Catalog
Frontier and uncensored models in one catalog
35 models across 8 families: GPT, Claude, Gemini, Grok, DeepSeek, GLM (including the uncensored and abliterated tiers), MiMo and Kimi. All of them are reachable through the same OpenAI-compatible endpoint, and prices are per 1,000,000 tokens.
- models
- 35
- families
- 8
Model families
Gemini
128K context for images, documents and mixed input.
1 model →GPT
Agentic workflows, function calling and long-context reasoning, with 1M-token and low-cost fast tiers.
8 models →Claude
Long-horizon reasoning, structured writing and code review, from Haiku up to Opus.
9 models →Grok
Conversational reasoning with current context, up to 500K.
3 models →DeepSeek
The cheapest coding and maths models here, including DeepSeek V4 Pro Uncensored.
4 models →GLM
Bilingual generalist and home of the abliterated and uncensored tiers.
7 models →MiMo
High-throughput batch work where cost per token matters most.
2 models →Kimi
1M-token context for agent loops, retrieval and long documents.
1 model →Which AI API model should you use?
A comparison by task, using the lowest-cost suitable model in each column.
| Use case | Best value | Best quality | Uncensored option |
|---|---|---|---|
| Coding & maths | DeepSeek V4.1 Flash | Claude Opus 5.5 | DeepSeek V4 Pro Uncensored |
| Agents & tool use | GPT-6 Luna | GPT-6.1 Sol | GLM-5.3 Uncensored |
| Long context (>1M) | MiMo V2.6 Flash | GPT-6 Astra | GLM-5.3 Abliterated |
| Vision & multimodal | Gemini 4 Argon | Gemini 4 Argon | None |
| Cheapest at scale | DeepSeek V4.1 Flash | GLM-5.3 Flash | GLM-5.3 Flash Uncensored |