Skip to content

Self-improving AI Employees for everyone

chore(config): curate latest models from the 2026-09-11 registry

trohitgab3731db74cd
diff --git a/docs-internal/native_llm_sdk.md b/docs-internal/native_llm_sdk.md
index b6c15558..44e37d53 100644
--- a/docs-internal/native_llm_sdk.md
+++ b/docs-internal/native_llm_sdk.md
@@ -93,7 +93,7 @@ Source of truth for this list: `server/config/llm_defaults.json` (the `providers
| Provider | Key Models | Context | Max Output | Thinking | Temp Range |
|----------|-----------|---------|-----------|----------|------------|
-| **OpenAI** | GPT-5.6 Sol/Terra/Luna (+ `-pro`; default `gpt-5.6-sol`), GPT-5.5/5.4 | 1.05M | 128K | effort | omitted for reasoning models |
+| **OpenAI** | GPT-6 Astra (+ `-pro`), GPT-5.6 Sol/Terra/Luna (+ `-pro`; default `gpt-5.6-sol`), GPT-5.5/5.4 | 1.05M | 128K | effort | omitted for reasoning models |
| **OpenAI** | GPT-4.1 | ~1.05M | 32K | none | 0-2 |
| **Anthropic** | Claude Opus 5 (default `claude-opus-5`), Fable 5.1 / 5, Sonnet 5 | 1M | 128K | adaptive | omitted (`temperature` / `top_p` / `top_k` rejected — `sampling_params_removed`) |
| **Anthropic** | Claude Opus 4.8/4.7 | 1M | 128K | adaptive | omitted (`sampling_params_removed`) |
@@ -101,7 +101,7 @@ Source of truth for this list: `server/config/llm_defaults.json` (the `providers
| **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, deepseek-v4-pro (deepseek-chat/reasoner legacy) | 1M | 64K | thinking modes | 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 |
diff --git a/docs-internal/workflow-schema.md b/docs-internal/workflow-schema.md
index 799cac4f..c0d08c9a 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-pro; chat/reasoner legacy aliases)
+- `deepseekChatModel` - DeepSeek V4 (deepseek-v4-flash / deepseek-v4.1-flash / deepseek-v4-pro; chat/reasoner legacy aliases)
- `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.json
index 129f9a3c..be803778 100644
--- a/server/config/llm_defaults.json
+++ b/server/config/llm_defaults.json
@@ -1,6 +1,6 @@
{
- "version": "2026.09.03",
- "last_updated": "2026-09-03",
+ "version": "2026.09.11",
+ "last_updated": "2026-09-11",
"_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": {
@@ -16,7 +16,7 @@
"openai": {
"display_name": "OpenAI",
"default_model": "gpt-5.6-sol",
- "popular_models": ["gpt-5.6-sol", "gpt-5.6-sol-pro", "gpt-5.6-terra", "gpt-5.6-terra-pro", "gpt-5.6-luna", "gpt-5.6-luna-pro", "gpt-5.5", "gpt-5.4", "gpt-4.1"],
+ "popular_models": ["gpt-5.6-sol", "gpt-6-astra", "gpt-6-astra-pro", "gpt-5.6-sol-pro", "gpt-5.6-terra", "gpt-5.6-terra-pro", "gpt-5.6-luna", "gpt-5.6-luna-pro", "gpt-5.5", "gpt-5.4", "gpt-4.1"],
"detection_patterns": ["gpt", "openai", "o1", "o3", "o4"],
"base_url": "https://api.openai.com/v1",
"models_endpoint": "https://api.openai.com/v1/models",
@@ -26,9 +26,11 @@
"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-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 ($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.",
"max_output_tokens": {
"gpt-5.6-sol": 128000,
+ "gpt-6-astra": 128000,
+ "gpt-6-astra-pro": 128000,
"gpt-5.6-sol-pro": 128000,
"gpt-5.6-terra": 128000,
"gpt-5.6-terra-pro": 128000,
@@ -41,6 +43,8 @@
},
"context_length": {
"gpt-5.6-sol": 1050000,
+ "gpt-6-astra": 1050000,
+ "gpt-6-astra-pro": 1050000,
"gpt-5.6-sol-pro": 1050000,
"gpt-5.6-terra": 1050000,
"gpt-5.6-terra-pro": 1050000,
@@ -52,7 +56,7 @@
"_default": 128000
},
"reasoning_models": ["o4-mini", "o3"],
- "thinking_models": ["gpt-5"],
+ "thinking_models": ["gpt-5", "gpt-6"],
"thinking_type": "effort",
"temperature_range": [0.0, 2.0]
},
@@ -170,7 +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", "google/gemini-3.5-flash", "moonshotai/kimi-k3", "x-ai/grok-4.20"],
+ "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"],
"detection_patterns": ["openrouter"],
"base_url": "https://openrouter.ai/api/v1",
"models_endpoint": "https://openrouter.ai/api/v1/models",
@@ -276,8 +280,9 @@
"deepseek": {
"display_name": "DeepSeek",
"default_model": "deepseek-v4-flash",
- "popular_models": ["deepseek-v4-flash", "deepseek-v4-pro"],
+ "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.",
"detection_patterns": ["deepseek"],
"base_url": "https://api.deepseek.com",
"models_endpoint": "https://api.deepseek.com/models",
@@ -286,6 +291,7 @@
"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,
@@ -293,6 +299,7 @@
},
"context_length": {
"deepseek-v4-flash": 1048576,
+ "deepseek-v4.1-flash": 1048576,
"deepseek-v4-pro": 1048576,
"deepseek-chat": 131072,
"deepseek-reasoner": 131072,
diff --git a/server/config/model_registry.json b/server/config/model_registry.json
index 23e1815b..c17cdb5a 100644
--- a/server/config/model_registry.json
+++ b/server/config/model_registry.json
@@ -1,8 +1,285 @@
{
- "_generated": "2026-09-09T07:22:39.821023+00:00",
+ "_generated": "2026-09-11T20:22:56.766352+00:00",
"_source": "openrouter",
- "_model_count": 431,
+ "_model_count": 443,
"models": {
+ "openai/gpt-astra-latest": {
+ "id": "~openai/gpt-astra-latest",
+ "name": "OpenAI GPT Astra Latest",
+ "provider": "openai",
+ "local_id": "gpt-astra-latest",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 10.0,
+ "output_price_per_mtok": 50.0,
+ "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-sol-latest": {
+ "id": "~openai/gpt-sol-latest",
+ "name": "OpenAI GPT Sol Latest",
+ "provider": "openai",
+ "local_id": "gpt-sol-latest",
+ "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-terra-latest": {
+ "id": "~openai/gpt-terra-latest",
+ "name": "OpenAI GPT Terra Latest",
+ "provider": "openai",
+ "local_id": "gpt-terra-latest",
+ "context_length": 1050000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 2.0,
+ "output_price_per_mtok": 12.0,
+ "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-luna-latest": {
+ "id": "~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,
+ "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"
+ ]
+ },
+ "sakana/fugu-ultra-v2": {
+ "id": "sakana/fugu-ultra-v2",
+ "name": "Sakana: Fugu Ultra v2",
+ "provider": "sakana",
+ "local_id": "fugu-ultra-v2",
+ "context_length": 1000000,
+ "max_output_tokens": 128000,
+ "input_price_per_mtok": 5.0,
+ "output_price_per_mtok": 30.0,
+ "supports_thinking": false,
+ "thinking_type": "none",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "include_reasoning",
+ "reasoning",
+ "reasoning_effort",
+ "structured_outputs",
+ "tool_choice",
+ "tools",
+ "web_search_options"
+ ]
+ },
+ "sakana/fugu-max": {
+ "id": "sakana/fugu-max",
+ "name": "Sakana: Fugu Max",
+ "provider": "sakana",
+ "local_id": "fugu-max",
+ "context_length": 1000000,
+ "max_output_tokens": 128000,
+ "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": [
+ "include_reasoning",
+ "reasoning",
+ "reasoning_effort",
+ "structured_outputs",
+ "tool_choice",
+ "tools",
+ "web_search_options"
+ ]
+ },
+ "inclusionai/ling-3.0-flash-vl": {
+ "id": "inclusionai/ling-3.0-flash-vl",
+ "name": "inclusionAI: Ling 3.0 Flash VL",
+ "provider": "inclusionai",
+ "local_id": "ling-3.0-flash-vl",
+ "context_length": 131072,
+ "max_output_tokens": 32768,
+ "input_price_per_mtok": 0.06,
+ "output_price_per_mtok": 0.18,
+ "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"
+ ]
+ },
+ "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,
+ "supports_thinking": false,
+ "thinking_type": "none",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logprobs",
+ "max_tokens",
+ "presence_penalty",
+ "reasoning",
+ "repetition_penalty",
+ "seed",
+ "stop",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_k",
+ "top_logprobs",
+ "top_p"
+ ]
+ },
+ "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": 384000,
+ "input_price_per_mtok": 0.15,
+ "output_price_per_mtok": 0.6,
+ "supports_thinking": false,
+ "thinking_type": "none",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "frequency_penalty",
+ "include_reasoning",
+ "logit_bias",
+ "logprobs",
+ "max_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"
+ ]
+ },
"inception/mercury-2.5": {
"id": "inception/mercury-2.5",
"name": "Inception: Mercury 2.5",
@@ -605,7 +882,7 @@
"provider": "z-ai",
"local_id": "glm-flash-latest",
"context_length": 1310720,
- "max_output_tokens": 943718,
+ "max_output_tokens": 131072,
"input_price_per_mtok": 0.075,
"output_price_per_mtok": 0.25,
"supports_thinking": false,
@@ -657,10 +934,13 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
+ "logit_bias",
"logprobs",
"max_tokens",
+ "min_p",
"presence_penalty",
"reasoning",
+ "repetition_penalty",
"response_format",
"seed",
"stop",
@@ -680,8 +960,8 @@
"local_id": "glm-5.3-flash",
"context_length": 1310720,
"max_output_tokens": 131072,
- "input_price_per_mtok": 0.075,
- "output_price_per_mtok": 0.25,
+ "input_price_per_mtok": 0.15,
+ "output_price_per_mtok": 0.5,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -911,9 +1191,9 @@
"provider": "z-ai",
"local_id": "glm-latest",
"context_length": 1310720,
- "max_output_tokens": 128000,
- "input_price_per_mtok": 1.113,
- "output_price_per_mtok": 3.498,
+ "max_output_tokens": 943718,
+ "input_price_per_mtok": 0.8727,
+ "output_price_per_mtok": 3.36,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -1081,6 +1361,7 @@
"temperature",
"tool_choice",
"tools",
+ "top_a",
"top_k",
"top_logprobs",
"top_p"
@@ -1318,7 +1599,7 @@
"provider": "deepseek",
"local_id": "deepseek-v4-pro-0813",
"context_length": 1048576,
- "max_output_tokens": 393216,
+ "max_output_tokens": 384000,
"input_price_per_mtok": 0.5795,
"output_price_per_mtok": 1.7384,
"supports_thinking": false,
@@ -1559,8 +1840,8 @@
"local_id": "solar-pro4",
"context_length": 524288,
"max_output_tokens": 131072,
- "input_price_per_mtok": 0.03,
- "output_price_per_mtok": 0.12,
+ "input_price_per_mtok": 0.09,
+ "output_price_per_mtok": 0.36,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -1903,7 +2184,6 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logprobs",
"max_tokens",
"presence_penalty",
"reasoning",
@@ -1912,7 +2192,6 @@
"stop",
"temperature",
"tools",
- "top_logprobs",
"top_p"
]
},
@@ -2254,7 +2533,7 @@
"provider": "thinkingmachines",
"local_id": "inkling",
"context_length": 1048576,
- "max_output_tokens": 471859,
+ "max_output_tokens": 32768,
"input_price_per_mtok": 1.0,
"output_price_per_mtok": 4.05,
"supports_thinking": false,
@@ -2397,8 +2676,8 @@
"local_id": "kimi-k3",
"context_length": 1048576,
"max_output_tokens": 943718,
- "input_price_per_mtok": 3.0,
- "output_price_per_mtok": 15.0,
+ "input_price_per_mtok": 1.89,
+ "output_price_per_mtok": 9.48,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -2999,8 +3278,8 @@
"local_id": "hy3",
"context_length": 262144,
"max_output_tokens": 128000,
- "input_price_per_mtok": 0.132,
- "output_price_per_mtok": 0.528,
+ "input_price_per_mtok": 0.0825,
+ "output_price_per_mtok": 0.33,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -3287,9 +3566,9 @@
"provider": "z-ai",
"local_id": "glm-5.2",
"context_length": 1048576,
- "max_output_tokens": 131072,
- "input_price_per_mtok": 0.966,
- "output_price_per_mtok": 3.036,
+ "max_output_tokens": 182476,
+ "input_price_per_mtok": 0.6,
+ "output_price_per_mtok": 2.0,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -4331,8 +4610,8 @@
"local_id": "kimi-latest",
"context_length": 1048576,
"max_output_tokens": 943718,
- "input_price_per_mtok": 2.4,
- "output_price_per_mtok": 12.0,
+ "input_price_per_mtok": 1.89,
+ "output_price_per_mtok": 9.48,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -4424,35 +4703,6 @@
"verbosity"
]
},
- "openai/gpt-latest": {
- "id": "~openai/gpt-latest",
- "name": "OpenAI GPT Latest",
- "provider": "openai",
- "local_id": "gpt-latest",
- "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"
- ]
- },
"qwen/qwen3.5-plus-20260420": {
"id": "qwen/qwen3.5-plus-20260420",
"name": "Qwen: Qwen3.5 Plus 2026-04-20",
@@ -4754,8 +5004,8 @@
"local_id": "deepseek-v4-pro",
"context_length": 1048576,
"max_output_tokens": 384000,
- "input_price_per_mtok": 0.9553,
- "output_price_per_mtok": 1.9105,
+ "input_price_per_mtok": 0.9478,
+ "output_price_per_mtok": 1.8956,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -4794,8 +5044,8 @@
"local_id": "deepseek-v4-flash",
"context_length": 1048576,
"max_output_tokens": 384000,
- "input_price_per_mtok": 0.0886,
- "output_price_per_mtok": 0.1772,
+ "input_price_per_mtok": 0.0851,
+ "output_price_per_mtok": 0.1702,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -5153,9 +5403,9 @@
"provider": "gemini",
"local_id": "gemma-4-26b-a4b-it",
"context_length": 262144,
- "max_output_tokens": 16384,
- "input_price_per_mtok": 0.07,
- "output_price_per_mtok": 0.34,
+ "max_output_tokens": 32768,
+ "input_price_per_mtok": 0.042,
+ "output_price_per_mtok": 0.22,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -5765,6 +6015,39 @@
"top_p"
]
},
+ "mistralai/mistral-small-2603:batch": {
+ "id": "mistralai/mistral-small-2603:batch",
+ "name": "Mistral: Mistral Small 4 (batch)",
+ "provider": "mistralai",
+ "local_id": "mistral-small-2603:batch",
+ "context_length": 262144,
+ "max_output_tokens": 209715,
+ "input_price_per_mtok": 0.075,
+ "output_price_per_mtok": 0.3,
+ "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",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ]
+ },
"z-ai/glm-5-turbo": {
"id": "z-ai/glm-5-turbo",
"name": "Z.ai: GLM 5 Turbo",
@@ -5813,6 +6096,7 @@
"frequency_penalty",
"include_reasoning",
"logit_bias",
+ "logprobs",
"max_tokens",
"min_p",
"presence_penalty",
@@ -5822,10 +6106,12 @@
"response_format",
"seed",
"stop",
+ "structured_outputs",
"temperature",
"tool_choice",
"tools",
"top_k",
+ "top_logprobs",
"top_p"
]
},
@@ -6277,9 +6563,9 @@
"provider": "qwen",
"local_id": "qwen3.5-122b-a10b",
"context_length": 262144,
- "max_output_tokens": 81920,
- "input_price_per_mtok": 0.29,
- "output_price_per_mtok": 2.4,
+ "max_output_tokens": 65536,
+ "input_price_per_mtok": 0.26,
+ "output_price_per_mtok": 2.08,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -6684,10 +6970,8 @@
"supported_parameters": [
"frequency_penalty",
"include_reasoning",
- "logit_bias",
"logprobs",
"max_tokens",
- "min_p",
"presence_penalty",
"reasoning",
"repetition_penalty",
@@ -7090,7 +7374,7 @@
"name": "Z.ai: GLM 4.7 Flash",
"provider": "z-ai",
"local_id": "glm-4.7-flash",
- "context_length": 202752,
+ "context_length": 200000,
"max_output_tokens": 117964,
"input_price_per_mtok": 0.0605,
"output_price_per_mtok": 0.4,
@@ -7743,6 +8027,36 @@
"top_p"
]
},
+ "mistralai/ministral-8b-2512:batch": {
+ "id": "mistralai/ministral-8b-2512:batch",
+ "name": "Mistral: Ministral 3 8B 2512 (batch)",
+ "provider": "mistralai",
+ "local_id": "ministral-8b-2512:batch",
+ "context_length": 262144,
+ "max_output_tokens": 209715,
+ "input_price_per_mtok": 0.075,
+ "output_price_per_mtok": 0.075,
+ "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/ministral-3b-2512": {
"id": "mistralai/ministral-3b-2512",
"name": "Mistral: Ministral 3 3B 2512",
@@ -7803,6 +8117,36 @@
"top_p"
]
},
+ "mistralai/mistral-large-2512:batch": {
+ "id": "mistralai/mistral-large-2512:batch",
+ "name": "Mistral: Mistral Large 3 2512 (batch)",
+ "provider": "mistralai",
+ "local_id": "mistral-large-2512:batch",
+ "context_length": 262144,
+ "max_output_tokens": 209715,
+ "input_price_per_mtok": 0.25,
+ "output_price_per_mtok": 0.75,
+ "supports_thinking": false,
+ "thinking_type": "none",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ]
+ },
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek: DeepSeek V3.2",
@@ -8048,7 +8392,7 @@
"provider": "moonshotai",
"local_id": "kimi-k2-thinking",
"context_length": 262144,
- "max_output_tokens": 235929,
+ "max_output_tokens": 100352,
"input_price_per_mtok": 0.6,
"output_price_per_mtok": 2.5,
"supports_thinking": false,
@@ -9209,35 +9553,6 @@
"top_p"
]
},
- "nousresearch/hermes-4-70b": {
- "id": "nousresearch/hermes-4-70b",
- "name": "Nous: Hermes 4 70B",
- "provider": "nousresearch",
- "local_id": "hermes-4-70b",
- "context_length": 131072,
- "max_output_tokens": 117964,
- "input_price_per_mtok": 0.13,
- "output_price_per_mtok": 0.4,
- "supports_thinking": false,
- "thinking_type": "none",
- "temperature_range": [
- 0.0,
- 2.0
- ],
- "is_reasoning_model": false,
- "supported_parameters": [
- "frequency_penalty",
- "include_reasoning",
- "max_tokens",
- "presence_penalty",
- "reasoning",
- "repetition_penalty",
- "response_format",
- "temperature",
- "top_k",
- "top_p"
- ]
- },
"nousresearch/hermes-4-405b": {
"id": "nousresearch/hermes-4-405b",
"name": "Nous: Hermes 4 405B",
@@ -9335,6 +9650,36 @@
"top_p"
]
},
+ "mistralai/mistral-medium-3.1:batch": {
+ "id": "mistralai/mistral-medium-3.1:batch",
+ "name": "Mistral: Mistral Medium 3.1 (batch)",
+ "provider": "mistralai",
+ "local_id": "mistral-medium-3.1:batch",
+ "context_length": 131072,
+ "max_output_tokens": 104857,
+ "input_price_per_mtok": 0.2,
+ "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",
+ "max_tokens",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ]
+ },
"z-ai/glm-4.5v": {
"id": "z-ai/glm-4.5v",
"name": "Z.ai: GLM 4.5V",
@@ -9775,6 +10120,37 @@
"top_p"
]
},
+ "mistralai/codestral-2508:batch": {
+ "id": "mistralai/codestral-2508:batch",
+ "name": "Mistral: Codestral 2508 (batch)",
+ "provider": "mistralai",
+ "local_id": "codestral-2508:batch",
+ "context_length": 256000,
+ "max_output_tokens": 204800,
+ "input_price_per_mtok": 0.15,
+ "output_price_per_mtok": 0.45,
+ "supports_thinking": false,
+ "thinking_type": "none",
+ "temperature_range": [
+ 0.0,
+ 2.0
+ ],
+ "is_reasoning_model": false,
+ "supported_parameters": [
+ "frequency_penalty",
+ "max_tokens",
+ "prediction",
+ "presence_penalty",
+ "response_format",
+ "seed",
+ "stop",
+ "structured_outputs",
+ "temperature",
+ "tool_choice",
+ "tools",
+ "top_p"
+ ]
+ },
"qwen/qwen3-coder-30b-a3b-instruct": {
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
@@ -9815,9 +10191,9 @@
"provider": "qwen",
"local_id": "qwen3-30b-a3b-instruct-2507",
"context_length": 262144,
- "max_output_tokens": 32000,
- "input_price_per_mtok": 0.0481,
- "output_price_per_mtok": 0.193,
+ "max_output_tokens": 235929,
+ "input_price_per_mtok": 0.09,
+ "output_price_per_mtok": 0.3,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -11247,8 +11623,8 @@
"local_id": "deepseek-chat-v3-0324",
"context_length": 163840,
"max_output_tokens": 147456,
- "input_price_per_mtok": 0.29,
- "output_price_per_mtok": 1.14,
+ "input_price_per_mtok": 0.25,
+ "output_price_per_mtok": 1.0,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
@@ -11993,9 +12369,9 @@
"provider": "deepseek",
"local_id": "deepseek-chat",
"context_length": 163840,
- "max_output_tokens": 16384,
- "input_price_per_mtok": 0.32,
- "output_price_per_mtok": 0.89,
+ "max_output_tokens": 16000,
+ "input_price_per_mtok": 0.2574,
+ "output_price_per_mtok": 1.0287,
"supports_thinking": false,
"thinking_type": "none",
"temperature_range": [
diff --git a/server/services/model_registry.py b/server/services/model_registry.py
index 589e14a3..d330e387 100644
--- a/server/services/model_registry.py
+++ b/server/services/model_registry.py
@@ -42,7 +42,7 @@ THINKING_PATTERNS: List[Tuple[str, str, str]] = [
("anthropic", r"claude-(opus|sonnet|haiku)-(4|5|6)", "budget"),
("anthropic", r"claude-3[\.\-]5", "budget"),
("openai", r"^(o1|o3|o4)", "effort"),
- ("openai", r"^gpt-5", "effort"), # GPT-5 hybrid reasoning
+ ("openai", r"^gpt-(5|6)", "effort"), # GPT-5 / GPT-6 hybrid reasoning
("gemini", r"gemini-(2\.5|3)", "budget"),
("groq", r"qwen3", "format"),
("cerebras", r"qwen", "budget"),