All comparisons


| Visit FerryAPI | Visit Magnitude | |
|---|---|---|
| What it costs | ||
| Pricing | Paid | Open source |
| Pricing details | Prepaid USD balance with per-token usage billing - no subscription - enterprise deployment available on request | Free and Apache-2.0. Models run on your own machine, so there are no token costs, API keys or rate limits, and there is no paid tier or hosted option. |
| Price range | Shown only after signing in | $0/mo |
| Free option | No free option | Free tier |
| What it is | ||
| What it does | OpenAI-compatible API gateway giving access to DeepSeek, Qwen, Kimi and MiMo on prepaid USD balance, with provider pools and customer API key management. | An Apache-2.0 inference server that profiles your hardware, recommends models that fit with estimated tokens per second, and wires them into the agent you use. |
| Platform | Web | macOS, Linux |
What it costs
- Pricing
- Paid
- Pricing details
- Prepaid USD balance with per-token usage billing - no subscription - enterprise deployment available on request
- Price range
- Shown only after signing in
- Free option
- No free option
What it is
- What it does
- OpenAI-compatible API gateway giving access to DeepSeek, Qwen, Kimi and MiMo on prepaid USD balance, with provider pools and customer API key management.
- Platform
- Web
What it costs
- Pricing
- Open source
- Pricing details
- Free and Apache-2.0. Models run on your own machine, so there are no token costs, API keys or rate limits, and there is no paid tier or hosted option.
- Price range
- $0/mo
- Free option
- Free tier
What it is
- What it does
- An Apache-2.0 inference server that profiles your hardware, recommends models that fit with estimated tokens per second, and wires them into the agent you use.
- Platform
- macOS, Linux
Read the full reviews
What each one is actually like to use, tested by hand rather than summarised from the vendor’s own page.
























