Modeller

Google DeepMind's workhorse Flash model that builds on Gemini 3.5 Flash with better coding, knowledge work, and multimodal performance while reducing output token usage by roughly 17% per the Artificial Analysis Index. Natively multimodal across text, image, audio, and video with a 1M-token context window, configurable thinking levels, and built-in computer use, tuned for scaling agentic workflows at a lower cost per output token.

Google's fastest and most cost-effective Gemini 3.5-class model, delivering around 350 output tokens per second per the Artificial Analysis Index. Designed for low-latency and high-throughput agentic workflows such as agentic search and document processing, with configurable thinking levels, built-in computer use, and full multimodal support across a 1M-token context window.

Anthropic's new state-of-the-art model, a thoughtful and proactive successor to Opus 4.8 that approaches Claude Fable 5's frontier intelligence at half the price. Delivers major gains in coding, agentic workflows, computer use, knowledge work, and scientific research, with strong self-verification and iteration, configurable effort settings, and Anthropic's best alignment and safety results to date. Also available in a Fast mode that runs around 2.5x the default speed.

Thinking Machines Lab's open-weights general-purpose multimodal Mixture-of-Experts model with 975B total parameters and 41B active parameters. Inkling accepts text, image, and audio inputs, produces text, and is designed for agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation.

Meta Superintelligence Labs' updated flagship, building on Muse Spark with stronger agentic reasoning, more reliable multi-agent orchestration, and improved multimodal understanding across voice, text, and image. Extends the context window and reduces latency and reasoning token usage while raising coding and tool-use accuracy. Powers Meta AI across its product ecosystem.

Google DeepMind'in yeni bir temel üzerinde yeniden geliştirdiği amiral gemisi Gemini modeli; 2 milyon token bağlam penceresi ve en zor matematik, kodlama ve multimodal görevler için Deep Think reasoning modu sunar. Metin, görüntü, ses ve videoyu yerel olarak işler; akışlı fonksiyon çağırmayı ve güvenilir uzun bağlam kullanımını destekler.

OpenAI GPT-5.6 serisinin dengeli modeli; en yüksek kalite düzeyinden bir miktar ödün verirken belirgin şekilde daha düşük gecikme ve maliyet sunar. Ayarlanabilir akıl yürütme derinliğiyle güçlü reasoning, kodlama ve agent tabanlı araç kullanımını korur. Bu nedenle ileri yeteneklere ihtiyaç duyan yüksek hacimli production iş yükleri için varsayılan seçenek olmaya uygundur.

The fast, low-cost tier of OpenAI's GPT-5.6 series, optimized for high-volume, latency-sensitive tasks such as classification, extraction, routing, and lightweight agentic steps. Approaches the larger GPT-5.6 tiers on many benchmarks while running several times faster at a fraction of the price.

OpenAI GPT-5.6 serisinin amiral gemisi modeli; zorlu gerçek dünya görevlerinde güvenilirliği ve verimliliği artırırken kodlama, bilimsel akıl yürütme, uzun vadeli planlama ve agent iş akışlarını geliştirir. Maksimum reasoning-effort ayarı ve karmaşık çok adımlı çalışmalar için alt agent'lar başlatan ultra modunu ekler.

xAI'nin bugüne kadarki en yetenekli modeli; kodlama, agent görevleri ve bilgi çalışması için geliştirilmiş, gerçek yazılım geliştirme araçlarıyla birlikte tasarlanmıştır. OpenAI uyumlu API üzerinden güncel bilgiye erişimi, genişletilmiş akıl yürütmeyi ve geniş bağlamda araç kullanımını destekler.

Anthropic'in en yetenekli Sonnet sınıfı modeli; ileri kodlama, agent ve profesyonel çalışma yeteneklerini orta segmente taşır ve daha düşük fiyatla Opus 4.8 arasındaki farkı azaltır. Seçilebilir reasoning derinliğiyle uyarlanabilir düşünmeyi, 1 milyon token bağlam penceresini ve metin, görüntü ve dosya girişlerini destekler. Kod adı Fennec'tir.

Cohere's enterprise flagship model building on Command A with stronger reasoning, agentic tool use, and multilingual performance across 23 languages. Optimized for secure, high-throughput RAG, retrieval, and long-horizon agent workflows in regulated environments, with private and on-premise deployment options.

Google DeepMind's experimental diffusion-based member of the Gemma 4 open model family. Unlike autoregressive models that generate text one token at a time, DiffusionGemma denoises a canvas of placeholder tokens to produce up to 256 tokens in parallel, finalizing output in one block. A Mixture-of-Experts model with 26B total parameters and 3.8B active per inference, delivering roughly 4x the throughput of similarly sized autoregressive Gemma models on local hardware. Excels at non-linear tasks like in-line editing, molecular sequencing, mathematical graphing, and self-correcting puzzles.

Google's medium-size open-weight model with 12 billion parameters from the Gemma 4 family. Encoder-free unified multimodal architecture that natively processes text, image, audio, and video inputs without dedicated encoders. Features a 256K context window and supports 140+ languages. First medium-sized model capable of natively ingesting audio. Suitable for local deployment on GPUs with 16GB VRAM.

NVIDIA's flagship open 550B-parameter Mixture-of-Experts model with 55B active parameters, built for frontier reasoning and orchestration in long-running agentic systems. Features hybrid Mamba-Transformer architecture, LatentMoE routing, multi-token prediction, and NVFP4 precision for 5x higher throughput. Achieves 30% lower cost-to-task-completion on agentic benchmarks. Supports 1M+ token context window with 95% accuracy on Ruler@1M.

Anthropic'in en gelişmiş modeli; Opus 4.7'nin üzerine kodlama, agent yetenekleri, akıl yürütme ve bilgi çalışmasında daha güçlü performans ekler. Daha dürüst yanıtlar, daha verimli araç kullanımı, dinamik iş akışı desteği ve iyileştirilmiş uyum sunar.

Writer's most advanced adaptive reasoning model with a 1 million token context window. Processes full million-token prompts in approximately 22 seconds with multi-turn function calls in 300ms. Optimized for enterprise agentic AI workflows at 3-4x lower cost than GPT-4.1.

Databricks' open-source 132B parameter Mixture-of-Experts transformer model with 36B active parameters per input. Released under Databricks Open Model License, optimized for enterprise workloads including SQL generation and coding tasks.

Snowflake's enterprise-focused open LLM with 480B total parameters using a fine-grained MoE architecture with only 17B active parameters per input. Apache 2.0 licensed, excels at SQL generation, coding, and enterprise intelligence tasks with breakthrough training efficiency.

Google DeepMind's balanced Gemini 3.5 model that pairs Pro-line reasoning quality with Flash-line latency and cost. Natively multimodal across text, image, audio, and video with a 1M-token context window, configurable thinking levels, and streaming function calling, tuned for high-throughput production workloads.

Google's balanced model combining Gemini 3 Pro's reasoning capabilities with the Flash line's latency, efficiency, and cost. Features configurable thinking levels, multimodal function responses, and streaming function calling for complex agentic workflows.

Google's most cost-efficient Gemini model optimized for high-volume, low-latency use cases. Delivers 2.5x faster time to first token versus Gemini 2.5 Flash with full multimodal support. Ideal for agentic tasks, data extraction, translation, and classification.

IBM's largest dense decoder-only 30B parameter language model from the Granite 4.1 family. Trained on approximately 15T tokens with long-context extension up to 512K tokens. Supports tool calling, RAG, code generation, multilingual tasks across 12 languages. Released under Apache 2.0.

IBM's dense decoder-only 8B parameter language model from the Granite 4.1 family. Supports 131K-token context, tool calling, RAG, code generation with fill-in-the-middle, text summarization, classification, and extraction across 12 languages. Released under Apache 2.0.