New models. Clearer choices.
Pricing, benchmarks and availability. Sources included.
40Sourced dossiers
- Routable today
- 35
- Gateway arrivals
- 16
- Latest Nov 12, 2026
Releases
Model releases
Publisher pricing, specs and benchmarks. Newest first.
- Latest · Google ·
Gemini 4 Hydrogen
Routable on MiniRouterRead release Claude Fable 5.2
Anthropic · Routable on MiniRouterMuse Ember
Meta · Routable on MiniRouterJoey-1
Baseten · Not in MiniRouter's catalogGemini 4 Carbon
Google · Routable on MiniRouterParticle-1
Particle AI · Routable on MiniRouterGPT-6.1 Terra
OpenAI · Routable on MiniRouterKimi K3.1 Pro
Moonshot AI · Routable on MiniRouterDeepSeek V4.1 Flash 1017
DeepSeek · Routable on MiniRouterMuse Spark Open
Meta · Routable on MiniRouterMuse Wonder 1.0
Meta · Routable on MiniRouterClaude Haiku 5.5
Anthropic · Routable on MiniRouterMistral Large 4
Mistral AI · Routable on MiniRouterGemini Nano Banana 2.1
Google · Not in MiniRouter's catalogGemini 4 Argon
Google · Routable on MiniRouterGPT-6.1 Sol
OpenAI · Routable on MiniRouterClaude Sonnet 5.5
Anthropic · Routable on MiniRouterGrok 4.7
SpaceXAI · Not in MiniRouter's catalogStep 5 Preview
StepFun · Routable on MiniRouterBonsai 2 27B
PrismML · Routable on MiniRouterDeepSeek V4.1 Flash
DeepSeek · Routable on MiniRouterGPT-6 Astra
OpenAI · Routable on MiniRouterGemini 3.8 Flash
Google · Routable on MiniRouterQwen3.8-Max-0902
Alibaba · Routable on MiniRouterClaude Fable 5.1
Anthropic · Routable on MiniRouterTencent Hy4 preview
Tencent · Not in MiniRouter's catalogGLM-5.3-Flash
Z.ai · Routable on MiniRouterQwen3.8-Flash
Alibaba · Routable on MiniRouterQwen3.8-Flash-Next
Alibaba · Not in MiniRouter's catalogDeepSeek-V4-Flash-Vision-Exp
DeepSeek · Routable on MiniRouterGLM-5.3
Z.ai · Routable on MiniRouterGemini 3.7 Flash
Google · Routable on MiniRouterDeepSeek-V4-Pro
DeepSeek · Routable on MiniRouterGrok 4.6
xAI · Routable on MiniRouterGPT-5.4 mini
OpenAI · Routable on MiniRouterMuse Glimmer 30B
Meta · Routable on MiniRouterMiniMax M3
MiniMax · Routable on MiniRouterKimi K3
Moonshot AI · Routable on MiniRouterQwen3.8-2.4T-A95B
Alibaba · Routable on MiniRouterGPT-5.6 Sol
OpenAI · Routable on MiniRouter
Arrivals
Recent gateway arrivals
Recent releases listed by Vercel AI Gateway or MiniRouter's direct providers in the last 14 days.
- googleVercel AI Gateway list rates (MiniRouter fee excluded): $1.5 input / $7.5 output per 1M · 1,000,000 context
Gemini 4 Hydrogen
Routable on MiniRoutergoogle/gemini-4-hydrogenGemini 4 Hydrogen is Google's fast multimodal model for reasoning, coding, and agentic workflows. It supports understanding text, images, video, and documents, with tool calling and structured outputs for building responsive applications. - paperinstrumentsVercel AI Gateway list rates (MiniRouter fee excluded): $0.15 input / $0.50 output per 1M · 1,048,576 context
Ultramarine 1 Flash
Routable on MiniRouterpaperinstruments/ultramarine-1-flashUltramarine 1 Flash is an open-weight multimodal reasoning model from Paper Instruments, post-trained from GLM-5.3 Flash for knowledge work in enterprise operations, finance, law, and consulting. It supports long-context document analysis and agentic workflows. - thinkingmachinesVercel AI Gateway list rates (MiniRouter fee excluded): $0.30 input / $1 output per 1M · 1,048,576 context
Inkling 2 Small
Routable on MiniRouterthinkingmachines/inkling-2-smallInkling 2 Small is Thinking Machines Lab’s second-generation multimodal Mixture-of-Experts model, with 594 billion total parameters and 17 billion active per token. It combines text and image understanding with controllable reasoning for coding, tool use, and professional knowledge work. - googleVercel AI Gateway list rates (MiniRouter fee excluded): $2 input / $10 output per 1M · 1,000,000 context
Gemini 4 Carbon
Routable on MiniRoutergoogle/gemini-4-carbonGemini 4 Carbon is Google’s reasoning model for complex software engineering, sustained agentic workflows, and cybersecurity defense. It combines a 1M-token context window with multimodal understanding, tool calling, and structured outputs for working across large codebases and documents. Carbon emphasizes reliable execution of multi-step plans, clearer handling of uncertainty, and identifying, validating, and remediating security vulnerabilities. - anthropicVercel AI Gateway list rates (MiniRouter fee excluded): $8 input / $40 output per 1M · 1,000,000 context
Claude Fable 5.2
Routable on MiniRouteranthropic/claude-fable-5.2Claude Fable 5.2 supports agentic coding, knowledge work, and research with always-on adaptive thinking and adjustable reasoning effort from low through max. - anthropicVercel AI Gateway list rates (MiniRouter fee excluded): $4 input / $20 output per 1M · 1,000,000 context
Claude Fable 5.2 (Batch)
Not yet in MiniRouter’s cataloganthropic/claude-fable-5.2-batchClaude Fable 5.2 supports agentic coding, knowledge work, and research with always-on adaptive thinking and adjustable reasoning effort from low through max. - anthropicVercel AI Gateway list rates (MiniRouter fee excluded): $16 input / $80 output per 1M · 1,000,000 context
Claude Fable 5.2 (Fast)
Routable on MiniRouteranthropic/claude-fable-5.2-fastClaude Fable 5.2 supports agentic coding, knowledge work, and research with always-on adaptive thinking and adjustable reasoning effort from low through max. - metaVercel AI Gateway list rates (MiniRouter fee excluded): $0.10 input / $0.50 output per 1M · 1,048,576 context
Muse Ember
Routable on MiniRoutermeta/muse-emberMuse Ember is Meta’s multimodal language model for conversational, reasoning, and agentic applications. It supports text and image understanding, tool calling, structured outputs, and document input, with a 1,048,576-token context window for working with large prompts and extended conversations. Implicit prompt caching supports reuse of shared input across requests. - deepseekVercel AI Gateway list rates (MiniRouter fee excluded): $2.4 input / $9.6 output per 1M · 1,048,576 context
DeepSeek V4.1 Flash 1017 Ultrafast
Routable on MiniRouterdeepseek/deepseek-v4.1-flash-1017-ultrafastDeepSeek V4.1 Flash 1017 Ultrafast serves the October 17, 2026 update of DeepSeek V4.1 Flash through Fireworks' accelerated serverless endpoint. It supports text and image input, configurable reasoning, tool calling, structured outputs, and automatic prefix caching. Available in public preview without a waitroom or session time limit. - humansandVercel AI Gateway list rates (MiniRouter fee excluded): $0.00 input / $0.00 output per 1M · 1,000,000 context
Ampersand v0.1
Not yet in MiniRouter’s cataloghumansand/ampersand-v0.1Ampersand v0.1 is a collaborator model from Humans& for shared goals, group conversations, and long-running collaboration. Its Responses API supports text, reasoning, client-side function tools, and implicit prompt caching. - googleVercel AI Gateway list rates (MiniRouter fee excluded): $1.5 input / $9 output per 1M · 131,072 context
Gemini Omni 1.2 Flash
Routable on MiniRoutergoogle/gemini-omni-1.2-flashGemini Omni 1.2 Flash is Google’s multimodal model for video generation and visual content creation. It combines text, image, and video inputs with text and video outputs, helping developers build creative applications that work across multiple media formats. - openaiVercel AI Gateway list rates (MiniRouter fee excluded): $5 text input / $30 image output per 1M tokens
GPT Image 2.6 Flare
Routable on MiniRouteropenai/gpt-image-2.6-flareGPT Image 2.6 Flare is an OpenAI image generation and editing model for interactive workflows using text and image inputs. - openaiVercel AI Gateway list rates (MiniRouter fee excluded): $5 text input / $30 image output per 1M tokens
GPT Image 2.6 Sunburst
Routable on MiniRouteropenai/gpt-image-2.6-sunburstGPT Image 2.6 Sunburst is an OpenAI image generation model that creates and edits images from text and image inputs. - tencentVercel AI Gateway list rates (MiniRouter fee excluded): $0.417 input / $1.251 output per 1M · 1,024,000 context
Tencent Hy4
Routable on MiniRoutertencent/hy4Tencent Hy4 is a text model for coding, reasoning, and agentic workflows. It supports tool calling, structured outputs, and prompt caching, with a 1M-token context window for tasks such as software engineering, document analysis, and office automation. - meituanVercel AI Gateway list rates (MiniRouter fee excluded): $0.30 input / $1.2 output per 1M · 1,048,576 context
LongCat 2.5
Routable on MiniRoutermeituan/longcat-2.5LongCat 2.5 is Meituan’s native multimodal model for coding and long-running agent workflows. It combines visual understanding with multi-step reasoning and tool use to work across complex codebases and full-project development. Its 1M-token context window supports tasks involving large documents, codebases, and text and image inputs. - zaiVercel AI Gateway list rates (MiniRouter fee excluded): $0.37 input / $1.25 output per 1M · 1,000,000 context
GLM 5.3 FlashX Legal
Routable on MiniRouterzai/glm-5.3-flashx-legalGLM 5.3 FlashX Legal is Z.ai’s model optimized for legal workflows, including contract review, evidence analysis, and compliance research. It helps teams analyze legal documents, cross-check records, and prepare structured findings for further review.
Source: Vercel AI Gateway's live model catalog ↗ and MiniRouter's public catalog ↗.