Modeller

Gemini 3.6 Flash

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.

Claude Opus 5

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.

Gemini 3.5 Flash-Lite

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.

Inkling

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.

Kimi K3

Moonshot AI's flagship Kimi model for frontier intelligence, agentic coding, knowledge work, and deep reasoning. Kimi K3 supports a 1-million-token context window for long-running software engineering and research workflows.

Gemini 3.5 Pro

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.

GPT-5.6 Luna

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.

GPT-5.6 Sol

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.

Muse Spark 1.1

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.

GPT-5.6 Terra

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.

Grok 4.5

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.

Claude Sonnet 5

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.

Sakana Fugu

Sakana AI's multi-agent orchestration model from Tokyo, delivered as a single OpenAI-compatible API. Fugu is itself a language model trained to call a pool of specialist LLMs (and recursive instances of itself), handling model selection, delegation, verification, and synthesis behind one endpoint. Built on Sakana AI's TRINITY and Conductor research, its routing intelligence is learned in model weights rather than hand-configured.

Sakana Fugu Ultra

The higher-quality tier of Sakana AI's Fugu multi-agent orchestration system, tuned for the hardest coding, reasoning, science, and agentic tasks. Coordinates a swappable pool of frontier LLMs through one OpenAI-compatible endpoint, delegating sub-tasks, verifying intermediate work, and synthesizing a single answer. Sakana reports strong vendor benchmarks including 93.2 on LiveCodeBench, 73.7 on SWE-Bench Pro, and 82.1 on TerminalBench.

Sarvam-M

Sarvam AI's 24B-parameter instruction-tuned model derived from Mistral-Small-3.1-24B, post-trained on English plus eleven major Indic languages (bn, hi, kn, gu, mr, ml, or, pa, ta, te). Delivers large relative gains on Indian-language, math, and programming benchmarks over its base model, with a hybrid reasoning mode for complex tasks.

Sarvam-30B

Sarvam AI's 30B-parameter Mixture-of-Experts reasoning model trained from scratch with only 2.4B active parameters per token. Optimized for real-time deployment and Indian languages, delivering strong reasoning, coding, and conversational performance while remaining efficient to serve. Open-weights.

GLM-5.2

Z.ai's (formerly Zhipu AI) flagship open-weight coding model with a 1M-token context window. Mixture-of-Experts architecture with 753B total parameters and ~40B active per request, featuring two cost-balancing reasoning modes. Tops several coding benchmarks while remaining a fraction of the cost of comparable proprietary frontier models. MIT-licensed weights.

Command A+

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.

Sarvam-105B

Sarvam AI's sovereign 105B-parameter Mixture-of-Experts model activating ~9B parameters per token, with a 128K-token context window. Trained on 12 trillion tokens across 22 Indian languages using 128 sparse experts with Multi-head Latent Attention and a custom low-fertility Indic tokenizer. Wins the majority of pairwise comparisons on Indian-language and STEM benchmarks.

Kimi K2.7 Code

Moonshot AI's latest open-source, coding-focused model in the Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. A 1-trillion-parameter model that cuts reasoning token usage by roughly 30% versus K2.6 while improving coding and agent performance — +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite for multi-language support. Released under a Modified MIT License and available via Kimi APIs and Hugging Face.

DiffusionGemma

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.

Claude Fable 5

Anthropic'in herkese açık ilk Mythos sınıfı modeli; şirketin daha önce geniş erişime sunduğu tüm modellerden daha yeteneklidir. Test edilen benchmark'ların neredeyse tamamında ileri düzey sonuçlar gösterir ve özellikle yazılım geliştirme, bilgi çalışması, görüntü işleme ve bilimsel araştırmada güçlüdür. Avantajı daha uzun ve karmaşık görevlerde artar. Yerleşik güvenlik önlemleri siber güvenlik, biyoloji, kimya ve distilasyonla ilgili hassas istekleri Claude Opus 4.8'e yönlendirir.

Gemma 4 12B

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.

Nemotron 3 Ultra

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.