Update AI model specifications and descriptions in models.ts

- Revised the description for Claude Sonnet 4.5 to correct punctuation.
- Updated the model ID and name for Google Gemini from 2.5 to 3.1, along with its description and context length.
- Enhanced the pricing structure for Gemini models, adjusting values for prompt, completion, and internal reasoning.
- Modified input modalities for Gemini models to include video and improve overall clarity in descriptions.

Author: gokulkrishh

data/models.ts

@@ -6,7 +6,7 @@ const models = [
     name: "Anthropic: Claude Sonnet 4.5",
     created: 1759161676,
     description:
-      "Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.",
+      "Claude Sonnet 4.5 is Anthropic's most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.",
     context_length: 1000000,
     architecture: {
       modality: "text+image-\u003Etext",
@@ -282,33 +282,33 @@ const models = [
     ],
   },
   {
-    id: "google/gemini-2.5-pro-preview-05-06",
-    canonical_slug: "google/gemini-2.5-pro-preview-03-25",
+    id: "google/gemini-3.1-pro-preview-customtools",
+    canonical_slug: "google/gemini-3.1-pro-preview-customtools",
     hugging_face_id: "",
-    name: "Google: Gemini 2.5 Pro Preview 05-06",
-    created: 1746578513,
+    name: "Google: Gemini 3.1 Pro Preview",
+    created: 1762300000,
     description:
-      "Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.",
-    context_length: 1048576,
+      "Gemini 3.1 Pro Preview is Google's latest state-of-the-art AI model with improved tool selection behavior, multimodal reasoning across text, image, video, audio, and code, a 1M-token context window, and strong software engineering performance. It significantly increases function calling reliability and ensures the model selects the most appropriate tool in coding agents and complex, multi-tool workflows.",
+    context_length: 1048756,
     architecture: {
       modality: "text+image-\u003Etext",
-      input_modalities: ["text", "image", "file", "audio"],
+      input_modalities: ["text", "audio", "image", "video", "file"],
       output_modalities: ["text"],
       tokenizer: "Gemini",
       instruct_type: null,
     },
     pricing: {
-      prompt: "0.00000125",
-      completion: "0.00001",
+      prompt: "0.000002",
+      completion: "0.000012",
       request: "0",
-      image: "0.00516",
+      image: "0.000002",
       web_search: "0",
-      internal_reasoning: "0",
-      input_cache_read: "0.00000031",
-      input_cache_write: "0.000001625",
+      internal_reasoning: "0.000012",
+      input_cache_read: "0.0000002",
+      input_cache_write: "0.000000375",
     },
     top_provider: {
-      context_length: 1048576,
+      context_length: 1048756,
       max_completion_tokens: 65535,
       is_moderated: false,
     },
@@ -376,7 +376,7 @@ const models = [
     name: "DeepSeek: Deepseek R1 0528 Qwen3 8B (free)",
     created: 1748538543,
     description:
-      "DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.\nIt now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.\nThe distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.",
+      'DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.\nIt now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought.\nThe distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B "thinking" giant on AIME 2024.',
     context_length: 131072,
     architecture: {
       modality: "text-\u003Etext",
@@ -418,30 +418,29 @@ const models = [
     ],
   },
   {
-    id: "google/gemini-2.5-flash-lite-preview-06-17",
-    canonical_slug: "google/gemini-2.5-flash-lite-preview-06-17",
+    id: "google/gemini-3.1-flash-lite-preview",
+    canonical_slug: "google/gemini-3.1-flash-lite-preview",
     hugging_face_id: "",
-    name: "Google: Gemini 2.5 Flash Lite Preview 06-17",
-    created: 1750173831,
+    name: "Google: Gemini 3.1 Flash Lite Preview",
+    created: 1762300000,
     description:
-      'Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the [Reasoning API parameter](https://openrouter.ai/docs/use-cases/reasoning-tokens) to selectively trade off cost for intelligence. ',
+      "Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.",
     context_length: 1048576,
     architecture: {
       modality: "text+image-\u003Etext",
-      input_modalities: ["file", "image", "text", "audio"],
+      input_modalities: ["text", "image", "video", "file", "audio"],
       output_modalities: ["text"],
       tokenizer: "Gemini",
       instruct_type: null,
     },
     pricing: {
-      prompt: "0.0000001",
-      completion: "0.0000004",
+      prompt: "0.00000025",
+      completion: "0.0000015",
       request: "0",
-      image: "0",
+      image: "0.00000025",
       web_search: "0",
-      internal_reasoning: "0",
+      internal_reasoning: "0.0000015",
       input_cache_read: "0.000000025",
-      input_cache_write: "0.0000001833",
     },
     top_provider: {
       context_length: 1048576,
@@ -464,32 +463,32 @@ const models = [
     ],
   },
   {
-    id: "openai/gpt-5",
-    canonical_slug: "openai/gpt-5-2025-08-07",
+    id: "openai/gpt-5.4",
+    canonical_slug: "openai/gpt-5.4",
     hugging_face_id: "",
-    name: "OpenAI: GPT-5",
-    created: 1754587413,
+    name: "OpenAI: GPT-5.4",
+    created: 1762300000,
     description:
-      'GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.',
-    context_length: 400000,
+      "GPT-5.4 is OpenAI's latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.",
+    context_length: 1050000,
     architecture: {
-      modality: "text+image-\u003Etext",
+      modality: "text+image->text",
       input_modalities: ["text", "image", "file"],
       output_modalities: ["text"],
       tokenizer: "GPT",
       instruct_type: null,
     },
     pricing: {
-      prompt: "0.00000125",
-      completion: "0.00001",
+      prompt: "0.0000025",
+      completion: "0.000015",
       request: "0",
       image: "0",
       web_search: "0",
       internal_reasoning: "0",
-      input_cache_read: "0.000000125",
+      input_cache_read: "0.00000025",
     },
     top_provider: {
-      context_length: 400000,
+      context_length: 1050000,
       max_completion_tokens: 128000,
       is_moderated: true,
     },
@@ -501,9 +500,23 @@ const models = [
       "response_format",
       "seed",
       "structured_outputs",
+      "stop",
+      "frequency_penalty",
+      "presence_penalty",
+      "logit_bias",
+      "logprobs",
+      "top_logprobs",
       "tool_choice",
       "tools",
     ],
+    default_parameters: {
+      temperature: null,
+      top_p: null,
+      top_k: null,
+      frequency_penalty: null,
+      presence_penalty: null,
+      repetition_penalty: null,
+    },
   },
   {
     id: "moonshotai/kimi-k2-0905",
@@ -556,31 +569,59 @@ const models = [
     ],
   },
   {
-    id: "openai/gpt-4.1",
-    canonical_slug: "openai/gpt-4.1-2025-04-14",
+    id: "openai/gpt-5.4-pro",
+    canonical_slug: "openai/gpt-5.4-pro",
     hugging_face_id: "",
-    name: "OpenAI: GPT-4.1",
-    created: 1744651385,
+    name: "OpenAI: GPT-5.4 Pro",
+    created: 1762300000,
     description:
-      "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.",
-    context_length: 1047576,
+      "GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.",
+    context_length: 1050000,
     architecture: {
-      modality: "text+image->text",
-      input_modalities: ["image", "text", "file"],
+      modality: "text+image-\u003Etext",
+      input_modalities: ["text", "image", "file"],
       output_modalities: ["text"],
       tokenizer: "GPT",
       instruct_type: null,
     },
     pricing: {
-      prompt: "0.000002",
-      completion: "0.000008",
+      prompt: "0.00003",
+      completion: "0.00018",
       request: "0",
       image: "0",
       web_search: "0",
       internal_reasoning: "0",
-      input_cache_read: "0.0000005",
     },
-    top_provider: { context_length: 1047576, max_completion_tokens: 32768, is_moderated: true },
+    top_provider: {
+      context_length: 1050000,
+      max_completion_tokens: 128000,
+      is_moderated: true,
+    },
+    per_request_limits: null,
+    supported_parameters: [
+      "include_reasoning",
+      "max_tokens",
+      "reasoning",
+      "response_format",
+      "seed",
+      "structured_outputs",
+      "stop",
+      "frequency_penalty",
+      "presence_penalty",
+      "logit_bias",
+      "logprobs",
+      "top_logprobs",
+      "tool_choice",
+      "tools",
+    ],
+    default_parameters: {
+      temperature: null,
+      top_p: null,
+      top_k: null,
+      frequency_penalty: null,
+      presence_penalty: null,
+      repetition_penalty: null,
+    },
   },
   {
     id: "openai/gpt-oss-20b:free",
@@ -589,7 +630,7 @@ const models = [
     name: "OpenAI: GTP-OSS-20b (free)",
     created: 1754414229,
     description:
-      "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.",
+      "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI's Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.",
     context_length: 131072,
     architecture: {
       modality: "text-\u003Etext",