Tool-calling models

DeepSeek: DeepSeek V4.1 Flash HereticFeaturedUncensoredReasoningVision512K context

Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separat…

deepseek-v4.1-flash-heretic2026-10-31$0.257/M input$1.03/M output

Z.ai: Apex Flash 1 AbliteratedFeaturedUncensoredReasoningVision1M context

Apex Flash 1 Abliterated is an experimental derivative of Cantina Security and Yeta's Apex Flash 1 with modified refusal behavior.

glm-5.3-flash-abliterated2026-10-05$0.195/M input$0.650/M output

DeepSeek: DeepSeek V4.1 Flash UncensoredFeaturedUncensoredReasoningVision1M context

A lower-refusal finetune of DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. Supports a context window of up to 1M tokens.

deepseek-v4.1-flash-uncensored2026-10-01$0.429/M input$1.72/M output

Xiaomi: MiMo V2.6 Flash UncensoredFeaturedUncensoredReasoningVision1M context

A lower-refusal MiMo V2.6 Flash finetune with a 1M-token context window, separate reasoning output, and tool calling. Supports image input and adjustable thinking effort.

mimo-v2.6-flash-uncensored2026-09-25$0.650/M input$1.95/M output

Z.ai: GLM 5.3 Flash UncensoredFeaturedUncensoredReasoningVision1M context

glm-5.3-flash-uncensored2026-07-29$0.260/M input$1.04/M output

Google: Gemini 4 HydrogenReasoningVision1.05M context

Google's Gemini 4 Hydrogen is a reasoning model for coding, problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, with tool calling and structured outp…

gemini-4-hydrogen2026-11-13$1.95/M input$9.75/M output

Meta: Muse EmberReasoningVision1.05M context

Meta's Muse Ember is the smallest and most efficient Muse model, built for the work agents repeat all day: tool calls, coding-agent subtasks, routing, and extraction. It accepts text, images, audio, video, and PDF docu…

muse-ember2026-11-11$0.130/M input$0.650/M output

Google: Gemini 4 CarbonReasoningVision1.05M context

Google's Gemini 4 Carbon is a reasoning model for complex coding, scientific and mathematical problem solving, and multi-step tasks that use tools. It accepts text, images, audio, video, and PDFs and produces text, wit…

gemini-4-carbon2026-11-11$2.60/M input$13.00/M output

Baidu: ERNIE Light DT 1.0 (Intl)Reasoning1.02M context

ERNIE Light DT 1.0 (Intl) is text model with Sparse Attention for working with long conversations and documents. It supports tool calling, structured output, a 1,024,000-token context window, and up to 131,072 output t…

ernie-light-dt-1.0-intl2026-11-11$1.69/M input$5.85/M output

Community: Nex N2.6ReasoningVision262K context

Nex N2.6 is Nex AGI's agentic model for coding and long-running tasks that use tools. It accepts text and images, produces text, and supports tool calling and structured output within a 262,144-token context window. Re…

nex-n2.62026-11-10$0.195/M input$0.650/M output

Anthropic: Claude Fable 5.2ReasoningVision1M context

Anthropic's Claude Fable 5.2 supports demanding reasoning, coding, and long-running agentic work, with text, image, and PDF inputs, tool calling, and structured outputs. It has a 1M-token context window and up to 128K …

claude-fable-5.22026-11-10$13.00/M input$65.00/M output

Orca: OrcaCyber DeepSeek V4.1 FlashReasoningVision1.05M context

An OrcaCyber model built on DeepSeek V4.1 Flash for authorized security research, coding, and tool use. Accepts text and images, with reasoning off by default. Supports a 1M-token context window, up to 393K output toke…

orcacyber-flash-1.02026-11-09$1.04/M input$2.08/M output

Orca: OrcaCyber DeepSeek V4.1 Flash ThinkingReasoningVision1.05M context

An OrcaCyber model built on DeepSeek V4.1 Flash for authorized security research, coding, and tool use. Accepts text and images, with reasoning on by default. Supports a 1M-token context window, up to 393K output token…

orcacyber-flash-1.0:thinking2026-11-09$1.04/M input$2.08/M output

Orca: OrcaCyber GLM 5.3 FlashReasoningVision1.05M context

An OrcaCyber model built on GLM 5.3 Flash for authorized security research, coding, and tool use. Accepts text and images. Reasoning is always enabled, with selectable effort. Supports a 1M-token context window, up to …

orcacyber-glm-5.3-flash2026-11-09$1.04/M input$2.08/M output

Orca: OrcaCyber MiMo V2.6 FlashReasoning1.05M context

An OrcaCyber model built on MiMo V2.6 Flash for authorized security research, coding, and tool use. Accepts text input, with reasoning enabled by default and an option to turn it off. Supports a 1M-token context window…

orcacyber-mimo-flash2026-11-09$1.04/M input$2.08/M output

Moonshot: Kimi K3.1 Pro PrivateReasoningVision262K context

Kimi K3.1 Pro is Moonshot AI's multimodal model post-trained from Kimi K3 for long-horizon coding, agentic workflows, and knowledge work. It always reasons, and supports image input, tool calling, and structured output…

kimi-k3.1-pro-private2026-11-09$5.20/M input$26.00/M output

Liquid: LFM3 1.7BReasoning262K context

Liquid AI's compact 1.7B-parameter text model for tool use, structured output, data extraction, and specialized agents. It reasons before answering and supports a 262,144-token context window with up to 8,192 output to…

lfm-3-1.7b2026-11-07$0.130/M input$0.325/M output

inclusionAI: Ling 3.0 Tiny262K context

Ling 3.0 Tiny is a compact 7.9B-parameter Mixture-of-Experts model with 1.3B parameters active per token. It is designed for responsive agents, reliable instruction following, natural multi-turn conversations, long-con…

ling-3.0-tiny2026-11-07$0.0195/M input$0.0585/M output

inclusionAI: Ling 3.0 Tiny ThinkingReasoning262K context

Ling 3.0 Tiny Thinking enables visible reasoning on inclusionAI's compact 7.9B-parameter Mixture-of-Experts model for harder agent tasks, coding, planning, function calling, and long-context workflows.

ling-3.0-tiny:thinking2026-11-07$0.0195/M input$0.0585/M output

Community: Ripple 65B PreviewReasoning16K context

Ripple 65B Preview is Ricursive Intelligence's Apache 2.0-licensed, 65-billion-parameter reasoning model for coding and agentic tasks. It accepts and returns text, supports automatic tool calling and JSON output, and h…

ripple-65b-preview2026-11-05$0.260/M input$0.780/M output

Orca: OrcaCyber K3.1 ProReasoningVision1.05M context

An OrcaRouter model for authorized security research, coding, and tool use. Accepts text and images, with reasoning enabled by default and an option to turn it off. Supports a 1M-token context window, up to 943K output…

orcacyber-k3.1-pro2026-11-05$5.20/M input$26.00/M output

Tencent: Tencent Hy4ReasoningVision1.05M context

Tencent Hy4 accepts text and images and returns text, with a 1,048,576-token context window and up to 65,536 output tokens. It supports coding, long-document analysis, automatic tool calling and structured output. Reas…

hy42026-11-04$0.542/M input$1.63/M output

Z.ai: GLM 5.3 FlashX LegalReasoningVision1.05M context

GLM 5.3 FlashX Legal is Z.AI's model trained for legal document analysis, contract review, legal reasoning and initial drafts. It accepts text and images and returns text, with always-on reasoning, tool calling, JSON o…

glm-5.3-flashx-legal2026-11-02$0.481/M input$1.63/M output

Orca: OrcaCyber MiniMax M3.1 FlashReasoning262K context

An OrcaCyber model for authorized security research, coding, and tool use. Reasoning is always enabled, with selectable effort. Supports a 262K-token context window, up to 131K output tokens, tool calling, and structur…

orcacyber-minimax-m3.1-flash2026-11-02$1.04/M input$2.08/M output

Orca: OrcaCyber Qwen3.8 Flash NextReasoningVision262K context

An OrcaCyber model for authorized security research, coding, and tool use. Accepts text and images, with reasoning enabled by default and an option to turn it off. Supports a 262K-token context window, up to 131K outpu…

orcacyber-qwen3.8-flash-next2026-11-02$1.04/M input$2.08/M output

DeepSeek: DeepSeek V4.1 Flash Heretic ThinkingUncensoredReasoningVision512K context

Heretic checkpoint of DeepSeek V4.1 Flash 1017, served by Sable at original mixed precision (FP8 dense/Engram and MXFP4 experts). Supports text and image input, tools, structured output, and optional reasoning. Separat…

deepseek-v4.1-flash-1017-heretic:thinking2026-10-31$0.257/M input$1.03/M output

Orca: OrcaCyber Zero 1.5Reasoning999K context

OrcaRouter's frontier cybersecurity model, post-trained for authorized security research: vulnerability research and reproduction, exploit development, penetration testing, and security auditing. Supports a 1M-token co…

orcacyber-zero-1.52026-10-30$3.90/M input$9.75/M output

Community: Particle-1ReasoningVision1.05M context

Particle-1 is Particle AI’s coding and data-engineering model, post-trained on DeepSeek V4.1 Flash. It accepts text and images, supports tool calling, and offers a shared 1,048,576-token context window with up to 131,0…

particle-12026-10-29$0.325/M input$1.30/M output

DeepSeek: DeepSeek V4.1 Flash 0910 UncensoredUncensoredReasoningVision524K context

Uncensored DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. The date label is retained for compatibility. Served only by its own checkpoint; it may be unavailable while that host is …

deepseek-v4.1-flash-0910-uncensored2026-10-27$0.429/M input$1.72/M output

DeepSeek: DeepSeek V4.1 Flash 0910 Uncensored ThinkingUncensoredReasoningVision524K context

Uncensored DeepSeek V4.1 Flash with text and image input, optional reasoning, and tool calling. The date label is retained for compatibility. Served only by its own checkpoint; it may be unavailable while that host is …

deepseek-v4.1-flash-0910-uncensored:thinking2026-10-27$0.429/M input$1.72/M output

Models