature_range": [0.0, 2.0]},"kimi": {@@ -313,27 +312,27 @@"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": "kimi-k3 GA (platform.kimi.ai): 2.8T params, 1M context, vision + tool calling + structured outputs, $3/$15 per MTok ($0.30 cache-hit). Default max_completion_tokens 131072 (configurable up to the full window). k2.x kept as cheaper tiers.",+ "_models_note": "kimi-k3 GA (platform.kimi.ai): 2.8T params, 1M context, vision + tool calling + structured outputs, $3/$15 per MTok ($0.30 cache-hit). Default max_completion_tokens 131072 (configurable up to the full window). platform.kimi.ai/docs/pricing/chat (2026-09-15) lists kimi-k2.7-code ($0.95/$4.00, cache hit $0.19), kimi-k2.7-code-highspeed ($1.90/$8.00) and kimi-k2.6 ($0.95/$4.00, cache hit $0.16) as the remaining k2 tiers; kimi-k2.5 is no longer listed and was dropped from the curated maps.","detection_patterns": ["kimi", "moonshot"],"base_url": "https://api.moonshot.ai/v1","models_endpoint": "https://api.moonshot.ai/v1/models","api_key_param": "api_key","max_tokens_param": "max_tokens","supported_params": ["temperature", "max_tokens", "top_p", "frequency_penalty", "presence_penalty", "stop", "seed", "tools", "tool_choice", "response_format"],- "thinking_default_on": ["kimi-k2.6", "kimi-k2.5", "kimi-k2.7-code"],- "fixed_temperature": {"kimi-k2.6": 0.6, "kimi-k2.5": 0.6, "kimi-k2.7-code": 0.6},+ "thinking_default_on": ["kimi-k2.6", "kimi-k2.7-code", "kimi-k2.7-code-highspeed"],+ "fixed_temperature": {"kimi-k2.6": 0.6, "kimi-k2.7-code": 0.6, "kimi-k2.7-code-highspeed": 0.6},"max_output_tokens": {"kimi-k3": 131072,"kimi-k2.6": 32768,- "kimi-k2.5": 98304,"kimi-k2.7-code": 98304,+ "kimi-k2.7-code-highspeed": 98304,"_default": 8192},"context_length": {"kimi-k3": 1048576,"kimi-k2.6": 262144,- "kimi-k2.5": 262144,"kimi-k2.7-code": 262144,+ "kimi-k2.7-code-highspeed": 262144,"_default": 262144},"temperature_range": [0.0, 1.0]@@ -342,7 +341,8 @@"display_name": "Mistral","default_model": "mistral-large-latest","popular_models": [],- "_popular_note": "Empty per the 1M-context policy — Mistral tops out at 262144 (large/medium). Models remain reachable via live fetch_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 -latest aliases resolve (docs.mistral.ai models overview, 2026-09-15) to mistral-medium-3504 (Medium 3.5, 256K), mistral-small-2603 (Small 4, 256K, $0.15/$0.60), mistral-large-2512 (Large 3, 256K, $0.50/$1.50) and codestral-2508 ($0.30/$0.90). Mistral does not publish max-output caps; the curated values are conservative and the registry cache wins when present.","detection_patterns": ["mistral", "codestral"],"base_url": "https://api.mistral.ai/v1","models_endpoint": "https://api.mistral.ai/v1/models",@@ -359,7 +359,7 @@"context_length": {"mistral-large-latest": 262144,"mistral-medium-latest": 262144,- "mistral-small-latest": 32768,+ "mistral-small-latest": 262144,"codestral-latest": 256000,"_default": 131072},@@ -370,7 +370,7 @@"default_model": "sarvam-105b","popular_models": [],"_popular_note": "Empty per the 1M-context policy — sarvam-105b tops out at 131072. Both models stay reachable via the per-node dropdown (fetch_models returns the curated list) and via the global selector, which falls back to the max_output_tokens keys when popular_models is empty.",- "_models_note": "sarvam-105b (128K ctx) and sarvam-30b (64K ctx), OpenAI-compatible at api.sarvam.ai/v1. sarvam-m is deprecated/removed and deliberately absent. Reasoning is ON by default (reasoning_effort defaults to 'medium' server-side) and the trace comes back as message.reasoning_content, which OpenAIProvider._normalize already reads.",+ "_models_note": "sarvam-105b (128K ctx) and sarvam-30b (64K ctx), OpenAI-compatible at api.sarvam.ai/v1. sarvam-m is deprecated/removed and deliberately absent. docs.sarvam.ai (2026-09-15) also lists sarvam-105b-conversations (32K) and beta third-party routes (Gemma-4 31B, GLM 5.2 / 5.3 / 5.3 Flash, DeepSeek V4 Flash) on the pricing page without documenting their API ids, so they are not curated. Reasoning is ON by default (reasoning_effort defaults to 'medium' server-side) and the trace comes back as message.reasoning_content, which OpenAIProvider._normalize already reads.","detection_patterns": ["sarvam"],"base_url": "https://api.sarvam.ai/v1","models_endpoint": "",diff --git a/server/config/model_registry.json b/server/config/model_registry.jsonindex c17cdb5a..3f17ee37 100644--- a/server/config/model_registry.json+++ b/server/config/model_registry.json@@ -1,11 +1,955 @@{- "_generated": "2026-09-11T20:22:56.766352+00:00",+ "_generated": "2026-09-24T07:52:57.403085+00:00","_source": "openrouter",- "_model_count": 443,+ "_model_count": 458,"models": {+ "fireworks/ember-1": {+ "id": "fireworks/ember-1",+ "name": "Fireworks: Ember-1",+ "provider": "fireworks",+ "local_id": "ember-1",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 3.0,+ "output_price_per_mtok": 15.0,+ "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",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "z-ai/glm-5.3-prime": {+ "id": "z-ai/glm-5.3-prime",+ "name": "Z.ai: GLM 5.3 Prime",+ "provider": "z-ai",+ "local_id": "glm-5.3-prime",+ "context_length": 1000000,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 2.8,+ "output_price_per_mtok": 8.8,+ "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",+ "reasoning_effort",+ "response_format",+ "seed",+ "stop",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "qwen/qwen3.8-max-prime": {+ "id": "qwen/qwen3.8-max-prime",+ "name": "Qwen: Qwen3.8 Max Prime",+ "provider": "qwen",+ "local_id": "qwen3.8-max-prime",+ "context_length": 1000000,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 4.0,+ "output_price_per_mtok": 12.0,+ "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",+ "reasoning_effort",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "stealth/space-bunny-alpha": {+ "id": "stealth/space-bunny-alpha",+ "name": "Space Bunny Alpha",+ "provider": "stealth",+ "local_id": "space-bunny-alpha",+ "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"+ ]+ },+ "aion-labs/aion-3.5-mini": {+ "id": "aion-labs/aion-3.5-mini",+ "name": "AionLabs: Aion 3.5 Mini",+ "provider": "aion-labs",+ "local_id": "aion-3.5-mini",+ "context_length": 262144,+ "max_output_tokens": 32768,+ "input_price_per_mtok": 0.7,+ "output_price_per_mtok": 1.4,+ "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"+ ]+ },+ "aion-labs/aion-3.5": {+ "id": "aion-labs/aion-3.5",+ "name": "AionLabs: Aion 3.5",+ "provider": "aion-labs",+ "local_id": "aion-3.5",+ "context_length": 262144,+ "max_output_tokens": 32768,+ "input_price_per_mtok": 3.0,+ "output_price_per_mtok": 6.0,+ "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"+ ]+ },+ "upstage/solar-mini4": {+ "id": "upstage/solar-mini4",+ "name": "Upstage: Solar Mini 4",+ "provider": "upstage",+ "local_id": "solar-mini4",+ "context_length": 524288,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.2,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "max_tokens",+ "parallel_tool_calls",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "cohere/command-a-plus": {+ "id": "cohere/command-a-plus",+ "name": "Cohere: Command A+",+ "provider": "cohere",+ "local_id": "command-a-plus",+ "context_length": 192000,+ "max_output_tokens": 64000,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 1.5,+ "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",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tools",+ "top_k",+ "top_p"+ ]+ },+ "openai/gpt-6-luna-pro": {+ "id": "openai/gpt-6-luna-pro",+ "name": "OpenAI: GPT-6 Luna Pro",+ "provider": "openai",+ "local_id": "gpt-6-luna-pro",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 0.1,+ "output_price_per_mtok": 0.5,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-luna-pro:batch": {+ "id": "openai/gpt-6-luna-pro:batch",+ "name": "OpenAI: GPT-6 Luna Pro (batch)",+ "provider": "openai",+ "local_id": "gpt-6-luna-pro:batch",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.25,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-luna": {+ "id": "openai/gpt-6-luna",+ "name": "OpenAI: GPT-6 Luna",+ "provider": "openai",+ "local_id": "gpt-6-luna",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 0.1,+ "output_price_per_mtok": 0.5,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-luna:batch": {+ "id": "openai/gpt-6-luna:batch",+ "name": "OpenAI: GPT-6 Luna (batch)",+ "provider": "openai",+ "local_id": "gpt-6-luna:batch",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.25,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-sol-pro": {+ "id": "openai/gpt-6-sol-pro",+ "name": "OpenAI: GPT-6 Sol Pro",+ "provider": "openai",+ "local_id": "gpt-6-sol-pro",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 10.0,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-sol-pro:batch": {+ "id": "openai/gpt-6-sol-pro:batch",+ "name": "OpenAI: GPT-6 Sol Pro (batch)",+ "provider": "openai",+ "local_id": "gpt-6-sol-pro:batch",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 5.0,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-sol": {+ "id": "openai/gpt-6-sol",+ "name": "OpenAI: GPT-6 Sol",+ "provider": "openai",+ "local_id": "gpt-6-sol",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 2.0,+ "output_price_per_mtok": 10.0,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_completion_tokens",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "openai/gpt-6-sol:batch": {+ "id": "openai/gpt-6-sol:batch",+ "name": "OpenAI: GPT-6 Sol (batch)",+ "provider": "openai",+ "local_id": "gpt-6-sol:batch",+ "context_length": 1050000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 1.0,+ "output_price_per_mtok": 5.0,+ "supports_thinking": true,+ "thinking_type": "effort",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "include_reasoning",+ "max_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "seed",+ "structured_outputs",+ "tool_choice",+ "tools"+ ]+ },+ "anthropic/claude-opus-5.5": {+ "id": "anthropic/claude-opus-5.5",+ "name": "Anthropic: Claude Opus 5.5",+ "provider": "anthropic",+ "local_id": "claude-opus-5.5",+ "context_length": 1000000,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 4.0,+ "output_price_per_mtok": 20.0,+ "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-opus-5.5:batch": {+ "id": "anthropic/claude-opus-5.5:batch",+ "name": "Anthropic: Claude Opus 5.5 (batch)",+ "provider": "anthropic",+ "local_id": "claude-opus-5.5:batch",+ "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_tokens",+ "reasoning",+ "reasoning_effort",+ "response_format",+ "stop",+ "structured_outputs",+ "tool_choice",+ "tools",+ "verbosity"+ ]+ },+ "xiaomi/mimo-v2.6-pro-ultraspeed": {+ "id": "xiaomi/mimo-v2.6-pro-ultraspeed",+ "name": "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",+ "provider": "xiaomi",+ "local_id": "mimo-v2.6-pro-ultraspeed",+ "context_length": 1048576,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 4.35,+ "output_price_per_mtok": 8.7,+ "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",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },+ "xiaomi/mimo-v2.6-flash": {+ "id": "xiaomi/mimo-v2.6-flash",+ "name": "Xiaomi: MiMo-V2.6-Flash",+ "provider": "xiaomi",+ "local_id": "mimo-v2.6-flash",+ "context_length": 1048576,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.14,+ "output_price_per_mtok": 0.28,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_p"+ ]+ },+ "xiaomi/mimo-v2.6-pro": {+ "id": "xiaomi/mimo-v2.6-pro",+ "name": "Xiaomi: MiMo-V2.6-Pro",+ "provider": "xiaomi",+ "local_id": "mimo-v2.6-pro",+ "context_length": 1048576,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.435,+ "output_price_per_mtok": 0.87,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "include_reasoning",+ "logit_bias",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "reasoning",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_p"+ ]+ },+ "xai/grok-4.7": {+ "id": "x-ai/grok-4.7",+ "name": "SpaceXAI: Grok 4.7",+ "provider": "xai",+ "local_id": "grok-4.7",+ "context_length": 500000,+ "max_output_tokens": 450000,+ "input_price_per_mtok": 1.6,+ "output_price_per_mtok": 4.8,+ "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",+ "response_format",+ "seed",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_logprobs",+ "top_p"+ ]+ },+ "qwen/qwen3.8-omni-flash": {+ "id": "qwen/qwen3.8-omni-flash",+ "name": "Qwen: Qwen3.8 Omni Flash",+ "provider": "qwen",+ "local_id": "qwen3.8-omni-flash",+ "context_length": 1000000,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 0.47,+ "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"+ ]+ },+ "prism-ml/ternary-bonsai-2-27b": {+ "id": "prism-ml/ternary-bonsai-2-27b",+ "name": "PrismML: Ternary Bonsai 2 27B",+ "provider": "prism-ml",+ "local_id": "ternary-bonsai-2-27b",+ "context_length": 262144,+ "max_output_tokens": 32768,+ "input_price_per_mtok": 0.075,+ "output_price_per_mtok": 0.5,+ "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",+ "reasoning_effort",+ "repetition_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_k",+ "top_logprobs",+ "top_p"+ ]+ },+ "z-ai/glm-5.3-flashx": {+ "id": "z-ai/glm-5.3-flashx",+ "name": "Z.ai: GLM 5.3 FlashX",+ "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,+ "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"+ ]+ },+ "deepseek/deepseek-pro-latest": {+ "id": "~deepseek/deepseek-pro-latest",+ "name": "DeepSeek: DeepSeek Pro Latest",+ "provider": "deepseek",+ "local_id": "deepseek-pro-latest",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.39,+ "output_price_per_mtok": 2.9,+ "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"+ ]+ },+ "deepseek/deepseek-flash-latest": {+ "id": "~deepseek/deepseek-flash-latest",+ "name": "DeepSeek: DeepSeek Flash Latest",+ "provider": "deepseek",+ "local_id": "deepseek-flash-latest",+ "context_length": 1048576,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.04,+ "output_price_per_mtok": 1.0,+ "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"+ ]+ },+ "inference-net/schematron-v2-turbo": {+ "id": "inference-net/schematron-v2-turbo",+ "name": "Inference.net: Schematron V2 Turbo",+ "provider": "inference-net",+ "local_id": "schematron-v2-turbo",+ "context_length": 128000,+ "max_output_tokens": 8192,+ "input_price_per_mtok": 0.03,+ "output_price_per_mtok": 0.15,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "logit_bias",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "top_k",+ "top_p"+ ]+ },+ "inference-net/schematron-v2-small": {+ "id": "inference-net/schematron-v2-small",+ "name": "Inference.net: Schematron V2 Small",+ "provider": "inference-net",+ "local_id": "schematron-v2-small",+ "context_length": 128000,+ "max_output_tokens": 4096,+ "input_price_per_mtok": 0.05,+ "output_price_per_mtok": 0.23,+ "supports_thinking": false,+ "thinking_type": "none",+ "temperature_range": [+ 0.0,+ 2.0+ ],+ "is_reasoning_model": false,+ "supported_parameters": [+ "frequency_penalty",+ "logit_bias",+ "max_tokens",+ "min_p",+ "presence_penalty",+ "response_format",+ "seed",+ "stop",+ "structured_outputs",+ "temperature",+ "top_k",+ "top_p"+ ]+ },"openai/gpt-astra-latest": {"id": "~openai/gpt-astra-latest",- "name": "OpenAI GPT Astra Latest",+ "name": "OpenAI: GPT Astra Latest","provider": "openai","local_id": "gpt-astra-latest","context_length": 1050000,@@ -34,7 +978,7 @@},"openai/gpt-sol-latest": {"id": "~openai/gpt-sol-latest",- "name": "OpenAI GPT Sol Latest",+ "name": "OpenAI: GPT Sol Latest","provider": "openai","local_id": "gpt-sol-latest","context_length": 1050000,@@ -63,7 +1007,7 @@},"openai/gpt-terra-latest": {"id": "~openai/gpt-terra-latest",- "name": "OpenAI GPT Terra Latest",+ "name": "OpenAI: GPT Terra Latest","provider": "openai","local_id": "gpt-terra-latest","context_length": 1050000,@@ -92,13 +1036,13 @@},"openai/gpt-luna-latest": {"id": "~openai/gpt-luna-latest",- "name": "OpenAI GPT Luna Latest",+ "name": "OpenAI: GPT Luna Latest","provider": "openai","local_id": "gpt-luna-latest","context_length": 1050000,"max_output_tokens": 128000,- "input_price_per_mtok": 0.2,- "output_price_per_mtok": 1.2,+ "input_price_per_mtok": 0.1,+ "output_price_per_mtok": 0.5,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -176,7 +1120,7 @@"name": "inclusionAI: Ling 3.0 Flash VL","provider": "inclusionai","local_id": "ling-3.0-flash-vl",- "context_length": 131072,+ "context_length": 262144,"max_output_tokens": 32768,"input_price_per_mtok": 0.06,"output_price_per_mtok": 0.18,@@ -191,6 +1135,7 @@"frequency_penalty","include_reasoning","logit_bias",+ "logprobs","max_tokens","min_p","presence_penalty",@@ -204,18 +1149,19 @@"tool_choice","tools","top_k",+ "top_logprobs","top_p"]},- "inclusionai/ling-3.0-flash-vl:free": {- "id": "inclusionai/ling-3.0-flash-vl:free",- "name": "inclusionAI: Ling 3.0 Flash VL (free)",- "provider": "inclusionai",- "local_id": "ling-3.0-flash-vl:free",- "context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.0,- "output_price_per_mtok": 0.0,+ "deepseek/deepseek-v4.1-flash": {+ "id": "deepseek/deepseek-v4.1-flash",+ "name": "DeepSeek: DeepSeek V4.1 Flash",+ "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,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -226,13 +1172,18 @@"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",@@ -241,15 +1192,15 @@"top_p"]},- "deepseek/deepseek-v4.1-flash": {- "id": "deepseek/deepseek-v4.1-flash",- "name": "DeepSeek: DeepSeek V4.1 Flash",+ "deepseek/deepseek-v4.1-flash:batch": {+ "id": "deepseek/deepseek-v4.1-flash:batch",+ "name": "DeepSeek: DeepSeek V4.1 Flash (batch)","provider": "deepseek",- "local_id": "deepseek-v4.1-flash",+ "local_id": "deepseek-v4.1-flash:batch","context_length": 1048576,- "max_output_tokens": 384000,- "input_price_per_mtok": 0.15,- "output_price_per_mtok": 0.6,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.112,+ "output_price_per_mtok": 0.336,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -261,7 +1212,6 @@"frequency_penalty","include_reasoning","logit_bias",- "logprobs","max_tokens","min_p","presence_penalty",@@ -276,7 +1226,6 @@"tool_choice","tools","top_k",- "top_logprobs","top_p"]},@@ -704,6 +1653,7 @@"response_format","stop","structured_outputs",+ "tool_choice","tools","verbosity"]@@ -793,17 +1743,23 @@],"is_reasoning_model": false,"supported_parameters": [+ "frequency_penalty","include_reasoning","max_completion_tokens","max_tokens",+ "presence_penalty","reasoning","reasoning_effort",+ "repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature","tool_choice",- "tools"+ "tools",+ "top_k",+ "top_p"]},"inclusionai/ling-3.0-flash-fin": {@@ -831,7 +1787,6 @@"presence_penalty","reasoning","repetition_penalty",- "response_format","seed","stop","structured_outputs",@@ -882,9 +1837,9 @@"provider": "z-ai","local_id": "glm-flash-latest","context_length": 1310720,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.075,- "output_price_per_mtok": 0.25,+ "max_output_tokens": 128000,+ "input_price_per_mtok": 0.045,+ "output_price_per_mtok": 0.14,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -899,6 +1854,7 @@"logprobs","max_tokens","min_p",+ "parallel_tool_calls","presence_penalty","reasoning","reasoning_effort",@@ -934,13 +1890,10 @@"supported_parameters": ["frequency_penalty","include_reasoning",- "logit_bias","logprobs","max_tokens",- "min_p","presence_penalty","reasoning",- "repetition_penalty","response_format","seed","stop",@@ -959,7 +1912,7 @@"provider": "z-ai","local_id": "glm-5.3-flash","context_length": 1310720,- "max_output_tokens": 131072,+ "max_output_tokens": 943718,"input_price_per_mtok": 0.15,"output_price_per_mtok": 0.5,"supports_thinking": false,@@ -976,6 +1929,7 @@"logprobs","max_tokens","min_p",+ "parallel_tool_calls","presence_penalty","reasoning","reasoning_effort",@@ -998,9 +1952,9 @@"provider": "z-ai","local_id": "glm-5.3-flash:batch","context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.075,- "output_price_per_mtok": 0.25,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.06,+ "output_price_per_mtok": 0.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1012,7 +1966,6 @@"frequency_penalty","include_reasoning","logit_bias",- "logprobs","max_tokens","min_p","presence_penalty",@@ -1020,13 +1973,13 @@"reasoning_effort","repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature","tool_choice","tools","top_k",- "top_logprobs","top_p"]},@@ -1100,43 +2053,6 @@"top_p"]},- "deepseek/deepseek-v4-flash-vision-exp:batch": {- "id": "deepseek/deepseek-v4-flash-vision-exp:batch",- "name": "DeepSeek: DeepSeek V4 Flash Vision Exp (batch)",- "provider": "deepseek",- "local_id": "deepseek-v4-flash-vision-exp:batch",- "context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.11,- "output_price_per_mtok": 0.33,- "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",- "presence_penalty",- "reasoning",- "reasoning_effort",- "repetition_penalty",- "response_format",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"tencent/hy-mt2-1.8b": {"id": "tencent/hy-mt2-1.8b","name": "Tencent: Hy-MT2-1.8B",@@ -1191,9 +2107,9 @@"provider": "z-ai","local_id": "glm-latest","context_length": 1310720,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.8727,- "output_price_per_mtok": 3.36,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.5625,+ "output_price_per_mtok": 2.5,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1256,9 +2172,9 @@"provider": "z-ai","local_id": "glm-5.3","context_length": 1310720,- "max_output_tokens": 943718,- "input_price_per_mtok": 1.4,- "output_price_per_mtok": 4.4,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.84,+ "output_price_per_mtok": 2.64,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1296,9 +2212,9 @@"provider": "z-ai","local_id": "glm-5.3:batch","context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.7,- "output_price_per_mtok": 2.2,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.45,+ "output_price_per_mtok": 2.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1310,20 +2226,20 @@"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"]},@@ -1367,6 +2283,38 @@"top_p"]},+ "qwen/qwen3.8-27b:free": {+ "id": "qwen/qwen3.8-27b:free",+ "name": "Qwen: Qwen3.8 27B (free)",+ "provider": "qwen",+ "local_id": "qwen3.8-27b: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",+ "presence_penalty",+ "reasoning",+ "reasoning_effort",+ "repetition_penalty",+ "stop",+ "structured_outputs",+ "temperature",+ "tool_choice",+ "tools",+ "top_p"+ ]+ },"dots-studio/dots-3-note-preview:free": {"id": "dots-studio/dots-3-note-preview:free","name": "Dots Studio: Dots3-Note Preview (free)",@@ -1524,44 +2472,6 @@"top_p"]},- "qwen/qwen3.8-2.4t-a95b:batch": {- "id": "qwen/qwen3.8-2.4t-a95b:batch",- "name": "Qwen: Qwen3.8 2.4T A95B (batch)",- "provider": "qwen",- "local_id": "qwen3.8-2.4t-a95b:batch",- "context_length": 1010000,- "max_output_tokens": 909000,- "input_price_per_mtok": 2.0,- "output_price_per_mtok": 6.0,- "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",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"bytedance-seed/seed-2.0-code": {"id": "bytedance-seed/seed-2.0-code","name": "ByteDance Seed: Seed-2.0-Code",@@ -1600,8 +2510,8 @@"local_id": "deepseek-v4-pro-0813","context_length": 1048576,"max_output_tokens": 384000,- "input_price_per_mtok": 0.5795,- "output_price_per_mtok": 1.7384,+ "input_price_per_mtok": 0.462,+ "output_price_per_mtok": 1.386,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1632,44 +2542,6 @@"top_p"]},- "deepseek/deepseek-v4-pro-0813:batch": {- "id": "deepseek/deepseek-v4-pro-0813:batch",- "name": "DeepSeek: DeepSeek V4 Pro 0813 (batch)",- "provider": "deepseek",- "local_id": "deepseek-v4-pro-0813:batch",- "context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.66,- "output_price_per_mtok": 1.98,- "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",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"xai/grok-4.6": {"id": "x-ai/grok-4.6","name": "SpaceXAI: Grok 4.6",@@ -1856,6 +2728,7 @@"parallel_tool_calls","presence_penalty","reasoning",+ "reasoning_effort","response_format","structured_outputs","temperature",@@ -1870,48 +2743,9 @@"provider": "meta","local_id": "muse-glimmer-30b","context_length": 131072,- "max_output_tokens": 117964,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 1.1,- "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"- ]- },- "meta/muse-glimmer-30b:batch": {- "id": "meta/muse-glimmer-30b:batch",- "name": "Meta: Muse Glimmer 30B (batch)",- "provider": "meta",- "local_id": "muse-glimmer-30b:batch",- "context_length": 131072,- "max_output_tokens": 117964,- "input_price_per_mtok": 0.175,- "output_price_per_mtok": 0.75,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 1.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -1931,6 +2765,7 @@"reasoning_effort","repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature",@@ -1974,13 +2809,13 @@},"deepseek/deepseek-v4-flash-latest": {"id": "~deepseek/deepseek-v4-flash-latest",- "name": "DeepSeek V4 Flash Latest",+ "name": "DeepSeek: DeepSeek V4 Flash Latest","provider": "deepseek","local_id": "deepseek-v4-flash-latest","context_length": 1310720,- "max_output_tokens": 393216,- "input_price_per_mtok": 0.05,- "output_price_per_mtok": 0.16,+ "max_output_tokens": 943718,+ "input_price_per_mtok": 0.03,+ "output_price_per_mtok": 0.32,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2020,8 +2855,8 @@"local_id": "deepseek-v4-flash-0731","context_length": 1310720,"max_output_tokens": 943718,- "input_price_per_mtok": 0.065,- "output_price_per_mtok": 0.18,+ "input_price_per_mtok": 0.03,+ "output_price_per_mtok": 0.32,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2054,44 +2889,6 @@"top_p"]},- "deepseek/deepseek-v4-flash-0731:batch": {- "id": "deepseek/deepseek-v4-flash-0731:batch",- "name": "DeepSeek: DeepSeek V4 Flash 0731 (batch)",- "provider": "deepseek",- "local_id": "deepseek-v4-flash-0731:batch",- "context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.11,- "output_price_per_mtok": 0.33,- "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",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs",- "top_p"- ]- },"thinkingmachines/inkling-small": {"id": "thinkingmachines/inkling-small","name": "Thinking Machines: Inkling Small",@@ -2112,7 +2909,6 @@"frequency_penalty","include_reasoning","logit_bias",- "logprobs","max_tokens","min_p","presence_penalty",@@ -2125,43 +2921,6 @@"tool_choice","tools","top_k",- "top_logprobs",- "top_p"- ]- },- "thinkingmachines/inkling-small:batch": {- "id": "thinkingmachines/inkling-small:batch",- "name": "Thinking Machines: Inkling Small (batch)",- "provider": "thinkingmachines",- "local_id": "inkling-small:batch",- "context_length": 524288,- "max_output_tokens": 471859,- "input_price_per_mtok": 0.5,- "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",- "logit_bias",- "logprobs",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "reasoning_effort",- "repetition_penalty",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_logprobs","top_p"]},@@ -2228,7 +2987,7 @@},"anthropic/claude-opus-5": {"id": "anthropic/claude-opus-5",- "name": "Claude Opus 5",+ "name": "Anthropic: Claude Opus 5","provider": "anthropic","local_id": "claude-opus-5","context_length": 1000000,@@ -2259,7 +3018,7 @@},"anthropic/claude-opus-5:batch": {"id": "anthropic/claude-opus-5:batch",- "name": "Claude Opus 5 (batch)",+ "name": "Anthropic: Claude Opus 5 (batch)","provider": "anthropic","local_id": "claude-opus-5:batch","context_length": 1000000,@@ -2533,42 +3292,6 @@"provider": "thinkingmachines","local_id": "inkling","context_length": 1048576,- "max_output_tokens": 32768,- "input_price_per_mtok": 1.0,- "output_price_per_mtok": 4.05,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "logit_bias",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "reasoning_effort",- "repetition_penalty",- "response_format",- "seed",- "stop",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },- "thinkingmachines/inkling:batch": {- "id": "thinkingmachines/inkling:batch",- "name": "Thinking Machines: Inkling (batch)",- "provider": "thinkingmachines",- "local_id": "inkling:batch",- "context_length": 524288,"max_output_tokens": 471859,"input_price_per_mtok": 1.0,"output_price_per_mtok": 4.05,@@ -2589,6 +3312,7 @@"reasoning","reasoning_effort","repetition_penalty",+ "seed","stop","temperature","tool_choice",@@ -2676,8 +3400,8 @@"local_id": "kimi-k3","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 1.89,- "output_price_per_mtok": 9.48,+ "input_price_per_mtok": 3.0,+ "output_price_per_mtok": 15.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2714,9 +3438,9 @@"provider": "moonshotai","local_id": "kimi-k3:batch","context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 3.0,- "output_price_per_mtok": 15.0,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 2.28,+ "output_price_per_mtok": 11.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -2735,6 +3459,7 @@"reasoning_effort","repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature",@@ -3190,8 +3915,8 @@"local_id": "grok-latest","context_length": 500000,"max_output_tokens": 450000,- "input_price_per_mtok": 2.0,- "output_price_per_mtok": 6.0,+ "input_price_per_mtok": 1.6,+ "output_price_per_mtok": 4.8,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3207,12 +3932,10 @@"reasoning_effort","response_format","seed",- "stop","structured_outputs","temperature","tool_choice","tools",- "top_k","top_logprobs","top_p"]@@ -3278,8 +4001,8 @@"local_id": "hy3","context_length": 262144,"max_output_tokens": 128000,- "input_price_per_mtok": 0.0825,- "output_price_per_mtok": 0.33,+ "input_price_per_mtok": 0.132,+ "output_price_per_mtok": 0.528,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3566,9 +4289,9 @@"provider": "z-ai","local_id": "glm-5.2","context_length": 1048576,- "max_output_tokens": 182476,- "input_price_per_mtok": 0.6,- "output_price_per_mtok": 2.0,+ "max_output_tokens": 131072,+ "input_price_per_mtok": 0.6496,+ "output_price_per_mtok": 2.0416,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3600,15 +4323,15 @@"top_p"]},- "z-ai/glm-5.2:batch": {- "id": "z-ai/glm-5.2:batch",- "name": "Z.ai: GLM 5.2 (batch)",+ "z-ai/glm-5.2:free": {+ "id": "z-ai/glm-5.2:free",+ "name": "Z.ai: GLM 5.2 (free)","provider": "z-ai",- "local_id": "glm-5.2:batch",- "context_length": 1048576,- "max_output_tokens": 943718,- "input_price_per_mtok": 0.7,- "output_price_per_mtok": 2.2,+ "local_id": "glm-5.2:free",+ "context_length": 32768,+ "max_output_tokens": 29491,+ "input_price_per_mtok": 0.0,+ "output_price_per_mtok": 0.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3619,21 +4342,16 @@"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"]},@@ -3662,8 +4380,8 @@"local_id": "kimi-k2.7-code","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.71,- "output_price_per_mtok": 3.5,+ "input_price_per_mtok": 0.7062,+ "output_price_per_mtok": 3.3,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3719,6 +4437,7 @@"response_format","stop","structured_outputs",+ "tool_choice","tools","verbosity"]@@ -3807,7 +4526,6 @@"presence_penalty","reasoning","repetition_penalty",- "response_format","seed","stop","temperature",@@ -3846,9 +4564,9 @@"provider": "nvidia","local_id": "nemotron-3-ultra-550b-a55b","context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.625,- "output_price_per_mtok": 3.125,+ "max_output_tokens": 182520,+ "input_price_per_mtok": 0.6,+ "output_price_per_mtok": 2.4,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -3978,41 +4696,6 @@"top_p"]},- "minimax/minimax-m3:batch": {- "id": "minimax/minimax-m3:batch",- "name": "MiniMax: MiniMax M3 (batch)",- "provider": "minimax",- "local_id": "minimax-m3:batch",- "context_length": 524288,- "max_output_tokens": 471859,- "input_price_per_mtok": 0.3,- "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",- "logit_bias",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "repetition_penalty",- "response_format",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"stepfun/step-3.7-flash": {"id": "stepfun/step-3.7-flash","name": "StepFun: Step 3.7 Flash",@@ -4514,7 +5197,7 @@},"anthropic/claude-haiku-latest": {"id": "~anthropic/claude-haiku-latest",- "name": "Anthropic Claude Haiku Latest",+ "name": "Anthropic: Claude Haiku Latest","provider": "anthropic","local_id": "claude-haiku-latest","context_length": 200000,@@ -4545,7 +5228,7 @@},"openai/gpt-mini-latest": {"id": "~openai/gpt-mini-latest",- "name": "OpenAI GPT Mini Latest",+ "name": "OpenAI: GPT Mini Latest","provider": "openai","local_id": "gpt-mini-latest","context_length": 400000,@@ -4574,7 +5257,7 @@},"gemini/gemini-pro-latest": {"id": "~google/gemini-pro-latest",- "name": "Google Gemini Pro Latest",+ "name": "Google: Gemini Pro Latest","provider": "gemini","local_id": "gemini-pro-latest","context_length": 1048576,@@ -4605,13 +5288,13 @@},"moonshotai/kimi-latest": {"id": "~moonshotai/kimi-latest",- "name": "MoonshotAI Kimi Latest",+ "name": "MoonshotAI: Kimi Latest","provider": "moonshotai","local_id": "kimi-latest","context_length": 1048576,"max_output_tokens": 943718,- "input_price_per_mtok": 1.89,- "output_price_per_mtok": 9.48,+ "input_price_per_mtok": 1.4,+ "output_price_per_mtok": 10.75,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -4644,7 +5327,7 @@},"gemini/gemini-flash-latest": {"id": "~google/gemini-flash-latest",- "name": "Google Gemini Flash Latest",+ "name": "Google: Gemini Flash Latest","provider": "gemini","local_id": "gemini-flash-latest","context_length": 1048576,@@ -4675,7 +5358,7 @@},"anthropic/claude-sonnet-latest": {"id": "~anthropic/claude-sonnet-latest",- "name": "Anthropic Claude Sonnet Latest",+ "name": "Anthropic: Claude Sonnet Latest","provider": "anthropic","local_id": "claude-sonnet-latest","context_length": 1000000,@@ -4780,8 +5463,8 @@"local_id": "qwen3.6-35b-a3b","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.1,- "output_price_per_mtok": 0.9,+ "input_price_per_mtok": 0.15,+ "output_price_per_mtok": 1.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -4852,9 +5535,9 @@"provider": "qwen","local_id": "qwen3.6-27b","context_length": 262144,- "max_output_tokens": 65536,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 2.0,+ "max_output_tokens": 262140,+ "input_price_per_mtok": 0.32,+ "output_price_per_mtok": 2.7,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5004,8 +5687,8 @@"local_id": "deepseek-v4-pro","context_length": 1048576,"max_output_tokens": 384000,- "input_price_per_mtok": 0.9478,- "output_price_per_mtok": 1.8956,+ "input_price_per_mtok": 0.9396,+ "output_price_per_mtok": 1.8792,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5044,8 +5727,8 @@"local_id": "deepseek-v4-flash","context_length": 1048576,"max_output_tokens": 384000,- "input_price_per_mtok": 0.0851,- "output_price_per_mtok": 0.1702,+ "input_price_per_mtok": 0.0886,+ "output_price_per_mtok": 0.1772,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5219,8 +5902,8 @@"local_id": "claude-opus-latest","context_length": 1000000,"max_output_tokens": 128000,- "input_price_per_mtok": 5.0,- "output_price_per_mtok": 25.0,+ "input_price_per_mtok": 4.0,+ "output_price_per_mtok": 20.0,"supports_thinking": true,"thinking_type": "budget","temperature_range": [@@ -5403,9 +6086,9 @@"provider": "gemini","local_id": "gemma-4-26b-a4b-it","context_length": 262144,- "max_output_tokens": 32768,- "input_price_per_mtok": 0.042,- "output_price_per_mtok": 0.22,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.09,+ "output_price_per_mtok": 0.3,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5501,41 +6184,6 @@"top_p"]},- "gemini/gemma-4-31b-it:batch": {- "id": "google/gemma-4-31b-it:batch",- "name": "Google: Gemma 4 31B (batch)",- "provider": "gemini",- "local_id": "gemma-4-31b-it:batch",- "context_length": 262144,- "max_output_tokens": 235929,- "input_price_per_mtok": 0.39,- "output_price_per_mtok": 0.97,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "logit_bias",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "repetition_penalty",- "response_format",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"gemini/gemma-4-31b-it:free": {"id": "google/gemma-4-31b-it:free","name": "Google: Gemma 4 31B (free)",@@ -5740,38 +6388,14 @@]},"gemini/lyria-3-clip-preview": {- "id": "google/lyria-3-clip-preview",- "name": "Google: Lyria 3 Clip Preview",- "provider": "gemini",- "local_id": "lyria-3-clip-preview",- "context_length": 1048576,- "max_output_tokens": 65536,- "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": [- "max_tokens",- "response_format",- "seed",- "temperature",- "top_p"- ]- },- "kwaipilot/kat-coder-pro-v2": {- "id": "kwaipilot/kat-coder-pro-v2",- "name": "Kwaipilot: KAT-Coder-Pro V2",- "provider": "kwaipilot",- "local_id": "kat-coder-pro-v2",- "context_length": 262144,- "max_output_tokens": 144000,- "input_price_per_mtok": 0.3,- "output_price_per_mtok": 1.2,+ "id": "google/lyria-3-clip-preview",+ "name": "Google: Lyria 3 Clip Preview",+ "provider": "gemini",+ "local_id": "lyria-3-clip-preview",+ "context_length": 1048576,+ "max_output_tokens": 65536,+ "input_price_per_mtok": 0.0,+ "output_price_per_mtok": 0.0,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -5780,20 +6404,10 @@],"is_reasoning_model": false,"supported_parameters": [- "frequency_penalty",- "logit_bias","max_tokens",- "min_p",- "presence_penalty",- "repetition_penalty","response_format","seed",- "stop",- "structured_outputs","temperature",- "tool_choice",- "tools",- "top_k","top_p"]},@@ -6011,7 +6625,6 @@"temperature","tool_choice","tools",- "top_k","top_p"]},@@ -6082,9 +6695,9 @@"provider": "nvidia","local_id": "nemotron-3-super-120b-a12b","context_length": 262144,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.085,- "output_price_per_mtok": 0.4,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.08,+ "output_price_per_mtok": 0.45,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -6182,7 +6795,7 @@"provider": "qwen","local_id": "qwen3.5-9b","context_length": 262144,- "max_output_tokens": 235929,+ "max_output_tokens": 32768,"input_price_per_mtok": 0.1,"output_price_per_mtok": 0.15,"supports_thinking": false,@@ -6214,41 +6827,6 @@"top_p"]},- "qwen/qwen3.5-9b:batch": {- "id": "qwen/qwen3.5-9b:batch",- "name": "Qwen: Qwen3.5-9B (batch)",- "provider": "qwen",- "local_id": "qwen3.5-9b:batch",- "context_length": 262144,- "max_output_tokens": 235929,- "input_price_per_mtok": 0.17,- "output_price_per_mtok": 0.25,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "include_reasoning",- "logit_bias",- "max_tokens",- "min_p",- "presence_penalty",- "reasoning",- "repetition_penalty",- "response_format",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_k",- "top_p"- ]- },"openai/gpt-5.4-pro": {"id": "openai/gpt-5.4-pro","name": "OpenAI: GPT-5.4 Pro",@@ -7249,6 +7827,7 @@"parallel_tool_calls","presence_penalty","reasoning",+ "reasoning_effort","response_format","structured_outputs","temperature",@@ -7803,36 +8382,6 @@"tools"]},- "mistralai/devstral-2512": {- "id": "mistralai/devstral-2512",- "name": "Mistral: Devstral 2 2512",- "provider": "mistralai",- "local_id": "devstral-2512",- "context_length": 262144,- "max_output_tokens": 209715,- "input_price_per_mtok": 0.4,- "output_price_per_mtok": 2.0,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "max_tokens",- "presence_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_p"- ]- },"relace/relace-search": {"id": "relace/relace-search","name": "Relace: Relace Search",@@ -8087,36 +8636,6 @@"top_p"]},- "mistralai/mistral-large-2512": {- "id": "mistralai/mistral-large-2512",- "name": "Mistral: Mistral Large 3 2512",- "provider": "mistralai",- "local_id": "mistral-large-2512",- "context_length": 262144,- "max_output_tokens": 209715,- "input_price_per_mtok": 0.5,- "output_price_per_mtok": 1.5,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "max_tokens",- "presence_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_p"- ]- },"mistralai/mistral-large-2512:batch": {"id": "mistralai/mistral-large-2512:batch","name": "Mistral: Mistral Large 3 2512 (batch)",@@ -8392,7 +8911,7 @@"provider": "moonshotai","local_id": "kimi-k2-thinking","context_length": 262144,- "max_output_tokens": 100352,+ "max_output_tokens": 98304,"input_price_per_mtok": 0.6,"output_price_per_mtok": 2.5,"supports_thinking": false,@@ -8542,9 +9061,9 @@"provider": "minimax","local_id": "minimax-m2","context_length": 204800,- "max_output_tokens": 131072,- "input_price_per_mtok": 0.255,- "output_price_per_mtok": 1.02,+ "max_output_tokens": 176947,+ "input_price_per_mtok": 0.3,+ "output_price_per_mtok": 1.2,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -8902,9 +9421,9 @@"provider": "qwen","local_id": "qwen3-vl-30b-a3b-instruct","context_length": 262144,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.15,- "output_price_per_mtok": 0.6,+ "max_output_tokens": 32768,+ "input_price_per_mtok": 0.13,+ "output_price_per_mtok": 0.52,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -9426,8 +9945,8 @@"provider": "qwen","local_id": "qwen3-next-80b-a3b-instruct","context_length": 262144,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.09,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.1,"output_price_per_mtok": 1.1,"supports_thinking": false,"thinking_type": "none",@@ -9495,7 +10014,7 @@"provider": "moonshotai","local_id": "kimi-k2-0905","context_length": 262144,- "max_output_tokens": 100352,+ "max_output_tokens": 98304,"input_price_per_mtok": 0.6,"output_price_per_mtok": 2.5,"supports_thinking": false,@@ -9890,9 +10409,9 @@"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": [@@ -9931,8 +10450,8 @@"local_id": "gpt-oss-120b:batch","context_length": 131072,"max_output_tokens": 117964,- "input_price_per_mtok": 0.15,- "output_price_per_mtok": 0.6,+ "input_price_per_mtok": 0.0296,+ "output_price_per_mtok": 0.136,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -9951,6 +10470,7 @@"reasoning_effort","repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature",@@ -9966,9 +10486,9 @@"provider": "openai","local_id": "gpt-oss-20b","context_length": 131072,- "max_output_tokens": 117964,- "input_price_per_mtok": 0.03,- "output_price_per_mtok": 0.13,+ "max_output_tokens": 32768,+ "input_price_per_mtok": 0.018,+ "output_price_per_mtok": 0.09,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -10006,8 +10526,8 @@"local_id": "gpt-oss-20b:batch","context_length": 131072,"max_output_tokens": 117964,- "input_price_per_mtok": 0.05,- "output_price_per_mtok": 0.2,+ "input_price_per_mtok": 0.024,+ "output_price_per_mtok": 0.112,"supports_thinking": true,"thinking_type": "effort","temperature_range": [@@ -10026,9 +10546,12 @@"reasoning_effort","repetition_penalty","response_format",+ "seed","stop","structured_outputs","temperature",+ "tool_choice",+ "tools","top_k","top_p"]@@ -10192,7 +10715,7 @@"local_id": "qwen3-30b-a3b-instruct-2507","context_length": 262144,"max_output_tokens": 235929,- "input_price_per_mtok": 0.09,+ "input_price_per_mtok": 0.1,"output_price_per_mtok": 0.3,"supports_thinking": false,"thinking_type": "none",@@ -10449,9 +10972,9 @@"provider": "qwen","local_id": "qwen3-235b-a22b-2507","context_length": 262144,- "max_output_tokens": 16384,- "input_price_per_mtok": 0.22,- "output_price_per_mtok": 0.88,+ "max_output_tokens": 235929,+ "input_price_per_mtok": 0.0875,+ "output_price_per_mtok": 0.35,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10485,7 +11008,7 @@"provider": "moonshotai","local_id": "kimi-k2","context_length": 131072,- "max_output_tokens": 100352,+ "max_output_tokens": 98304,"input_price_per_mtok": 0.57,"output_price_per_mtok": 2.3,"supports_thinking": false,@@ -10647,10 +11170,10 @@"name": "Mistral: Mistral Small 3.2 24B","provider": "mistralai","local_id": "mistral-small-3.2-24b-instruct",- "context_length": 131072,+ "context_length": 256000,"max_output_tokens": 16384,- "input_price_per_mtok": 0.075,- "output_price_per_mtok": 0.2,+ "input_price_per_mtok": 0.0938,+ "output_price_per_mtok": 0.25,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -10685,7 +11208,7 @@"local_id": "minimax-m1","context_length": 1000000,"max_output_tokens": 40000,- "input_price_per_mtok": 0.55,+ "input_price_per_mtok": 0.4,"output_price_per_mtok": 2.2,"supports_thinking": false,"thinking_type": "none",@@ -10925,39 +11448,12 @@"top_p"]},- "anthropic/claude-opus-4": {- "id": "anthropic/claude-opus-4",- "name": "Anthropic: Claude Opus 4",- "provider": "anthropic",- "local_id": "claude-opus-4",- "context_length": 200000,- "max_output_tokens": 32000,- "input_price_per_mtok": 15.0,- "output_price_per_mtok": 75.0,- "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_p"- ]- },"anthropic/claude-sonnet-4": {"id": "anthropic/claude-sonnet-4","name": "Anthropic: Claude Sonnet 4","provider": "anthropic","local_id": "claude-sonnet-4",- "context_length": 1000000,+ "context_length": 200000,"max_output_tokens": 64000,"input_price_per_mtok": 3.0,"output_price_per_mtok": 15.0,@@ -11010,36 +11506,6 @@"top_p"]},- "gemini/gemini-2.5-pro-preview-05-06": {- "id": "google/gemini-2.5-pro-preview-05-06",- "name": "Google: Gemini 2.5 Pro Preview 05-06",- "provider": "gemini",- "local_id": "gemini-2.5-pro-preview-05-06",- "context_length": 1048576,- "max_output_tokens": 65535,- "input_price_per_mtok": 1.25,- "output_price_per_mtok": 10.0,- "supports_thinking": true,- "thinking_type": "budget",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "include_reasoning",- "max_tokens",- "reasoning",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_p"- ]- },"meta/llama-guard-4-12b": {"id": "meta-llama/llama-guard-4-12b","name": "Meta: Llama Guard 4 12B",@@ -11063,7 +11529,6 @@"min_p","presence_penalty","repetition_penalty",- "response_format","seed","stop","temperature",@@ -11145,9 +11610,9 @@"provider": "qwen","local_id": "qwen3-14b","context_length": 131072,- "max_output_tokens": 8192,- "input_price_per_mtok": 0.2275,- "output_price_per_mtok": 0.91,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.12,+ "output_price_per_mtok": 0.24,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -11552,9 +12017,9 @@"provider": "meta","local_id": "llama-4-maverick","context_length": 1048576,- "max_output_tokens": 115200,- "input_price_per_mtok": 0.2,- "output_price_per_mtok": 0.696,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.1875,+ "output_price_per_mtok": 0.6525,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -11704,6 +12169,8 @@"seed","stop","temperature",+ "tool_choice",+ "tools","top_k","top_logprobs","top_p"@@ -12301,7 +12768,6 @@"response_format","seed","stop",- "structured_outputs","temperature","tool_choice","tools",@@ -12369,9 +12835,9 @@"provider": "deepseek","local_id": "deepseek-chat","context_length": 163840,- "max_output_tokens": 16000,- "input_price_per_mtok": 0.2574,- "output_price_per_mtok": 1.0287,+ "max_output_tokens": 16384,+ "input_price_per_mtok": 0.32,+ "output_price_per_mtok": 0.89,"supports_thinking": false,"thinking_type": "none","temperature_range": [@@ -12683,6 +13149,7 @@"min_p","presence_penalty","repetition_penalty",+ "response_format","seed","stop","temperature",@@ -12713,13 +13180,10 @@"max_tokens","presence_penalty","repetition_penalty",- "response_format","seed","stop","structured_outputs","temperature",- "tool_choice",- "tools","top_k","top_logprobs","top_p"@@ -12975,7 +13439,6 @@"min_p","presence_penalty","repetition_penalty",- "response_format","seed","stop","structured_outputs",@@ -13009,7 +13472,6 @@"min_p","presence_penalty","repetition_penalty",- "response_format","seed","stop","structured_outputs",@@ -13682,39 +14144,6 @@"top_p"]},- "openai/gpt-4-turbo-preview": {- "id": "openai/gpt-4-turbo-preview",- "name": "OpenAI: GPT-4 Turbo Preview",- "provider": "openai",- "local_id": "gpt-4-turbo-preview",- "context_length": 128000,- "max_output_tokens": 4096,- "input_price_per_mtok": 10.0,- "output_price_per_mtok": 30.0,- "supports_thinking": false,- "thinking_type": "none",- "temperature_range": [- 0.0,- 2.0- ],- "is_reasoning_model": false,- "supported_parameters": [- "frequency_penalty",- "logit_bias",- "logprobs",- "max_tokens",- "presence_penalty",- "response_format",- "seed",- "stop",- "structured_outputs",- "temperature",- "tool_choice",- "tools",- "top_logprobs",- "top_p"- ]- },"openrouter/auto": {"id": "openrouter/auto","name": "Auto Router",@@ -13898,8 +14327,8 @@"local_id": "mythomax-l2-13b","context_length": 8192,"max_output_tokens": 3686,- "input_price_per_mtok": 0.06,- "output_price_per_mtok": 0.06,+ "input_price_per_mtok": 0.08,+ "output_price_per_mtok": 0.11,"supports_thinking": false,"thinking_type": "none","temperature_range": [diff --git a/server/config/pricing.json b/server/config/pricing.jsonindex cbc7eced..2c7dd9dc 100644--- a/server/config/pricing.json+++ b/server/config/pricing.json@@ -1,12 +1,18 @@{- "version": "2026.07",- "last_updated": "2026-07-25",+ "version": "2026.09",+ "last_updated": "2026-09-15","llm": {"openai": {- "gpt-5.6-sol": {"input": 5.00, "output": 30.00, "cache_read": 0.50},- "gpt-5.6-terra": {"input": 2.50, "output": 15.00, "cache_read": 0.25},- "gpt-5.6-luna": {"input": 1.00, "output": 6.00, "cache_read": 0.10},+ "_note": "developers.openai.com/api/docs/pricing, 2026-09-15 (standard tier). The -pro variants are not on the pricing page; they mirror their base model per the OpenRouter cache.",+ "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-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},+ "gpt-5.6-luna": {"input": 0.20, "output": 1.20, "cache_read": 0.02},+ "gpt-5.6-luna-pro": {"input": 0.20, "output": 1.20, "cache_read": 0.02},"gpt-5.5": {"input": 5.00, "output": 30.00, "cache_read": 0.50},"gpt-5.4": {"input": 2.50, "output": 15.00},"gpt-5.3-chat": {"input": 1.75, "output": 14.00},@@ -18,11 +24,12 @@"anthropic": {"claude-opus-5": {"input": 5.00, "output": 25.00, "cache_read": 0.50},"claude-opus-5-fast": {"input": 10.00, "output": 50.00, "cache_read": 1.00},+ "claude-fable-5-1": {"input": 10.00, "output": 50.00, "cache_read": 0.25},"claude-fable-5": {"input": 10.00, "output": 50.00, "cache_read": 1.00},"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": {"input": 3.00, "output": 15.00, "cache_read": 0.30},+ "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},"claude-sonnet-4-0": {"input": 3.00, "output": 15.00, "cache_read": 0.30},@@ -30,8 +37,13 @@"_default": {"input": 3.00, "output": 15.00, "cache_read": 0.30}},"gemini": {- "gemini-3.6-flash": {"input": 1.50, "output": 7.50},+ "_note": "ai.google.dev/gemini-api/docs/pricing paid tier, 2026-09-15, <=200K prompt tier. 3.6/3.7/3.8 Flash rise to $1.50/$7.50 on 2027-01-01.",+ "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},+ "gemini-3.5-flash": {"input": 1.50, "output": 9.00},"gemini-3.5-flash-lite": {"input": 0.30, "output": 2.50},+ "gemini-3.1-flash-lite": {"input": 0.25, "output": 1.50},"gemini-3.1-pro-preview": {"input": 2.00, "output": 12.00},"gemini-3-flash-preview": {"input": 0.50, "output": 3.00},"gemini-3-pro-preview": {"input": 2.00, "output": 12.00},@@ -52,47 +64,55 @@"_default": {"input": 0.15, "output": 0.60}},"xai": {+ "_note": "docs.x.ai/docs/models, 2026-09-15, base tier (prompts past 200K tokens are billed at double).",+ "grok-4.6": {"input": 2.00, "output": 6.00},"grok-4.5": {"input": 2.00, "output": 6.00},- "grok-4.20": {"input": 2.00, "output": 6.00},+ "grok-4.3": {"input": 1.25, "output": 2.50},+ "grok-4.20": {"input": 1.25, "output": 2.50},+ "grok-4.20-multi-agent": {"input": 1.25, "output": 2.50},"_default": {"input": 2.00, "output": 6.00}},"cerebras": {+ "_note": "Cerebras no longer publishes per-model prices on its docs (2026-09-15); gpt-oss-120b keeps the last published figure and qwen-3.8-27b falls to _default.","gpt-oss-120b": {"input": 0.35, "output": 0.75},- "zai-glm-4.7": {"input": 2.25, "output": 2.75},- "gemma-4-31b": {"input": 0.99, "output": 1.49},"_default": {"input": 0.35, "output": 0.75}},"openrouter": {"_default": {"input": 1.00, "output": 5.00}},"deepseek": {- "deepseek-v4-pro": {"input": 0.435, "output": 0.87},- "deepseek-v4-flash": {"input": 0.14, "output": 0.28},- "deepseek-chat": {"input": 0.28, "output": 0.42, "cache_read": 0.028},- "deepseek-reasoner": {"input": 0.55, "output": 2.19, "cache_read": 0.14},- "_default": {"input": 0.28, "output": 0.42}+ "_note": "api-docs.deepseek.com/quick_start/pricing, 2026-09-15, off-peak rates (peak hours 01:00-04:00 and 06:00-10:00 UTC Mon-Fri are double). deepseek-v4-flash is a retired alias served by V4.1-Flash at the Flash price; deepseek-chat / deepseek-reasoner are discontinued.",+ "deepseek-flash": {"input": 0.15, "output": 0.60, "cache_read": 0.003},+ "deepseek-v4.1-flash": {"input": 0.15, "output": 0.60, "cache_read": 0.003},+ "deepseek-v4-flash": {"input": 0.15, "output": 0.60, "cache_read": 0.003},+ "deepseek-v4-pro": {"input": 0.66, "output": 1.98, "cache_read": 0.022},+ "_default": {"input": 0.15, "output": 0.60}},"kimi": {+ "_note": "platform.kimi.ai/docs/pricing/chat, 2026-09-15; cache_read is the cache-hit input price.","kimi-k3": {"input": 3.00, "output": 15.00, "cache_read": 0.30},- "kimi-k2.5": {"input": 0.60, "output": 2.50, "cache_read": 0.15},+ "kimi-k2.7-code": {"input": 0.95, "output": 4.00, "cache_read": 0.19},+ "kimi-k2.7-code-highspeed": {"input": 1.90, "output": 8.00, "cache_read": 0.38},+ "kimi-k2.6": {"input": 0.95, "output": 4.00, "cache_read": 0.16},"kimi-k2-thinking": {"input": 0.60, "output": 2.50, "cache_read": 0.15},"moonshot-v1-8k": {"input": 0.20, "output": 2.00},"moonshot-v1-32k": {"input": 1.00, "output": 3.00},"moonshot-v1-128k": {"input": 2.00, "output": 5.00},- "_default": {"input": 0.60, "output": 2.50}+ "_default": {"input": 0.95, "output": 4.00}},"mistral": {- "mistral-large-latest": {"input": 2.00, "output": 6.00},- "mistral-small-latest": {"input": 0.20, "output": 0.60},+ "_note": "Large 3 (mistral-large-2512), Small 4 (mistral-small-2603) and Codestral from mistral.ai pricing / docs, 2026-09-15; Medium 3.5 (mistral-medium-3504) is not on the public page and mirrors the OpenRouter cache.",+ "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},"open-mistral-nemo": {"input": 0.15, "output": 0.15},- "_default": {"input": 0.20, "output": 0.60}+ "_default": {"input": 0.15, "output": 0.60}},"sarvam": {- "_note": "Sarvam publishes INR list prices; converted at 1 INR = 0.0113 USD (~88.5 INR/USD, 2026-07). Source rates per MTok: sarvam-105b 4 in / 16 out / 2.5 cached; sarvam-30b 2.5 / 10 / 1.5. _default mirrors sarvam-105b (the provider default_model) so an unresolved id never under-reports. PricingService._build_llm_registry skips non-dict values, so this key is inert.",- "sarvam-105b": {"input": 0.045, "output": 0.181, "cache_read": 0.028},- "sarvam-30b": {"input": 0.028, "output": 0.113, "cache_read": 0.017},- "_default": {"input": 0.045, "output": 0.181, "cache_read": 0.028}+ "_note": "docs.sarvam.ai/api-reference-docs/pricing (2026-09-15) lists INR per 1M tokens: sarvam-105b 29.28 in / 10.98 cached / 73.2 out; converted at 1 INR = 0.0113 USD. sarvam-30b is no longer on the pricing page, so it falls to _default, which mirrors sarvam-105b (the provider default_model) so an unresolved id never under-reports. PricingService._build_llm_registry skips non-dict values, so this key is inert.",+ "sarvam-105b": {"input": 0.331, "output": 0.827, "cache_read": 0.124},+ "_default": {"input": 0.331, "output": 0.827, "cache_read": 0.124}},"ollama": {"_description": "Local inference is free at the API layer — user-borne hardware costs are not tracked here.",diff --git a/server/tests/llm/test_provider_continuation.py b/server/tests/llm/test_provider_continuation.pyindex b27f7c53..9195fff5 100644--- a/server/tests/llm/test_provider_continuation.py+++ b/server/tests/llm/test_provider_continuation.py@@ -633,7 +633,7 @@ async def test_compat_provider_policy_applies_kimi_and_groq_quirks():)await kimi.chat([Message(role="user", content="hi")],- model="kimi-k2.5",+ model="kimi-k2.6",temperature=0.1,)kimi_params = kimi._client.chat.completions.create.call_args.kwargs@@ -645,11 +645,11 @@ async def test_compat_provider_policy_applies_kimi_and_groq_quirks():groq._client.chat.completions.create = kimi._client.chat.completions.createawait groq.chat([Message(role="user", content="hi")],- model="qwen/qwen3-32b",+ model="qwen/qwen3.8-27b",thinking=ThinkingConfig(enabled=True, format="hidden"),)groq_params = groq._client.chat.completions.create.call_args.kwargs- assert groq_params["model"] == "qwen/qwen3-32b"+ assert groq_params["model"] == "qwen/qwen3.8-27b"assert groq_params["extra_body"]["reasoning_format"] == "hidden"await groq.chat(