Model APIs
Open models served through an API, by the token. 50 providers on EveryNeocloud so far.
A model API sells the output of a model rather than the hardware: the customer sends text or images and pays per million tokens. Inference platforms, chip clouds and hyperscalers all serve open models this way, from Llama and Qwen to DeepSeek and Mistral. For many companies this is the simplest way to use AI compute, with no GPUs to manage at all.
How it is priced
Prices are set per million input tokens and per million output tokens, with output usually costing more because it is generated one token at a time. Providers compete on price, on speed in tokens per second, and on the delay before the first token. Independent benchmarks compare them model by model, and prices for the same model can differ several times between providers.
Who serves them
Groq, Cerebras and SambaNova serve models on their own chips. Neoclouds such as Nebius and Together AI, and European clouds such as Scaleway, run APIs on Nvidia GPUs. AWS offers many models through Bedrock. Routers such as OpenRouter let one account call hundreds of models across providers. The companies that make closed models, such as OpenAI and Anthropic, run their own APIs.
Famous model APIs providers
Further reading
Photo credits on this page
The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.
- Cerebras: Coolcaesar, CC BY 4.0, source
- Cloudflare: HaeB, CC BY-SA 4.0, source
- Groq: Avivweinstein, CC BY-SA 4.0, source
- SpaceX Super Intelligence: BrokenSegue, CC BY-SA 4.0, source
- Jio Platforms: Nairspecht, CC BY-SA 4.0, source
- Scaleway: Online.net / Iliad, CC BY 3.0, source
- OpenRouter: Wikideas1, CC0, source
- Baidu: N509FZ, CC BY-SA 4.0, source
- Yandex Cloud: WikiFido, CC BY-SA 4.0, source
- Google data centers: erwinboogert, CC BY-SA 3.0, source