WorldRouter

Models

52 models

Claude Fable 5

Anthropic's high-capability Fable 5 model for advanced reasoning, repository-scale coding, long-context analysis, and agentic workflows.

Anthropic|1M context|700 Credits input/3,500 Credits output/70 Credits cache read/875 Credits cache write/ 1M tokens

Claude Fable 5.1

Anthropic's latest Fable model for demanding reasoning, long-context analysis, and agentic workflows.

Anthropic|1M context|700 Credits input/3,500 Credits output/17.5 Credits cache read/875 Credits cache write/ 1M tokens

Claude Haiku 4.5

Fast and cost-efficient Claude model for latency-sensitive assistants, summaries, and high-volume production traffic.

Anthropic|1M context|70 Credits input/350 Credits output/7 Credits cache read/87.5 Credits cache write/ 1M tokens

Claude Haiku 5.5

Anthropic's fastest Claude model for latency-sensitive and high-volume tasks.

Anthropic|1M context|Tiered pricing:0–100K:7 Credits input/35 Credits output/0.7 Credits cache read/8.75 Credits cache write·>100K–1M:35 Credits input/175 Credits output/3.5 Credits cache read/43.75 Credits cache write/ 1M tokens

Claude Opus 4.6

Most capable model for complex reasoning, analysis, and extended coding tasks. Excels at nuanced understanding and creative generation with 1M context.

Anthropic|1M context|350 Credits input/1,750 Credits output/35 Credits cache read/437.5 Credits cache write/ 1M tokens

Claude Opus 4.7

Anthropic's newest top-tier Claude for the most demanding reasoning, long-context analysis, and extended coding workloads.

Anthropic|1M context|350 Credits input/1,750 Credits output/35 Credits cache read/437.5 Credits cache write/ 1M tokens

Claude Opus 4.8

Anthropic's high-capability Opus model for demanding reasoning, long-context analysis, and extended coding workloads.

Anthropic|1M context|350 Credits input/1,750 Credits output/35 Credits cache read/437.5 Credits cache write/ 1M tokens

Claude Opus 5

Anthropic's top-tier Claude for demanding reasoning, long-context analysis, and extended coding workloads.

Anthropic|1M context|350 Credits input/1,750 Credits output/35 Credits cache read/437.5 Credits cache write/ 1M tokens

Claude Opus 5.5

Anthropic's latest Opus model for long-running agentic coding and knowledge work.

Anthropic|1M context|280 Credits input/1,400 Credits output/14 Credits cache read/350 Credits cache write/ 1M tokens

Claude Sonnet 4.6

Best balance of intelligence and speed. Ideal for enterprise workloads, RAG, and agentic coding with strong instruction following.

Anthropic|1M context|210 Credits input/1,050 Credits output/21 Credits cache read/262.5 Credits cache write/ 1M tokens

Claude Sonnet 5

Anthropic's latest Sonnet model for high-throughput coding, agentic workflows, and long-context reasoning.

Anthropic|1M context|140 Credits input/700 Credits output/14 Credits cache read/175 Credits cache write/ 1M tokens

Claude Sonnet 5.5

Anthropic's Sonnet 5.5 model for high-throughput coding, agentic workflows, and long-context reasoning.

Anthropic|1M context|140 Credits input/700 Credits output/14 Credits cache read/175 Credits cache write/ 1M tokens

DeepSeek V3.2

DeepSeek V3.2 served through Qianfan International for high-ROI chat, coding, math, and reasoning workloads.

DeepSeek|144K context|35 Credits input/105 Credits output/30 Credits cache read/ 1M tokens

DeepSeek V4 Flash

Lower-latency DeepSeek V4 variant optimized for cost-sensitive chat and structured generation at scale.

DeepSeek|1M context|WorldRouter time-window pricing (UTC):Off-peak:15.4 Credits input/46.2 Credits output/0.49 Credits cache read/15.4 Credits cache write·Peak:30.8 Credits input/92.4 Credits output/0.98 Credits cache read/30.8 Credits cache write/ 1M tokens

DeepSeek V4 Pro

DeepSeek's higher-end V4 model for coding, math, and complex analysis with stronger quality than prior open-weight generations.

DeepSeek|1M context|WorldRouter time-window pricing (UTC):Off-peak:46.2 Credits input/138.6 Credits output/1.54 Credits cache read/46.2 Credits cache write·Peak:92.4 Credits input/277.2 Credits output/3.08 Credits cache read/92.4 Credits cache write/ 1M tokens

DeepSeek V4.1 Flash

Fast DeepSeek V4.1 model served through BytePlus Ark with native Anthropic Messages compatibility.

DeepSeek|1M context|WorldRouter time-window pricing (UTC):Off-peak:10.5 Credits input/42 Credits output/0.21 Credits cache read/10.5 Credits cache write·Peak:21 Credits input/84 Credits output/0.42 Credits cache read/21 Credits cache write/ 1M tokens

ERNIE 5.0

Baidu's flagship Qianfan International model for text chat plus verified vision input with image URLs, Base64 images, multi-turn image conversations, and detail controls.

Baidu|128K context|98 Credits input/392 Credits output/ 1M tokens

GLM-4.5 Air

Efficient GLM model for low-cost bilingual chat, summarization, and extraction.

Zhipu|131K context|13 Credits input/85 Credits output/2.5 Credits cache read/13 Credits cache write/ 1M tokens

GLM-4.6

Earlier GLM generation with dependable bilingual chat and instruction following.

Zhipu|205K context|39 Credits input/190 Credits output/39 Credits cache read/39 Credits cache write/ 1M tokens

GLM-4.7

Zhipu GLM model for balanced reasoning, coding support, and Chinese-English tasks.

Zhipu|203K context|40 Credits input/175 Credits output/8 Credits cache read/40 Credits cache write/ 1M tokens

GLM-4.7 Flash

Fast GLM flash model for inexpensive chat, classification, and structured output.

Zhipu|203K context|6 Credits input/40 Credits output/1 Credits cache read/6 Credits cache write/ 1M tokens

GLM-5

Zhipu AI's latest foundation model with strong bilingual capabilities and advanced reasoning for enterprise applications.

Zhipu|200K context|55 Credits input/176 Credits output/11 Credits cache read/55 Credits cache write/ 1M tokens

GLM-5.1

Newer Zhipu flagship with stronger bilingual reasoning and enterprise-oriented instruction following.

Zhipu|200K context|77 Credits input/242 Credits output/14.3 Credits cache read/77 Credits cache write/ 1M tokens

GLM-5.2

Z.ai flagship model for long-horizon engineering tasks with a 1M-token context window.

Zhipu|1M context|98 Credits input/308 Credits output/18.2 Credits cache read/98 Credits cache write/ 1M tokens

GLM-5.3

Z.ai GLM route for long-context bilingual reasoning, coding, and agent workloads.

Zhipu|1M context|98 Credits input/308 Credits output/18.2 Credits cache read/98 Credits cache write/ 1M tokens

GLM-5.3-Flash

Z.ai multimodal Flash model for long-context reasoning, coding, and visual tasks.

Zhipu|1M context|10.5 Credits input/35 Credits output/2.1 Credits cache read/10.5 Credits cache write/ 1M tokens

GPT Image 2

OpenAI image-generation route for synchronous text-to-image requests over the standard Images API.

OpenAI|33K context|600 Credits input/2,250 Credits output/ 1M tokens

GPT-5.4

Latest frontier model from OpenAI with enhanced reasoning, tool use, and multimodal understanding across text, images, and audio.

OpenAI|1M context|Tiered pricing:0–272K:175 Credits input/1,050 Credits output/17.5 Credits cache read/175 Credits cache write·272K–1M:350 Credits input/1,575 Credits output/35 Credits cache read/350 Credits cache write/ 1M tokens

GPT-5.4 Mini

Small and fast model optimized for lightweight tasks. Excellent cost-efficiency for simple queries and high-volume applications.

OpenAI|400K context|52.5 Credits input/315 Credits output/5.25 Credits cache read/52.5 Credits cache write/ 1M tokens

GPT-5.5

OpenAI's newer frontier model with stronger reasoning depth, tool use, and reliability for demanding agentic tasks.

OpenAI|1M context|Tiered pricing:0–272K:350 Credits input/2,100 Credits output/35 Credits cache read/350 Credits cache write·272K–1M:700 Credits input/3,150 Credits output/70 Credits cache read/700 Credits cache write/ 1M tokens

GPT-5.6 Luna

OpenAI-compatible route for GPT-5.6 Luna, tuned for frontier reasoning, coding, and agentic workloads.

OpenAI|1M context|Tiered pricing:0–272K:14 Credits input/84 Credits output/1.4 Credits cache read/17.5 Credits cache write·272K–1M:28 Credits input/126 Credits output/2.8 Credits cache read/35 Credits cache write/ 1M tokens

GPT-5.6 Sol

OpenAI-compatible ClawOS route for GPT-5.6 Sol, tuned for frontier reasoning, coding, and agentic workloads.

OpenAI|1M context|Tiered pricing:0–272K:280 Credits input/1,400 Credits output/28 Credits cache read/350 Credits cache write·272K–1M:560 Credits input/2,100 Credits output/56 Credits cache read/700 Credits cache write/ 1M tokens

GPT-5.6 Terra

OpenAI-compatible ClawOS route for GPT-5.6 Terra, tuned for frontier reasoning, coding, and agentic workloads.

OpenAI|1M context|Tiered pricing:0–272K:140 Credits input/840 Credits output/14 Credits cache read/175 Credits cache write·272K–1M:280 Credits input/1,260 Credits output/28 Credits cache read/350 Credits cache write/ 1M tokens

GPT-6 Astra

OpenAI-compatible Hboom Azure-Mid route for GPT-6 Astra.

OpenAI|1M context|Tiered pricing:0–272K:700 Credits input/3,500 Credits output/70 Credits cache read/875 Credits cache write·272K–1M:1,400 Credits input/5,250 Credits output/140 Credits cache read/1,750 Credits cache write/ 1M tokens

GPT-6 Luna

Efficient reasoning for focused, high-volume tasks.

OpenAI|1.1M context|Tiered pricing:0–272K:7 Credits input/35 Credits output/0.7 Credits cache read/8.75 Credits cache write·272K–1.05M:14 Credits input/52.5 Credits output/1.4 Credits cache read/17.5 Credits cache write/ 1M tokens

GPT-6 Sol

Reasoning for complex coding and agentic workflows.

OpenAI|1.1M context|Tiered pricing:0–272K:140 Credits input/700 Credits output/14 Credits cache read/175 Credits cache write·272K–1.05M:280 Credits input/1,050 Credits output/28 Credits cache read/350 Credits cache write/ 1M tokens

GPT-6.1 Sol

Near-Astra performance for complex coding, computer use, and professional work.

OpenAI|1.1M context|Tiered pricing:0–272K:140 Credits input/700 Credits output/7 Credits cache read/175 Credits cache write·272K–1.05M:280 Credits input/1,050 Credits output/14 Credits cache read/350 Credits cache write/ 1M tokens

Kimi K2.6

Updated Moonshot model with stronger long-context reasoning and higher output quality for research and document-heavy workflows.

Moonshot|256K context|66.5 Credits input/280 Credits output/11.2 Credits cache read/66.5 Credits cache write/ 1M tokens

Kimi K2.7 Code

Moonshot coding model served through the OpenClaw route for software engineering and agent workflows.

Moonshot|256K context|66.5 Credits input/280 Credits output/13.3 Credits cache read/66.5 Credits cache write/ 1M tokens

Kimi K3

Moonshot's flagship long-horizon coding and knowledge-work model with a 1M-token context window and always-on reasoning.

Moonshot|1.0M context|210 Credits input/1,050 Credits output/21 Credits cache read/210 Credits cache write/ 1M tokens

MiniMax M2.5

MiniMax's versatile model with balanced performance across reasoning, creative writing, and multilingual tasks.

MiniMax|200K context|21 Credits input/84 Credits output/4.2 Credits cache read/26.25 Credits cache write/ 1M tokens

MiniMax M2.7

Refreshed MiniMax model with broader context and balanced performance for multilingual chat, reasoning, and creative work.

MiniMax|192K context|21 Credits input/84 Credits output/4.2 Credits cache read/26.25 Credits cache write/ 1M tokens

MiniMax M2.7 Highspeed

Low-latency MiniMax M2.7 variant for fast coding, refactoring, and agent workflows.

MiniMax|192K context|60 Credits input/240 Credits output/6 Credits cache read/37.5 Credits cache write/ 1M tokens

MiniMax M3

Frontier MiniMax model for agentic coding, tool use, multimodal input, and long-context reasoning.

MiniMax|1M context|Tiered pricing:0–512K:30 Credits input/120 Credits output/6 Credits cache read·512K–1M:60 Credits input/240 Credits output/12 Credits cache read/ 1M tokens

PixVerse C1

PixVerse C1 async video generation route using the official PixVerse API protocol.

PixVerse|33K context|Tiered pricing:360p no audio:3 Credits output·360p audio:4 Credits output·540p no audio:4 Credits output·540p audio:5 Credits output·720p no audio:5 Credits output·720p audio:6.5 Credits output·1080p no audio:9.5 Credits output·1080p audio:12 Credits output/ sec

PixVerse V6

PixVerse V6 async video generation route using the official PixVerse API protocol.

PixVerse|33K context|Tiered pricing:360p no audio:2.5 Credits output·360p audio:3.5 Credits output·540p no audio:3.5 Credits output·540p audio:4.5 Credits output·720p no audio:4.5 Credits output·720p audio:6 Credits output·1080p no audio:9 Credits output·1080p audio:11.5 Credits output/ sec

Seedance 2.0

BytePlus ModelArk Seedance 2.0 async video route with direct provider task polling and billing.

BytePlus|33K context|1,020.5413 Credits output/ 1M tokens

Seedance 2.0 Asset

BytePlus ModelArk Seedance asset-library video route using asset groups, asset polling, task polling, and billing.

BytePlus|33K context|1,071.885 Credits output/ 1M tokens

Seedance 2.0 Asset Fast

Faster BytePlus ModelArk Seedance asset-library video route with asset ingestion and async task polling.

BytePlus|33K context|777.7175 Credits output/ 1M tokens

Seedance 2.0 Fast

BytePlus ModelArk Seedance fast route for basic async video generation with direct provider task polling and billing.

BytePlus|33K context|740.5024 Credits output/ 1M tokens

Seedance 2.5

BytePlus ModelArk Seedance 2.5 async video route for text-to-video, frame references, video references, and extended 2.5 controls.

BytePlus|33K context|1,016.5 Credits output/ 1M tokens

Seedance 2.5 Asset

BytePlus ModelArk Seedance 2.5 asset-library video route with asset ingestion, async task polling, and extended 2.5 controls.

BytePlus|33K context|1,067.325 Credits output/ 1M tokens