All comparisons


| Visit Standard Compute | Visit vLLM | |
|---|---|---|
| What it costs | ||
| Pricing | Paid | Open source |
| Pricing details | Individual plans Starter $19, Economy $39, Standard $89 and Pro $249 a month; business plans Pro Plus $499, Growth $999 and Scale $2,499 a month, with a custom Business tier. Each includes a monthly compute budget with no per-token fees. Small free trial allowance on request. | Free and Apache-2.0. There is no pricing page, no hosted tier and no paid edition; the project is funded by donations through GitHub and OpenCollective, and compute for development and testing is contributed by sponsors. Your cost is the hardware you run it on. |
| Price range | $19 - $2499/mo | Not published by the vendor |
| Free option | Free trial only | No free option |
| What it is | ||
| What it does | Flat-rate LLM API gateway with smart routing across frontier models, replacing per-token billing with a predictable monthly price for coding agents and tools. | The Apache-2.0 serving engine that most self-hosted LLM stacks run on, exposing any of 200+ open-weights architectures behind an OpenAI-compatible API. |
What it costs
- Pricing
- Paid
- Pricing details
- Individual plans Starter $19, Economy $39, Standard $89 and Pro $249 a month; business plans Pro Plus $499, Growth $999 and Scale $2,499 a month, with a custom Business tier. Each includes a monthly compute budget with no per-token fees. Small free trial allowance on request.
- Price range
- $19 - $2499/mo
- Free option
- Free trial only
What it is
- What it does
- Flat-rate LLM API gateway with smart routing across frontier models, replacing per-token billing with a predictable monthly price for coding agents and tools.
What it costs
- Pricing
- Open source
- Pricing details
- Free and Apache-2.0. There is no pricing page, no hosted tier and no paid edition; the project is funded by donations through GitHub and OpenCollective, and compute for development and testing is contributed by sponsors. Your cost is the hardware you run it on.
- Price range
- Not published by the vendor
- Free option
- No free option
What it is
- What it does
- The Apache-2.0 serving engine that most self-hosted LLM stacks run on, exposing any of 200+ open-weights architectures behind an OpenAI-compatible API.
Read the full reviews
What each one is actually like to use, tested by hand rather than summarised from the vendor’s own page.


























