Anthropic
Claude
- Opus 4.8
- Opus 4.7
- Opus 4.6
- Opus 4.5
- Sonnet 5
- Sonnet 4.6
- Sonnet 4.5
- Sonnet 4
- Haiku 4.5
- Fable 5
Clawgate Inference brings leading models from Anthropic, OpenAI, and more into the CLIs your team already uses, with no extra setup for your engineers. You choose which models they can use, and usage is billed at provider rates, at cost, plus one clear platform fee.
Your developers keep one vsk_… key. Switching between a frontier
model and a low-cost open one is a dashboard setting, not a new account, a new billing
relationship, or a change to anyone’s workflow.
Claude
GPT
Grok
DeepSeek
Kimi
GLM
Fugu
Nemotron
New models are added as providers release them. Admins set the allowed models per team and per project, so you can serve lower-cost models whenever full power is not needed.
On the Team plan and above, connect an OpenRouter key to reach models far beyond the curated catalog above. The same per-team and per-project allow-lists, budgets, and analytics apply.
Left alone, Claude Code, Codex, and OpenCode pick a model on their own, and you pay for that choice. Clawgate puts the decision back with you.
Pick exactly which models a policy permits. Ask for something outside the list and Clawgate serves the best model you have allowed instead of failing the request.
Pin a whole team or a single project to one model when you want predictable cost per request, whatever the CLI asks for.
Turn on smart model routing and routine work is served by a lighter, cheaper model automatically, saving your top model for the hard parts. See how routing works →