88 models
Claude Fable 5
Anthropic's high-capability Fable 5 model for advanced reasoning, repository-scale coding, long-context analysis, and agentic workflows.
Claude Haiku 4.5
Default Claude Haiku route for fast background work, summaries, and lightweight agent loops.
Claude Opus 4.6
Default Claude Opus route for complex planning and high-quality reasoning.
Claude Opus 5
Default Claude Opus 5 route for the strongest planning, coding, and long-running agent work.
Claude Sonnet 4.6
Default Claude Sonnet route for balanced coding, analysis, and agent traffic.
DeepSeek Chat V3 0324
DeepSeek V3 chat snapshot for dependable coding, math, and general reasoning.
DeepSeek Chat V3.1
DeepSeek V3.1 chat model for balanced quality, cost, and coding support.
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus model for stronger chat and technical reasoning workloads.
DeepSeek V3.2
DeepSeek V3.2 served through Qianfan International for high-ROI chat, coding, math, and reasoning workloads.
DeepSeek V3.2 Exp
Experimental DeepSeek V3.2 model for previewing newer reasoning and chat behavior.
DeepSeek V4 Flash
Lower-latency DeepSeek V4 route for cost-sensitive chat and structured generation.
DeepSeek V4 Pro
Infer DeepSeek Pro route for coding, math, and complex analysis with official DeepSeek primary routing and provider fallbacks.
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.
Gemini 2.5 Flash
Discounted Gemini Flash route for fast multimodal-capable assistant traffic.
Gemini 2.5 Flash Image
Gemini image-capable route for visual prompts and image-token billing.
Gemini 3 Pro Image Preview
Higher-fidelity Gemini image-generation route for richer visual outputs and prompt-following.
Gemini 3.1 Flash Image Preview
Low-latency Gemini 3.1 image-preview route for quick visual generation with discounted output-image pricing.
Gemma 3 12B IT
Small Gemma 3 instruction model for very low-cost chat and classification tasks.
Gemma 3 27B IT
Instruction-tuned Gemma 3 model for lightweight assistants and text generation.
Gemma 4 26B A4B IT
Compact instruction-tuned Gemma model for fast and low-cost production use.
Gemma 4 31B IT
Instruction-tuned Gemma model for economical chat, coding support, and analysis.
GLM-4.5 Air
Efficient GLM model for low-cost bilingual chat, summarization, and extraction.
GLM-4.6
Earlier GLM generation with dependable bilingual chat and instruction following.
GLM-4.7
Zhipu GLM model for balanced reasoning, coding support, and Chinese-English tasks.
GLM-4.7 Flash
Fast GLM flash model for inexpensive chat, classification, and structured output.
GLM-5
Zhipu AI's latest foundation model with strong bilingual capabilities and advanced reasoning for enterprise applications.
GLM-5.1
Newer Zhipu flagship with stronger bilingual reasoning and enterprise-oriented instruction following.
GLM-5.2
Z.ai flagship route for long-context bilingual reasoning and agent workloads.
GPT Image 2
OpenAI image-generation route for synchronous text-to-image requests over the standard Images API.
GPT OSS 120B
Large open-weight GPT OSS model for economical reasoning, coding, and general chat.
GPT OSS 20B
Smaller open-weight GPT OSS model for lightweight chat and high-volume routing.
GPT-5.3 Codex
Default Codex-oriented GPT route for developer agents and code tasks.
GPT-5.4
Default GPT-5.4 route for cost-sensitive production agents.
GPT-5.5
Frontier GPT route for demanding reasoning, tool use, and agentic workloads.
GPT-5.6 Luna
Default GPT-5.6 Luna route for cost-sensitive agent traffic and high-volume reasoning workloads.
GPT-5.6 Sol
High-capability GPT-5.6 route for complex coding, review, and agent planning.
GPT-5.6 Terra
Default GPT-5.6 Terra route for stronger reasoning, coding, and agentic workloads.
GPT-6 Astra
Long-context GPT-6 Astra route for demanding reasoning, coding, and agentic workloads.
Grok 4.1 Fast
Default Grok route for low-latency chat and production traffic.
Kimi K2.5
Moonshot AI's powerful model with strong long-context understanding and reasoning. Excels at document analysis and complex tasks.
Kimi K2.6
Updated Moonshot model with stronger long-context reasoning and higher output quality for research and document-heavy workflows.
Kimi K3
Moonshot's flagship long-horizon coding and knowledge-work model with a 1M-token context window and always-on reasoning.
Kling v2.6
Kling async video route for text-to-video and image-to-video generation through the ClawOS media API.
Kling v3
Kling v3 async video route for higher-quality text-to-video and image-to-video generation.
Kling v3 Omni
Kling v3 omni async video route for prompt-guided video editing with optional first-frame image input.
Llama 3.1 70B Instruct
Larger Llama instruct model for stronger open-weight reasoning and generation.
Llama 3.1 8B Instruct
Small Llama instruct model for inexpensive chat, classification, and extraction.
Llama 3.3 70B Instruct
Updated 70B Llama instruct model for general-purpose chat and reasoning.
Llama 4 Maverick
Llama 4 model for long-context open-weight chat and multimodal-adjacent workflows.
MiMo V2 Flash
Xiaomi MiMo flash model for high-throughput, latency-sensitive production traffic.
MiMo V2.5
General-purpose MiMo model with 1M context and tiered pricing for longer prompts.
MiMo V2.5 Pro
Updated MiMo pro model for broad long-context reasoning and production assistants.
MiniMax M2.5
MiniMax's versatile model with balanced performance across reasoning, creative writing, and multilingual tasks.
MiniMax M2.7
Refreshed MiniMax model with broader context and balanced performance for multilingual chat, reasoning, and creative work.
Mistral Nemo
Efficient Mistral model for broad multilingual chat and economical generation.
Mistral Small 3.2 24B Instruct
Instruction-tuned Mistral Small model for compact reasoning and production assistants.
Nemotron 3 Nano 30B A3B
Compact NVIDIA Nemotron model for efficient chat and instruction following.
Nemotron 3 Super 120B A12B
Larger NVIDIA Nemotron model for stronger reasoning and production assistants.
PixVerse C1
PixVerse C1 async video generation route using the official PixVerse API protocol.
PixVerse V6
PixVerse V6 async video generation route using the official PixVerse API protocol.
Qwen 3 235B A22B 2507
Large Qwen mixture model for economical reasoning and long-context generation.
Qwen 3 30B A3B Instruct 2507
Compact Qwen mixture model for fast instruction following and practical chat.
Qwen 3 32B
Mid-sized Qwen 3 model for affordable reasoning, chat, and content generation.
Qwen 3 Coder
Qwen 3 coder model for software engineering, code repair, and technical analysis.
Qwen 3 Coder Next
Qwen coding model for code generation, refactoring, and agentic developer workflows.
Qwen 3 Coder Plus
Specialized coding model from Alibaba with strong code generation, debugging, and analysis capabilities.
Qwen 3 Next 80B A3B Instruct
Qwen Next mixture model for efficient reasoning, chat, and instruction following.
Qwen 3 VL 235B A22B Instruct
Qwen VL model for multimodal-oriented prompts and strong text instruction following.
Qwen 3.5 27B
Mid-sized Qwen 3.5 model for general chat, analysis, and structured output.
Qwen 3.5 35B A3B
Efficient Qwen mixture model balancing quality, cost, and multilingual coverage.
Qwen 3.5 397B A17B
Large Qwen 3.5 model for high-quality multilingual reasoning and synthesis.
Qwen 3.5 9B
Small Qwen 3.5 model for low-latency chat, routing, and simple transformations.
Qwen 3.5 Flash
Fast and cost-effective Qwen model optimized for high-throughput tasks. Supports up to 1M context with tiered pricing.
Qwen 3.5 Flash 02-23
Qwen 3.5 Flash snapshot for fast, low-cost multilingual assistant traffic.
Qwen 3.5 Plus
Alibaba's flagship language model with strong multilingual and reasoning capabilities. Supports up to 1M context with tiered pricing.
Qwen 3.5 Plus 02-15
Qwen 3.5 Plus snapshot with 1M context and tiered long-prompt pricing.
Qwen 3.6 Plus
Latest generation Qwen model with improved reasoning and instruction following capabilities.
Seedance 2.0 (Official)
Official BytePlus ModelArk Seedance 2.0 async video route with direct official-provider task polling and billing.
Seedance 2.0 (Relay)
Asynchronous text-to-video route served through the ClawOS relay at the discounted relay rate.
Seedance 2.0 Asset (Official)
Official BytePlus ModelArk Seedance asset-library video route using official asset groups, asset polling, task polling, and billing.
Seedance 2.0 Asset (Relay)
Relay Seedance video generation with asset-group support for character, face, and reusable media references.
Seedance 2.0 Asset Fast (Official)
Faster official BytePlus ModelArk Seedance asset-library video route with official asset ingestion and async task polling.
Seedance 2.0 Asset Fast (Relay)
Faster relay Seedance asset-group video route for reference-driven generation with lower turnaround time.
Seedance 2.0 Fast (Official)
Official BytePlus ModelArk Seedance fast route for basic async video generation with direct official-provider task polling and billing.
Seedance 2.0 Fast (Relay)
Lower-latency Seedance text-to-video route served through the ClawOS relay at the discounted relay rate.
Seedance 2.5 (Official)
Official BytePlus ModelArk Seedance 2.5 async video route for text-to-video, frame references, video references, and extended 2.5 controls.
Seedance 2.5 Asset (Official)
Official BytePlus ModelArk Seedance 2.5 asset-library video route with official asset ingestion, async task polling, and extended 2.5 controls.
Step 3.5 Flash
StepFun flash model for quick multilingual chat, extraction, and structured generation.