Model Available

Every model below is served through the XENN gateway. The figures are technical limits, counted in tokens: context length is the most a single request may contain — your prompt and the model’s reply together — while max output is the longest reply the model can produce in one answer. Pricing is not shown here; it lives in your dashboard.

Token = the smallest unit of text a model reads: roughly a word, a number or a punctuation mark. Both limits are counted in tokens.
Context length caps input + output together in one request; a request that exceeds it is rejected.
Max output is the ceiling for the reply alone — always the smaller of the two figures, and it applies even when the context window is still far from full.