LogoClaw Cost Gate
Login

Curated Models

Browse our curated selection of popular and recommended AI models for getting started with OpenClaw. While hundreds of models are available via the API, these represent the best balance of capability, speed, and cost for general use.

Tag:
Model Name ↑Weekly Usage ↕$/M Tokens ↕Release Date ↕Agent ↕Value ↕Use
Anthropic: Claude Haiku 4.5196$1.802025-10-1549-
Anthropic: Claude Opus 4.61,040$9.002026-02-048422
Anthropic: Claude Sonnet 4.6677$5.402026-02-178019
DeepSeek: DeepSeek V3.21,200$0.282025-12-017798
Google: Gemini 3 Flash Preview978$1.002025-12-1785225
Google: Gemini 3.1 Pro Preview181$4.002026-02-1995156
Google: Gemma 4 31B7$0.192026-04-027318
MiniMax: MiniMax M2.51,230$0.292026-02-1290800
MiniMax: MiniMax M2.7706$0.482026-03-1886512
MoonshotAI: Kimi K2.5551$0.652026-01-2792744
OpenAI: GPT-5.4105$5.002026-03-059297
OpenAI: GPT-5.4 Nano28$0.412026-03-1781242
OpenAI: gpt-oss-120b448$0.072025-08-05728
Qwen: Qwen3.5-122B-A10B13$0.622026-02-2590641
Qwen: Qwen3.5-9B-$0.072026-03-1084392
Z.ai: GLM 4.7 Flash-$0.132026-01-1978128
Z.ai: GLM 5750$1.042026-02-1190386
Z.ai: GLM 5 Turbo-$1.762026-03-1592275
xAI: Grok 4.1 Fast828$0.262025-11-1964-
xAI: Grok 4.2020$2.802026-03-3193189

* Weekly Usage is the total tokens processed (in Billions) across the OpenRouter network.
* Cost/M Token is a blended estimate per 1 Million tokens, calculated as (Input * 4 + Output) / 5.
* Agent represents the average of agentic capabilities benchmarks in the Artificial Analysis Intelligence Index (GDPval-AA, 𝜏²-Bench Telecom). See https://artificialanalysis.ai/.
* Value is calculated as (Agent - 70)² / Max(Cost, 0.5) for Agent scores > 70.