Models
Landing pages for models you can request through bnrouter’s OpenAI-compatible gateway. Price and the exact model id are always taken from the console.
These pages summarize official vendor announcements and show how to send an OpenAI-compatible request to bnrouter. They do not invent prices, context lengths, or gateway model ids.
Gemini 4 Argon API
On 13 October 2026, Google opened Gemini 4 Argon to developers. Google describes it as a frontier model for complex workflows across real-world software engineering, enterprise knowledge work, and cybersecurity defense, including long-horizon work such as code migrations and research.
See current price in console.
Open model pageMeta
Muse Wonder API
On 12 October 2026, Meta introduced the Muse Wonder series — Muse Wonder and Muse Wonder Full — as models for personal and professional AI agents. Meta says Muse Wonder is available through the Meta Model API and Muse Code, and that Muse Wonder Full is available to Muse Code subscribers.
See current price in console.
Open model pageOpenMOSS
MOSS Image API
OpenMOSS describes MOSS Image as a text-to-image family with native layout control. Besides natural-language prompts, the project page says objects, rendered text, and their positions can be specified in a structured JSON prompt, with emphasis on Chinese and English text rendering.
See current price in console.
Open model pageBria
Fibo 2.0 API
Bria’s official docs introduce Fibo 2 as a model for generating and editing images, trained on licensed data. Bria says generate and edit share the same API, and that Fibo 2 can change only what you ask for while keeping the rest of an image.
See current price in console.
Open model pageBlack Forest Labs
FLUX 3 Video API
On 4 August 2026, Black Forest Labs wrote that an initial version of FLUX 3 Video for generation from text and images became generally available via the BFL API and selected partners. BFL describes clips with native audio generated alongside the video.
See current price in console.
Open model pageBlack Forest Labs
FLUX 3 Image Klein API
On 15 October 2026, Black Forest Labs released FLUX 3 Image Klein as an open-weights member of the FLUX 3 Image family for text-to-image, image editing, and multi-reference generation. BFL says it is available as open weights and through the BFL API.
See current price in console.
Open model pageNano Banana 2.1 API
Google’s Gemini API docs describe Gemini Nano Banana 2.1 as the latest high-efficiency image generation and conversational editing model, an update to Nano Banana 2. Google says it improves visual quality, prompt adherence, multi-turn character consistency, and text rendering.
See current price in console.
Open model pageAnthropic
Claude Haiku 5.5 API
On 7 October 2026, Anthropic introduced Claude Haiku 5.5 as the cheapest, fastest, and most capable small model it had released. Anthropic says it is designed for high-volume, cost-sensitive work such as summaries, classification, database queries, subagents, customer support, and browser use.
See current price in console.
Open model pagexAI
Grok Imagine Video 1.5 Lite API
xAI’s official docs describe grok-imagine-video-1.5-lite as a Grok Imagine video model for text-to-video and image-to-video, with native audio and lip-synced speech. xAI recommends the Lite model for simple videos, and the full 1.5 model when references, voices, pinned frames, or native 1080p are required.
See current price in console.
Open model pageVidu
Vidu Q4 API
Vidu’s official API update notice dated 7 October 2026 lists Vidu Q4 preview as a new model. Vidu describes more authentic performances with reference voices, smoother high-dynamic motion, stronger cinematic quality, and more reference images.
See current price in console.
Open model pageAlibaba Qwen
Qwen-Image-2.1-Turbo API
The official Qwen-Image-2.1 repository news dated 9 October 2026 says Qwen-Image-2.1-Turbo is an accelerated checkpoint for image generation and editing in fewer denoising steps, built on Qwen-Image-2.1. The same note says Pro and Turbo APIs are live on Alibaba Cloud Model Studio, and that open weights are available.
See current price in console.
Open model pageAlibaba
Wan 3.0 API
Alibaba Cloud’s official community post dated 7 August 2026 introduces Wan3.0 as an advanced video generation model in public beta, with longer clips than the previous Wan generation and multimodal reference inputs. Alibaba says testers can apply on Model Studio and Qwen Cloud.
See current price in console.
Open model pageOpenAI
GPT Image 2.5 API
On 8 September 2026, OpenAI introduced ChatGPT Images 2.5 and, for developers, two Image API models: GPT-Image-2.5 Flare for faster everyday generation and GPT-Image-2.5 Sunburst for higher-precision editing. OpenAI’s changelog lists both models for image generation and editing through the Image API.
See current price in console.
Open model pageKrea
Krea 3 API
On 15 October 2026, Krea introduced Krea 3 as an image editing model built for production work. Krea says most edits return at native 2K, that products and characters stay consistent, and that the model also handles text-to-image.
See current price in console.
Open model pageByteDance Seed
Seedance 2.5 API
On 31 July 2026, ByteDance Seed officially launched Seedance 2.5 as a new-generation video creation model. Seed describes one-take creation, upgraded multimodal referencing, and timestamp-level editing, with native audio-video generation.
See current price in console.
Open model page