Custom Providers

xAI's flagship reasoning model with vision and tool use. 256k context, strong at complex reasoning and STEM tasks.

xAI's May 2026 flagship. 1M context, vision, always-on reasoning, real-time X/web retrieval via DeepSearch.

Ideogram's flagship text-to-image model with industry-leading text rendering and prompt adherence.

Moonshot AI's 1T-parameter MoE model. Industry-leading agentic coding and tool-use benchmarks.

MiniMax's 456B hybrid lightning-attention model with native 4M-token context. Industry-leading long-context.

Perplexity's premium web-grounded search model with multi-step reasoning over live sources.

Voyage's general-purpose embedding model. 1024 dims, 32k context, strong retrieval performance.

AI21's flagship hybrid Mamba-Transformer model with a 256k context window for long-document tasks.

Cost-efficient hybrid Mamba-Transformer model with 256k context. Tuned for high-throughput RAG.

Cartesia's ultra-low-latency TTS (~90ms TTFB). State-space model with voice cloning support.

Open-weights multilingual research model from Cohere covering 23 languages. 35B parameters.

Cohere's fast lightweight chat model (deprecated Sep 2025). Kept as comparison tombstone.

Cohere's mid-tier RAG/tool model. Cost-efficient sibling of Command R+ with 128k context.

Cohere's flagship RAG- and tool-optimized chat model. 128k context, refreshed August 2024.

Cohere's multilingual embedding model. Supports 100+ languages with separate search and classification modes.

Deepgram's flagship STT. First to offer realtime multilingual transcription with self-serve customization.

Microsoft Edge neural voices accessed via the open-source edge-tts wrapper. 400+ voices across 100+ locales, suitable for batch generation.

NVIDIA GET3D generative model for textured 3D shapes. Trained on category-specific datasets producing meshes with high-quality textures.

xAI's vision-capable Grok 2 snapshot. Image-in, text-out with strong multilingual instruction following.

xAI's flagship model. Strong at reasoning, coding, and real-time knowledge with web search capabilities.

xAI's cost-efficient high-throughput model. 2M context, optional reasoning, optimized for agentic loops and real-time apps.

MiniMax's Hailuo video-01. 6s 1280x720 clips with strong cinematic motion and physical realism.

Ideogram's fast text-to-image variant. Strong typography and logo rendering at low latency.

Jina's frontier multilingual embedding model. 570M params, 8192 ctx, 89 languages, Matryoshka dims 128-1024.

Kuaishou's Kling 1.6 Pro. Premium cinematic motion and physics realism, ~$0.07/sec.

HuggingFace's 450M VLA pretrained on 487 community LeRobot datasets. Runs on consumer GPUs.

Luma's Dream Machine 1.6. 720p text/image-to-video with strong motion and camera control.

Mixedbread's open-source 335M embedding model. Top MTEB benchmark for English retrieval at release.

NVIDIA's world foundation model for physical AI. Diffusion-based video prediction for robotics simulation.

Berkeley/Stanford 93M transformer diffusion policy. Pretrained on 800k Open-X-Embodiment episodes.

Compact 27M variant of Octo. Faster inference on consumer GPUs, designed for low-latency control.

Stanford/Berkeley open VLA trained on 970k Open-X-Embodiment episodes. Supports LoRA fine-tuning.

Perplexity's fastest and cheapest web-grounded chat model. Live-source citations included.

Perplexity's reasoning model with chain-of-thought and integrated web search.

Autoregressive π-0 variant using FAST action tokenizer. Faster inference at competitive task success.

Physical Intelligence's flagship VLA flow-matching policy. Generalist robot control, pretrained on 10k+ hrs robot data.

Upgraded π-0 with open-world generalization via knowledge insulation. Weights and fine-tuning open-sourced.

Pika Labs' 2.0 release. Cinematic text/image-to-video with scene composition controls.

Playground's text-to-image model focused on graphic design aesthetics and embedded typography.

PlayHT's 2.0 generative voice model. Multi-lingual expressive speech synthesis with sub-second latency and high-fidelity voice cloning.

Alibaba's flagship pretrained MoE model. Top-tier reasoning and code performance via DashScope API.

Tsinghua's 1B diffusion-transformer bimanual manipulation policy. Predicts next 64 actions per inference.

Recraft's high-prompt-adherence raster image model. Strong layout control and brand-style consistency.

Recraft's vector/SVG generation model. Editable illustrations and icons from text.

Reka's frontier multimodal model supporting text, image, video and audio inputs.

Reka's small on-device-friendly multimodal model. ~7B parameters, 16k context.

Reka's 21B dense multimodal model balancing speed and quality. Up to 128k context.

Runway's faster, cheaper Gen-3 variant. Image-to-video at 5 credits/sec (~$0.05/sec).

Snowflake's open MoE model: 480B total / 17B active params with dense+MoE hybrid architecture.

Stability AI's Stable Audio 2.0. Text-to-music up to 3 minutes of full-length, structured tracks at 44.1 kHz.

Stability AI's 8B-parameter flagship SD3.5 model. Strong prompt adherence and aesthetic quality.

Distilled 4-step variant of SD3.5 Large. 8B params, ~4x faster inference at competitive quality.

Stability AI's 2.5B-parameter SD3.5 with strong quality/speed trade-off. Consumer-GPU friendly.

Voyage's code-specialized embedding model. Up to 32k context, Matryoshka 256-2048 dims, int8/binary support.

01.AI's larger general-purpose chat model with 32k context window and strong bilingual performance.