auto_storiesModel Wiki

Gemini 3.5 Flash is a large language model from Google. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 3.1 Flash Lite is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 3.1 Flash Lite Preview is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Nano Banana 2 is a large language model from Google, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 3.1 Pro Preview Custom Tools is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 3.1 Pro Preview is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 3 Flash Preview is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 3 Pro Preview is a large language model from Google, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini Flash Latest is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini Flash-Lite Latest is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Nano Banana is a large language model from Google, with an approximate context window of 32,768 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.5 Flash-Lite is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini Embedding 001 is a large language model from Google, with an approximate context window of 2,048 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.5 Pro Preview TTS is a large language model from Google, with an approximate context window of 8,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.5 Flash Preview TTS is a large language model from Google, with an approximate context window of 8,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.5 Pro is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.5 Flash is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.5 Pro

Google advanced multimodal model for long-context and reasoning-heavy tasks

Gemini 2.5 Pro is Google's high-capability Gemini model, useful for complex reasoning, long-context analysis and multimodal applications across text and media inputs.

Gemini 2.5 Flash

Fast Gemini model for low-latency multimodal and high-throughput tasks

Gemini 2.5 Flash is optimized for speed and efficiency, making it suitable for interactive products, lightweight reasoning and high-volume calls.

Gemini 2.0 Flash-Lite is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Gemini 2.0 Flash is a large language model from Google, with an approximate context window of 1,048,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

DeepSeek V4 Pro is a large language model from DeepSeek, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

DeepSeek V4 Flash is a large language model from DeepSeek, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

DeepSeek Reasoner is a large language model from DeepSeek, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

DeepSeek Chat

DeepSeek Chat model profile for capabilities, pricing and use cases

DeepSeek Chat is a large language model from DeepSeek. This entry summarizes its positioning, typical use cases, strengths, limitations and related pricing signals for quick comparison.

GPT-5.5 Pro is a large language model from OpenAI, with an approximate context window of 1,050,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.4 Pro is a large language model from OpenAI, with an approximate context window of 1,050,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.3 Chat (latest) is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.3 Codex Spark is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.3 Codex is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.2 is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.2 Pro is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.2 Chat is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.2 Codex is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.1 Codex mini is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.1 Chat is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.1 is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.1 Codex Max is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.1 Codex is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5 Pro is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5-Codex is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5 Chat (latest) is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5 Nano is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5 is a large language model from OpenAI, with an approximate context window of 400,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5 Mini is a large language model from OpenAI. This entry summarizes its positioning, typical use cases, strengths, limitations and related pricing signals for quick comparison.

o3-pro is a large language model from OpenAI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o4-mini is a large language model from OpenAI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o3 is a large language model from OpenAI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4.1 is a large language model from OpenAI, with an approximate context window of 1,047,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4.1 mini is a large language model from OpenAI, with an approximate context window of 1,047,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4.1 nano is a large language model from OpenAI, with an approximate context window of 1,047,576 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o1-pro is a large language model from OpenAI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o3-mini is a large language model from OpenAI. This entry summarizes its positioning, typical use cases, strengths, limitations and related pricing signals for quick comparison.

o1 is a large language model from OpenAI. This entry summarizes its positioning, typical use cases, strengths, limitations and related pricing signals for quick comparison.

GPT-4o (2024-11-20) is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o1-preview is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o1-mini is a large language model from OpenAI. This entry summarizes its positioning, typical use cases, strengths, limitations and related pricing signals for quick comparison.

GPT-4o (2024-08-06) is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4o mini is a lightweight OpenAI model designed for lower-cost, high-throughput applications while keeping useful multimodal and tool-assisted capabilities.

o4-mini-deep-research is a large language model from OpenAI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

o3-deep-research is a large language model from OpenAI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4o (2024-05-13) is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4o is OpenAI's general-purpose flagship multimodal model. It is suitable for products that need strong text understanding, image analysis, code assistance, tool calling and stable conversation quality at scale.

text-embedding-3-large is a large language model from OpenAI, with an approximate context window of 8,191 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

text-embedding-3-small is a large language model from OpenAI, with an approximate context window of 8,191 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4 Turbo is a large language model from OpenAI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-4 is a large language model from OpenAI, with an approximate context window of 8,192 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-3.5-turbo is a large language model from OpenAI, with an approximate context window of 16,385 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

text-embedding-ada-002 is a large language model from OpenAI, with an approximate context window of 8,192 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GPT-5.4 nano is an OpenAI general-purpose model for batch tagging, simple extraction, routing, preprocessing and extremely cost-sensitive workloads.

GPT-5.4 is an OpenAI general-purpose model for product assistants, content generation, coding assistance, structured processing and multimodal understanding.

GPT-5.4 mini is an OpenAI general-purpose model for high-volume support, summarization, rewriting, lightweight classification and cost-sensitive automation.

GPT-5.5 is an OpenAI general-purpose model for hard Q&A, complex coding, long-form analysis and agent workflows.

GPT Image 2 is an OpenAI image model for text-to-image generation, image editing, creative design and visual content workflows.

GPT Realtime 2 is an OpenAI realtime model for low-latency voice input, voice output and interactive conversational experiences.

GPT Realtime mini is an OpenAI realtime model for low-latency voice input, voice output and interactive conversational experiences.

GPT Realtime 1.5 is an OpenAI realtime model for low-latency voice input, voice output and interactive conversational experiences.

GPT Realtime Translate focuses on low-latency speech translation for cross-language calls, meetings and voice products.

GPT Realtime Whisper is an OpenAI speech-to-text model for transcription, captions, voice input and audio content processing.

GPT-4o Transcribe is an OpenAI speech-to-text model for transcription, captions, voice input and audio content processing.

GPT-4o mini Transcribe is an OpenAI speech-to-text model for transcription, captions, voice input and audio content processing.

Kimi K2.6 is a large language model from Moonshot AI, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Kimi K2.5 is a large language model from Moonshot AI, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Kimi K2 Thinking is a large language model from Moonshot AI, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Kimi K2 Thinking Turbo is a large language model from Moonshot AI, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Kimi K2 0905 is a large language model from Moonshot AI, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Kimi K2 Turbo is a large language model from Moonshot AI, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Kimi K2 0711 is a large language model from Moonshot AI, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Moonshot v1 128K is a Moonshot/Kimi model for very long-document analysis, retrieval-augmented reading and complex context workflows, often evaluated for Chinese document and knowledge workflows.

Kimi K2 is a Moonshot/Kimi model for complex reasoning, coding, agent workflows and higher-value production tasks, often evaluated for Chinese document and knowledge workflows.

Claude Opus 4.7 is a large language model from Anthropic, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Sonnet 4.6 is a large language model from Anthropic, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Opus 4.6 is a large language model from Anthropic, with an approximate context window of 1,000,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Opus 4.5 (latest) is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Haiku 4.5 (latest) is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Sonnet 4.5

Claude Sonnet model optimized for coding, agents and complex workflows

Claude Sonnet 4.5 is positioned as a high-quality model for coding, long-form reasoning, agent workflows and structured professional writing. It is a strong option when reliability and instruction following matter.

Claude Opus 4.1 (latest) is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Opus 4 (latest) is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Sonnet 4 (latest) is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Sonnet 4

Claude Sonnet 4 model profile for capabilities, pricing and use cases

Claude Sonnet 4 is a large language model from Anthropic. This entry summarizes its positioning, typical use cases, strengths, limitations and related pricing signals for quick comparison.

Claude Opus 4

High-end Claude model for difficult reasoning, coding and long-running work

Claude Opus 4 is positioned for demanding tasks that need stronger reasoning, deeper code understanding and careful execution over longer workflows.

Claude Sonnet 3.7 is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Haiku 3.5 (latest) is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Haiku 3.5 is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Sonnet 3.5 v2 is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Haiku 3 is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Sonnet 3 is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Claude Opus 3 is a large language model from Anthropic, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Step 3.5 Flash 2603 is a large language model from stepfun, with an approximate context window of 256,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Step 3.5 Flash is a large language model from stepfun. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Step 1 32K is a StepFun model for document understanding, summarization and knowledge Q&A, commonly evaluated for Chinese assistants, document and multimodal workflows.

Step 1 128K is a StepFun model for very long-document analysis and retrieval-augmented workflows, commonly evaluated for Chinese assistants, document and multimodal workflows.

Step 2 Mini is a StepFun model for low-latency and cost-sensitive high-volume workloads, commonly evaluated for Chinese assistants, document and multimodal workflows.

Step 1V 8K is a StepFun model for visual Q&A, multimodal analysis and image-text understanding, commonly evaluated for Chinese assistants, document and multimodal workflows.

Mistral Small 4 is a large language model from Mistral, with an approximate context window of 256,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Devstral 2 is a large language model from Mistral, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Devstral Small 2 is a large language model from Mistral, with an approximate context window of 256,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Devstral 2 (latest) is a large language model from Mistral, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral Medium 3.1 is a large language model from Mistral, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Devstral Medium is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Devstral Small is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral Small 3.2 is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Devstral Small 2505 is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral Medium 3 is a large language model from Mistral, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Magistral Medium (latest) is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Magistral Small is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral Large 3 is a large language model from Mistral, with an approximate context window of 262,144 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral Large 2.1 is a large language model from Mistral, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Ministral 3B (latest) is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Pixtral 12B is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral Nemo is a large language model from Mistral, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mixtral 8x22B is a large language model from Mistral, with an approximate context window of 64,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mixtral 8x7B is a large language model from Mistral, with an approximate context window of 32,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Mistral 7B is a large language model from Mistral, with an approximate context window of 8,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Codestral is a Mistral model for code completion, code generation and developer assistance, with options across enterprise, coding, vision and open-weight workflows.

Mistral Small is a Mistral model for low-latency high-concurrency and cost-sensitive workloads, with options across enterprise, coding, vision and open-weight workflows.

Mistral Large is a Mistral model for complex reasoning, enterprise Q&A and multilingual tasks, with options across enterprise, coding, vision and open-weight workflows.

Ministral 8B is a Mistral model for edge deployment, low-cost usage and basic text tasks, with options across enterprise, coding, vision and open-weight workflows.

Pixtral Large is a Mistral model for image-text understanding, visual Q&A and multimodal analysis, with options across enterprise, coding, vision and open-weight workflows.

Mixtral 8x7B is a Mistral model for general language tasks, research and self-hosted deployments, with options across enterprise, coding, vision and open-weight workflows.

GLM-4.7-FlashX is a large language model from Zhipu AI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.7-Flash is a large language model from Zhipu AI, with an approximate context window of 200,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.7 is a large language model from Zhipu AI, with an approximate context window of 204,800 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.6V is a large language model from Zhipu AI, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.6 is a large language model from Zhipu AI, with an approximate context window of 204,800 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.5V is a large language model from Zhipu AI, with an approximate context window of 64,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.5-Air is a large language model from Zhipu AI, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.5 is a large language model from Zhipu AI, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4.5-Flash is a large language model from Zhipu AI, with an approximate context window of 131,072 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

GLM-4-Air is a Zhipu AI GLM model for low-cost high-concurrency Chinese assistant workloads, commonly evaluated for Chinese enterprise and agent workflows.

GLM-4-Flash is a Zhipu AI GLM model for fast responses, lightweight automation and high-frequency conversations, commonly evaluated for Chinese enterprise and agent workflows.

GLM-4.5 is a Zhipu AI GLM model for agent workflows, coding and complex reasoning tasks, commonly evaluated for Chinese enterprise and agent workflows.

GLM-Z1 is a Zhipu AI GLM model for multi-step reasoning, math, coding and complex problem solving, commonly evaluated for Chinese enterprise and agent workflows.

Command A Translate is a large language model from Cohere, with an approximate context window of 8,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command A Reasoning is a large language model from Cohere, with an approximate context window of 256,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command A Vision is a large language model from Cohere, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command A is a large language model from Cohere, with an approximate context window of 256,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command R7B Arabic is a large language model from Cohere, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command R is a large language model from Cohere, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command R+ is a large language model from Cohere, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command R7B is a large language model from Cohere, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Command A is a Cohere generation model for enterprise Q&A, RAG, agents and multilingual generation.

Command R+ is a Cohere generation model for enterprise Q&A, RAG, agents and multilingual generation.

Command R is a Cohere generation model for enterprise Q&A, RAG, agents and multilingual generation.

Command Light is a Cohere generation model for enterprise Q&A, RAG, agents and multilingual generation.

Embed v4.0 is a Cohere embedding model for semantic search, RAG indexing, clustering and similarity workflows.

Rerank v3.5 is a Cohere reranking model for search reranking, RAG refinement and answer-quality improvements.

Llama-4-Maverick-17B-128E-Instruct-FP8 is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Cerebras-Llama-4-Scout-17B-16E-Instruct is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Llama-4-Scout-17B-16E-Instruct-FP8 is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Cerebras-Llama-4-Maverick-17B-128E-Instruct is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Groq-Llama-4-Maverick-17B-128E-Instruct is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Llama-3.3-8B-Instruct is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Llama-3.3-70B-Instruct is a large language model from llama, with an approximate context window of 128,000 tokens. It can be evaluated for assistants, knowledge Q&A, content generation, structured extraction and business automation. Pricing and availability may vary by upstream provider or relay service.

Llama 3.1 8B is a Meta Llama model for local deployment, basic chat and low-cost inference, commonly evaluated for open ecosystems, self-hosting and customizable AI products.

Llama 3.1 70B is a Meta Llama model for general language understanding, generation and enterprise self-hosting, commonly evaluated for open ecosystems, self-hosting and customizable AI products.

Llama 3.1 405B is a Meta Llama model for complex reasoning, multilingual tasks and high-quality generation, commonly evaluated for open ecosystems, self-hosting and customizable AI products.

Llama 3.2 Vision is a Meta Llama model for image-text understanding, visual Q&A and multimodal applications, commonly evaluated for open ecosystems, self-hosting and customizable AI products.

Llama 4 Scout is a Meta Llama model for multimodal, long-context and efficient reasoning workflows, commonly evaluated for open ecosystems, self-hosting and customizable AI products.

Llama 4 Maverick is a Meta Llama model for complex multimodal tasks, agents and high-quality generation, commonly evaluated for open ecosystems, self-hosting and customizable AI products.

MiMo V2.5 is a Xiaomi MiMo model for Chinese conversation, content generation and tool-use workflows, useful for Chinese assistants, tool use and ecosystem-oriented applications.

MiMo V2.5 Pro is a Xiaomi MiMo model for complex reasoning, coding and long-text tasks, useful for Chinese assistants, tool use and ecosystem-oriented applications.

MiMo V2 Flash is a Xiaomi MiMo model for low-latency high-frequency chat and quick responses, useful for Chinese assistants, tool use and ecosystem-oriented applications.

MiMo V2 Omni is a Xiaomi MiMo model for multimodal understanding and integrated interactive experiences, useful for Chinese assistants, tool use and ecosystem-oriented applications.

MiMo V2 Pro is a Xiaomi MiMo model for complex tasks, coding assistance and business automation, useful for Chinese assistants, tool use and ecosystem-oriented applications.

ABAB6.5s Chat is a MiniMax model for Chinese chat, writing and business assistant workloads, often evaluated for Chinese assistants, generation and multimedia workflows.

ABAB6.5 Chat is a MiniMax model for general conversation, long-text understanding and complex interactions, often evaluated for Chinese assistants, generation and multimedia workflows.

MiniMax Text 01 is a MiniMax model for general language understanding, generation and agent workflows, often evaluated for Chinese assistants, generation and multimedia workflows.

MiniMax M1 is a MiniMax model for long-context reasoning, coding and complex task planning, often evaluated for Chinese assistants, generation and multimedia workflows.

MiniMax Speech 01 focuses on voice generation and multimedia experiences rather than general text conversation.

Doubao Pro is a Volcengine Doubao model for higher-quality Chinese assistants, content generation and business automation, often evaluated for Chinese enterprise and multimodal workflows.

Doubao Lite is a Volcengine Doubao model for low-cost high-concurrency chat and lightweight text tasks, often evaluated for Chinese enterprise and multimodal workflows.

Doubao Seed 1.6 is a Volcengine Doubao model for general chat, reasoning and agent workflow evaluation, often evaluated for Chinese enterprise and multimodal workflows.

Doubao Seed 1.6 Thinking is a Volcengine Doubao model for complex reasoning, multi-step analysis and coding assistance, often evaluated for Chinese enterprise and multimodal workflows.

Doubao Vision Pro is a Volcengine Doubao model for image-text analysis, multimodal Q&A and visual content understanding, often evaluated for Chinese enterprise and multimodal workflows.

ERNIE 4.0 Turbo 8K is a Baidu ERNIE/Qianfan model for Chinese understanding, content generation and enterprise applications, commonly evaluated for Chinese enterprise workloads.

ERNIE 4.5 Turbo is a Baidu ERNIE/Qianfan model for multi-scenario Chinese tasks, knowledge Q&A and business assistants, commonly evaluated for Chinese enterprise workloads.

ERNIE X1 is a Baidu ERNIE/Qianfan model for complex analysis, logical reasoning and multi-step problem solving, commonly evaluated for Chinese enterprise workloads.

ERNIE Speed is a Baidu ERNIE/Qianfan model for low-latency conversations and high-frequency basic text tasks, commonly evaluated for Chinese enterprise workloads.

ERNIE Lite is a Baidu ERNIE/Qianfan model for cost-sensitive Q&A, summarization and content generation, commonly evaluated for Chinese enterprise workloads.