Choose a category in More filters to see relevant price sorts.
DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model…
Apache-2.0 text model with 501B total and 23B active parameters; ships BF16, FP8 and NVFP4 weights.
OpenRouter lists a 1,048,576-token context and up to 943,718 output tokens for this open-weight model aimed at agentic coding.
Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...
Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...
FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers...
Long decode can use the unified 1M-token budget for output; reads video, audio and PDFs, with implicit-only caching.
Requires Responses API for tools; offers Ultrafast inference with US or EU data residency.
Tuned for quick iteration on scoped fixes and documents; Anthropic favors Opus 5.5 for open-ended work needing sustained judgment.
Directs speech with inline emotion tags and IPA pronunciation; supports streaming and adjustable voice stability.
Supports inline performance tags and IPA pronunciation; stability and voice-similarity controls tune delivery.
Separate spoken text from delivery instructions, or script a two-voice dialogue with per-turn style overrides.
Separates spoken text from delivery instructions; supports exactly two named speakers with ordered dialogue turns.
Supply preferred RGB palette colors and a background color directly, alongside the text prompt and custom image dimensions.
Universal-3.5 Pro is AssemblyAI's speech-to-text model served through its Sync API, returning a complete transcript with word-level timestamps in a single synchronous response for audio up to 20 minutes. It...
Always-on adaptive thinking defaults to medium effort; built for sustained work across large codebases and professional documents.
Can turn reasoning off for high-volume requests; Chat Completions tool calls require reasoning_effort=none.
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...
600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment.
Causal encoder-decoder activates 8B parameters for input and 16B for output, reducing the compute needed for long inputs.
Accepts mid-turn steering and async tool calls, so agents can take new instructions while other tools are still running.
Beta controls change effort per message without invalidating the prompt cache and report progress between tool calls.
Realtime TTS 2.0 is a low-latency text-to-speech model with natural language steering, allowing you to control tone and emotion directly in the prompt (e.g., “[be happy and upbeat] Hello!”). It supports…
Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis,…