Models
70+ models from 20+ providers
Browse every text, image, video, and voice model available on Palabres, then start chatting for free.
Text Generation Models
Auto
Provider: OpenRouter
Capabilities: search
Auto classifies each prompt and routes it to a strong model for the task.
GPT-6 Astra
Provider: OpenAI
Capabilities: reasoning
GPT-6 Astra is a frontier reasoning model built for advanced coding, multistep tool use, and complex professional work.
GPT-5.6 Sol
Provider: OpenAI
Capabilities: reasoning
GPT-5.6 Sol is a frontier reasoning model for complex professional work.
GPT-5.6 Terra
Provider: OpenAI
Capabilities: reasoning
GPT-5.6 Terra balances reasoning quality and efficiency.
GPT-5.6 Luna
Provider: OpenAI
Capabilities: reasoning
GPT-5.6 Luna is an efficient reasoning model for high-volume workloads.
GPT-4o mini
Provider: OpenAI
Capabilities: search
GPT-4o mini is a small, fast multimodal model for everyday chat. Supports web search.
gpt-oss-120b
Provider: OpenAI
gpt-oss-120b is a stronger open-weight 120B model for higher quality responses.
gpt-oss-20b
Provider: OpenAI
gpt-oss-20b is a fast open-weight 20B model for everyday chat.
Claude Fable 5.1
Provider: Anthropic
Capabilities: reasoning, search
Claude Fable 5.1 is tuned for long-context creative and analytical work, with more efficient reasoning and improved coding accuracy over Fable 5. Supports reasoning and web search.
Claude Fable 5
Provider: Anthropic
Capabilities: reasoning, search
Claude Fable 5 is tuned for long-context creative and analytical work. Supports reasoning and web search.
Claude Opus 5
Provider: Anthropic
Capabilities: reasoning, search
Claude Opus 5 excels at coding, debugging, and novel problem-solving. Supports reasoning and web search.
Claude Opus 4.8
Provider: Anthropic
Capabilities: reasoning, search
Claude Opus 4.8 is the flagship for maximum quality on complex tasks. Supports web search.
Claude Opus 4.7
Provider: Anthropic
Capabilities: reasoning, search
Claude Opus 4.7 handles hard reasoning, research, and careful drafting. Supports web search.
Claude Sonnet 5
Provider: Anthropic
Capabilities: reasoning, search
Claude Sonnet 5 is strong for everyday coding, writing, and analysis. Supports reasoning and web search.
Claude Haiku 4.5
Provider: Anthropic
Capabilities: search
Claude Haiku 4.5 is fast for quick answers and light coding. Supports web search.
Gemini 3.8 Flash
Provider: Google
Capabilities: reasoning, search
Gemini 3.8 Flash is a fast general-purpose model built for coding, agentic tasks, and multi-step reasoning. Supports reasoning and web search.
Gemini 3.7 Flash
Provider: Google
Capabilities: reasoning, search
Gemini 3.7 Flash is a workhorse model built for coding and agentic tasks, with strong web app generation and document understanding. Supports reasoning and web search.
Gemini 3.6 Flash
Provider: Google
Capabilities: reasoning, search
Gemini 3.6 Flash is the workhorse for coding, knowledge work, and multimodal tasks with strong token efficiency. Supports reasoning and web search.
Gemini 3.5 Flash
Provider: Google
Capabilities: reasoning, search
Gemini 3.5 Flash is a fast, high-quality multimodal model. Supports reasoning and web search.
Gemini 3.5 Flash Lite
Provider: Google
Capabilities: reasoning, search
Gemini 3.5 Flash Lite is the fastest 3.5-class model for high-throughput chat and light agent work. Supports reasoning and web search.
Gemini 3.1 Pro
Provider: Google
Capabilities: reasoning, search
Gemini 3.1 Pro is built for deeper analysis and long context. Supports reasoning and web search.
Gemini 3.1 Flash Lite
Provider: Google
Capabilities: reasoning, search
Gemini 3.1 Flash Lite is lightweight for snappy chat and light reasoning. Supports web search.
Gemma 4 31B
Provider: Google
Capabilities: search
Gemma 4 31B is a capable dense model for general chat. Supports web search.
Gemma 4 31B 🎁
Provider: Google
Capabilities: search
Gemma 4 31B is a denser open model for stronger general chat. Supports web search.
Gemma 4 26B A4B
Provider: Google
Capabilities: search
Gemma 4 26B A4B is an efficient mixture-of-experts model for general chat. Supports web search.
Gemma 4 26B A4B 🎁
Provider: Google
Capabilities: search
Gemma 4 26B A4B is a lightweight mixture-of-experts model. Supports web search.
Gemma 3 27B
Provider: Google
Gemma 3 27B is an open instruction model for solid general chat.
Grok 4.6
Provider: xAI
Capabilities: reasoning, search
Grok 4.6 is the flagship for current knowledge, reasoning, and web search.
Grok 4.5
Provider: xAI
Capabilities: reasoning, search
Grok 4.5 is the flagship for current knowledge, reasoning, and web search.
DeepSeek V4 Flash 0731
Provider: DeepSeek
Capabilities: search, reasoning
DeepSeek V4 Flash is for quick reasoning and coding. Supports web search.
DeepSeek V4 Pro 0813
Provider: DeepSeek
Capabilities: search, reasoning
DeepSeek V4 Pro is the flagship for coding and hard reasoning. Supports web search.
DeepSeek R1 🎁
Provider: DeepSeek
Capabilities: reasoning, search
DeepSeek R1 is a strong open reasoning model. Supports web search.
☁️ DeepSeek R1 (⚗️ Qwen 32B)
Provider: DeepSeek
Capabilities: reasoning
DeepSeek R1 (Qwen 32B distill) is reasoning-focused for multi-step problem solving.
Kimi K3
Provider: Moonshot
Capabilities: reasoning
Kimi K3 is a 2.8T multimodal reasoning model with 1M context.
Kimi K2.6
Provider: Moonshot
Capabilities: reasoning, search
Kimi K2.6 offers long-context reasoning. Supports web search.
Kimi K2.7 Code
Provider: Moonshot
Capabilities: reasoning, search
Kimi K2.7 Code is a software engineering specialist with reasoning and web search.
MiniMax M3
Provider: MiniMax
Capabilities: search, reasoning
MiniMax M3 is a reasoning model with solid multilingual performance. Supports web search.
GLM-5.3
Provider: Z.ai
Capabilities: search, reasoning
GLM-5.3 is a frontier coding and agentic model with strong long-horizon task handling. Supports reasoning and web search.
GLM-5.3 Flash
Provider: Z.ai
Capabilities: search, reasoning
GLM-5.3 Flash is a fast, lightweight coding and agentic model. Supports reasoning and web search.
GLM-5.2
Provider: Z.ai
Capabilities: search, reasoning
GLM-5.2 is a bilingual flagship with reasoning and web search.
Deep Max
Provider: Exa
Capabilities: search
Deep Max runs maximum-effort agentic web search and synthesis for hard research questions.
Answer (Pro)
Provider: Exa
Capabilities: search
Answer Pro returns higher-quality, source-rich web answers.
Answer
Provider: Exa
Capabilities: search
Answer returns web-grounded responses optimized for retrieval quality.
Sonar Reasoning Pro
Provider: Perplexity
Capabilities: search, reasoning
Sonar Reasoning Pro does multi-step research with web search and chain-of-thought.
Sonar Pro
Provider: Perplexity
Capabilities: search
Sonar Pro goes deeper on research-style answers with built-in web search.
Sonar
Provider: Perplexity
Capabilities: search
Sonar gives grounded answers with built-in web search.
Sonar Deep Research
Provider: Perplexity
Capabilities: search, reasoning
Sonar Deep Research runs long-form, multi-source investigations.
Mistral Large 3
Provider: Mistral
Mistral Large 3 is the flagship for complex reasoning and multilingual work.
Mistral Medium 3.5
Provider: Mistral
Capabilities: reasoning
Mistral Medium 3.5 unifies chat, reasoning, and coding in one balanced model.
Mistral Small 4
Provider: Mistral
Capabilities: reasoning
Mistral Small 4 is efficient for everyday chat, coding, and quick reasoning.
Ministral 3 8B
Provider: Mistral
Ministral 3 8B is a compact model for fast everyday tasks.
Ministral 3 3B
Provider: Mistral
Ministral 3 3B is a tiny edge model for simple, ultra-fast prompts.
Codestral
Provider: Mistral
Codestral is a code specialist for generation, completion, and debugging.
Command A
Provider: Cohere
Command A is built for enterprise-style chat, RAG, and tool use.
Inkling
Provider: Thinking Machines
Capabilities: reasoning, search
Inkling is a multimodal MoE model (41B active, 975B total) for reasoning, coding, and multilingual chat, with 1M context. Supports web search.
Mercury 2.5
Provider: Inception Labs
Capabilities: reasoning
Mercury 2.5 is a fast reasoning diffusion model with tunable reasoning and a 260K context window.
Mercury 2
Provider: Inception Labs
Mercury 2 is the next-generation diffusion model for fast generation.
Mercury Coder
Provider: Inception Labs
Mercury Coder is a diffusion model specialized for code generation.
Mercury
Provider: Inception Labs
Mercury is a diffusion language model optimized for speed.
Muse Spark 1.3
Provider: Meta
Capabilities: reasoning, search
Muse Spark 1.3 is a multimodal reasoning model for coding and agentic work, with 1M context and more efficient tool use than Muse Spark 1.2.
Muse Spark 1.2
Provider: Meta
Capabilities: reasoning, search
Muse Spark 1.2 is a multimodal reasoning model for coding and agentic work, with 1M context.
Muse Spark 1.1
Provider: Meta
Capabilities: reasoning, search
Muse Spark 1.1 is an earlier multimodal reasoning checkpoint for coding and long-context work.
Llama 4 Maverick
Provider: Meta
Capabilities: search
Llama 4 Maverick is a higher-capacity multimodal model. Supports web search.
Llama 4 Scout
Provider: Meta
Capabilities: search
Llama 4 Scout is a fast multimodal model. Supports web search.
Llama 3.3 70B
Provider: Meta
Capabilities: search
Llama 3.3 70B has strong instruction following. Supports web search.
Llama 3.1 405B
Provider: Meta
Llama 3.1 405B is the full open-weight model for maximum quality.
☁️ Llama 3.1 70B
Provider: Meta
Llama 3.1 70B is a reliable open model for general chat.
MiMo-V2.5-Pro
Provider: Xiaomi
Capabilities: search, reasoning
MiMo-V2.5-Pro is strong at reasoning and web search for general work.
MiMo-V2.5
Provider: Xiaomi
Capabilities: search, reasoning
MiMo-V2.5 improves reasoning and supports web search.
MiMo-V2-Pro
Provider: Xiaomi
Capabilities: search
MiMo-V2-Pro is for higher-quality general chat. Supports web search.
MiMo-V2-Omni
Provider: Xiaomi
Capabilities: search
MiMo-V2-Omni is a multimodal assistant. Supports web search.
Qwen3.8 Max
Provider: Alibaba Cloud
Capabilities: search, reasoning
Qwen3.8 Max is a multimodal reasoning flagship for complex reasoning, visual understanding, coding, and agentic work. Supports web search.
Qwen3.8 Flash
Provider: Alibaba Cloud
Capabilities: search, reasoning
Qwen3.8 Flash is a fast, cost-efficient model for reasoning and coding. Supports web search.
Qwen3.7 Max
Provider: Alibaba Cloud
Capabilities: search, reasoning
Qwen3.7 Max is the flagship for maximum multilingual quality with reasoning and web search.
Qwen3.7 Plus
Provider: Alibaba Cloud
Capabilities: search, reasoning
Qwen3.7 Plus is strong at reasoning, coding, and multilingual work. Supports web search.
Qwen3 235B A22B
Provider: Alibaba Cloud
Capabilities: search
Qwen3 235B A22B is a high-end mixture-of-experts model. Supports web search.
Qwen3 32B
Provider: Alibaba Cloud
Capabilities: search
Qwen3 32B is a dense model for solid general performance. Supports web search.
Qwen3 30B A3B
Provider: Alibaba Cloud
Capabilities: search
Qwen3 30B A3B is an efficient mid-size mixture-of-experts. Supports web search.
Qwen3 14B
Provider: Alibaba Cloud
Capabilities: search
Qwen3 14B is stronger for chat and coding. Supports web search.
Qwen3 8B
Provider: Alibaba Cloud
Capabilities: search
Qwen3 8B is a compact model for light chat and coding. Supports web search.
Nemotron 3.5 Lightning
Provider: NVIDIA
Capabilities: search, reasoning
Nemotron 3.5 Lightning is NVIDIA's fast, low-cost mixture-of-experts model for high-throughput agentic workloads, with a 262K context window.
Nemotron 3.5 Lightning 🎁
Provider: NVIDIA
Capabilities: search, reasoning
Nemotron 3 Ultra
Provider: NVIDIA
Capabilities: search, reasoning
Nemotron 3 Ultra is a massive mixture-of-experts model for hard tasks with reasoning and web search.
Nemotron 3 Ultra 🎁
Provider: NVIDIA
Capabilities: search, reasoning
Nemotron 3 Ultra is a large mixture-of-experts model with reasoning and web search.
MAI DS R1
Provider: Microsoft
Capabilities: search
MAI DS R1 is a reasoning distill for multi-step problem solving. Supports web search.
Phi-4
Provider: Microsoft
Capabilities: search
Phi-4 is a compact model for chat and light coding. Supports web search.
Nova Pro
Provider: Amazon
Capabilities: search
Nova Pro is for higher-quality general work. Supports web search.
Nova Lite
Provider: Amazon
Capabilities: search
Nova Lite is for fast everyday chat. Supports web search.
Nova Micro
Provider: Amazon
Capabilities: search
Nova Micro is an ultra-small model for simple prompts. Supports web search.
Image Generation Models
GPT Image 2.5 Flare
Provider: OpenAI
GPT Image 2.5 Flare generates high-fidelity images with faster generation, precise prompt adherence, and flexible aspect ratios.
GPT Image 2.5 Sunburst
Provider: OpenAI
GPT Image 2.5 Sunburst is tuned for premium creative workflows, with tighter control over multi-turn edits and detailed typography.
GPT Image 2
Provider: OpenAI
GPT Image 2 produces high-fidelity images up to 2K resolution with precise prompt adherence, detailed typography, and flexible aspect ratios.
DALL·E 3
Provider: OpenAI
Gemini 3 Pro Image
Provider: Google
Gemini 3 Pro Image produces professional-grade imagery with precise composition, fine detail, and high creative control.
Gemini 3.1 Flash Image
Provider: Google
Gemini 3.1 Flash Image generates high-resolution images up to 4K and handles multi-turn visual edits with character and style consistency.
Gemini 3.1 Flash-Lite Image
Provider: Google
Gemini 3.1 Flash-Lite Image provides fast, efficient image generation designed for rapid iterations and high volume.
FLUX1.1 [pro] Ultra
Provider: Black Forest Labs
FLUX1.1 [pro]
Provider: Black Forest Labs
FLUX.1 [dev]
Provider: Black Forest Labs
FLUX.1 [schnell]
Provider: Black Forest Labs
Muse Image
Provider: Meta
Muse Image generates and edits images from text and reference photos, reasoning through multi-part prompts before rendering.
Ideogram 4.0 (Quality)
Provider: Ideogram
Ideogram 4.0 (Balanced)
Provider: Ideogram
Ideogram 4.0 (Turbo)
Provider: Ideogram
Recraft V3
Provider: Recraft
Recraft V3 SVG
Provider: Recraft
stable-diffusion-3.5-large
Provider: Stability AI
stable-diffusion-xl-base-1.0
Provider: Stability AI
stable-diffusion-xl-lightning
Provider: ByteDance
dreamshaper-8-lcm
Provider: Lykon
Video Generation Models
Gemini Omni Flash
Provider: Google
Gemini Omni Flash generates video from text, images, or a reference clip, and extends scenes up to 40s.
Veo 3.1
Provider: Google
Veo 3.1 Fast
Provider: Google
Veo 3.1 Lite
Provider: Google
Wan 2.7
Provider: Alibaba
Wan 2.7 supports text-to-video, image-to-video, and reference-guided clips at 720p or 1080p.
Wan 2.6
Provider: Alibaba
Wan 2.6 generates 1080p video from text or image prompts with optional audio.
HappyHorse 1.1
Provider: Alibaba
HappyHorse 1.1 generates short videos from text, a start frame, or reference images.
Hailuo 2.3
Provider: MiniMax
Hailuo 2.3 generates 1080p video from text prompts or a reference image.
Hailuo-02
Provider: MiniMax
Seedance 2.0
Provider: ByteDance
Seedance 2.0 generates video with strong character consistency and multimodal references.
Seedance 2.0 Fast
Provider: ByteDance
Seedance 2.0 Fast prioritizes quicker turnaround for text and image-to-video clips.
Seedance 1.5 Pro
Provider: ByteDance
Seedance 1.5 Pro generates video and audio together in a unified pass.
Sora 2 Pro
Provider: OpenAI
Sora 2 Pro generates high-fidelity video with strong motion and synchronized audio.
Kling v3.0 Pro
Provider: KwaiVGI
Kling v3.0 Pro delivers higher visual quality for text and image-to-video clips.
Kling Video O1
Provider: KwaiVGI
Kling Video O1 generates cinematic text and image-to-video clips at 720p.
Kling v3.0 Standard
Provider: KwaiVGI
Kling v3.0 Standard supports text and image-to-video with first and last frame control.
FLUX 3 Video
Provider: Black Forest Labs
FLUX 3 Video generates up to 20s clips with synchronized audio from text, stills, or a prior clip.
Grok Imagine Video
Provider: xAI
Grok Imagine Video creates short clips from text or a starting image, with flexible aspect ratios.
ray-2-720p
Provider: Luma Labs
ray-2-540p
Provider: Luma Labs
hunyuan-video
Provider: Tencent
haiper-video-2
Provider: Haiper
Audio Generation Models
Lyria 2
Provider: Google
Lyria 3.5
Provider: Google
Lyria 3.5 composes full-length songs with lyrics and instrumentation from a text prompt.
Voice Synthesis Models
☁️ MeloTTS
Provider: Cloudflare
OpenAI
Provider: OpenAI
ElevenLabs
Provider: ElevenLabs
Ready to try these models?
Start chatting for free, or compare plans for higher limits and media generation.