Free
Try every frontier model with a small daily allowance.
$0.00
- Daily allowance
- 5,000
- Monthly allowance
- 150,000
Every frontier AI model, one subscription
Create a ClawAI account and reach Claude Opus 5, GPT-5, Gemini 3 Pro, Kimi K2, GLM-5.1, Qwen3, DeepSeek V3.2, Grok 4 and Amazon Bedrock from a single chat — no separate vendor accounts, no separate bills, no juggling API keys. Pick a plan, log in, and start working.
Start free and upgrade whenever you need more. Paid plans from $5 a month, cancel any time.
Last reviewed 2026-07-27
The models you get
One subscription covers every provider below. Switch models mid-conversation, or let ClawAI pick the best one for each message.
Newest models in the catalog
A concise snapshot of recently added models available through current connectors.
- GLM-5.2Zhipu
- Kimi K3Moonshot
- Qwen3.5Alibaba
- MiniMax M2.7MiniMax
- DeepSeek V4 ProDeepSeek
- DeepSeek V4 FlashDeepSeek
- Gemini 3 Flash PreviewGoogle
- Nemotron 3 SuperNVIDIA
Anthropic Claude
Deep reasoning, long documents, and careful code review.
- Claude Fable 5
- Claude Opus 5
- Claude Sonnet 5
- Claude Haiku 4.5
OpenAI GPT
Broad general capability with strong tool use and structured output.
- GPT-5.6 Sol
- GPT-5.6 Terra
- GPT-5.6 Luna
- GPT-5.5
Google Gemini
Very large context windows, fast responses, and native multimodal input.
- Gemini 3.6 Flash
- Gemini 3.5 Flash
- Gemini 3.5 Flash-Lite
- Gemini 3.1 Pro Preview
Moonshot Kimi
Long-context analysis and agentic workflows at low cost.
- Kimi K3
- Kimi K2.7 Code
- Kimi K2.6
Zhipu GLM
Strong bilingual reasoning with explicit thinking modes.
- GLM-5.2
- GLM-5.1
- GLM-5 Turbo
- GLM-5
Alibaba Qwen
Excellent code generation and a wide range of model sizes.
- Qwen3.7 Plus
- Qwen3.6 Plus
- Qwen3.5 Plus
- Qwen3 Coder Next
DeepSeek
Mathematics, algorithms, and step-by-step reasoning.
- DeepSeek V4 Pro
- DeepSeek V4 Flash
xAI Grok
Fast conversational answers with current-events awareness.
- Grok 4.5
- Grok 4.20
- Grok 4.3
Amazon Bedrock
Enterprise-grade hosting for teams already invested in AWS.
- Nova 2 Lite
- GPT-5.6 Sol
- Claude Opus 5
- Grok 4.3
New frontier models are added as they launch — your plan covers them from day one, metered against a single allowance.
Plans and pricing
Every paid plan unlocks every model. The only difference is how much you can use each day and each month.
Trial
A trial subscription
$0.10/month
- Daily allowance
- 10,000
- Monthly allowance
- 300,000
Starter
Everyday access to fast, low-cost frontier models.
$5.00/month
- Daily allowance
- 50,000
- Monthly allowance
- 750,000
Plus
More allowance and access to standard-tier models.
$10.00/month
- Daily allowance
- 100,000
- Monthly allowance
- 1,750,000
Pro
Premium models, deep reasoning and heavy orchestration.
$20.00/month
- Daily allowance
- 250,000
- Monthly allowance
- 4,000,000
Team
Shared workspaces and a large pooled allowance.
$50.00/month
- Daily allowance
- 750,000
- Monthly allowance
- 11,000,000
Scale
High-volume access across every model class.
$100.00/month
- Daily allowance
- 1,500,000
- Monthly allowance
- 24,000,000
Unlimited
Unlimited chats and messages, with fair-use on premium cloud.
$200.00/month
- Daily allowance
- 5,000,000
- Monthly allowance
- Unlimited
What happens when you send a message
You send a message in a conversation, optionally attaching files or picking a specific model.
Routing picks the model based on the mode you chose, what the message asks for, and which providers are healthy right now.
Context is assembled saved memories, attached context packs and the relevant chunks of your uploaded files are merged into the prompt within a token budget, alongside the conversation history.
The model answers streamed back as it is generated, with live timing and reasoning where the model exposes it, and an automatic fallback to another model if the first one fails.
The exchange is recorded facts and preferences worth keeping are saved for next time, and the cost is metered against your allowance so there is no surprise at the end of the month.
Memory and context are switches you control per conversation. Everything a model was given is listed in a receipt attached to the answer, so you can check what informed it. Uploaded files are chunked and retrieved the same way, which is how ClawAI answers questions about your own documents instead of guessing from training data.
Beyond a single chat window
When one model’s answer isn’t enough on its own, ClawAI offers several ways to combine, check, and improve on it.
- Parallel compare
- send one prompt to two to five models at once and see every response side by side, with per-model latency and token counts.
- Consensus
- run the same prompt across several models and synthesize a single answer from where they agree.
- Escalation chains
- start with a fast, cheap model and automatically escalate to a stronger one when quality falls short of a threshold.
- Best-of-N
- generate several candidate answers and select the strongest one by a scoring pass.
- Answer repair
- detect and correct specific classes of errors in a prior response rather than regenerating from scratch.
- Verification
- have a second pass check a response for correctness before it reaches you, with configurable revision limits.
- Role packs
- run a prompt through a small team of role-specialized models (for example, a planner, a critic, and a writer) that hand off to one another.
- Pipelines
- chain multiple orchestration stages into a single named, repeatable workflow.
- Judge & Critic review
- an optional independent model reviews and scores a generated response before it is treated as final.
For organisations
Need ClawAI inside your own network?
Companies can have ClawAI deployed on their own servers running local models only, so no prompt, document or conversation ever leaves their infrastructure. This is a bespoke deployment we set up with you — talk to us and we will scope it.
- Runs on your servers
- Deployed into your data centre or private cloud, managed by your team, behind your firewall.
- Local models only
- Open-weight models served on your own hardware. No external provider calls and no third-party data processing.
- Your controls, your audit trail
- SSO, role-based access, retention rules and a full audit log of every request, all kept inside your environment.
Start on the free plan
Create an account and send your first message in under a minute. Upgrade only when you outgrow the free allowance.