AI Models Directory
Browse every model on the Anoman gateway — compare pricing, context, and capabilities across all providers.
498 models
| Select to compare | Cache Read Rp/1M | Features | ||||||
|---|---|---|---|---|---|---|---|---|
| AI model | aion-2-0 | Rp 14.784 | Rp 29.568 | — | 131K | |||
| AI model | aion-3-0 | Rp 55.440 | Rp 110.880 | — | 131K | |||
| AI model | aion-3-0-mini | Rp 12.936 | Rp 25.872 | — | 131K | |||
| AI model | aion-3-5 | Rp 55.440 | Rp 110.880 | — | 262K | |||
| AI model | aion-3-5-mini | Rp 12.936 | Rp 25.872 | — | 262K | |||
| AI model | ember-1 | Rp 55.440 | Rp 277.200 | — | 1.0M | |||
| AI model | fugu-max | Rp 36.960 | Rp 110.880 | — | 1.0M | |||
| AI model | fugu-ultra | Rp 92.400 | Rp 554.400 | — | 1.0M | |||
| AI model | fugu-ultra-v2 | Rp 92.400 | Rp 554.400 | — | 1.0M | |||
| AI model | glimpse | Rp 11.088 | Rp 55.440 | — | 262K | |||
| AI model | granite-4-1-8b | Rp 924 | Rp 1.848 | — | 131K | |||
| AI model | granite-4-2-8b | Rp 1.109 | Rp 4.620 | — | 131K | |||
| AI model | hermes-4-405b | Rp 18.480 | Rp 55.440 | — | 131K | |||
| AI model | hermes-4-70b | Rp 2.403 | Rp 7.392 | — | 131K | |||
| AI model | inkling | Rp 18.480 | Rp 74.844 | — | 524K | |||
| AI model | laguna-s-2-1 | Rp 1.664 | Rp 3.327 | — | 1.0M | |||
| AI model | laguna-xs-2-1 | Rp 1.109 | Rp 2.218 | — | 262K | |||
| AI model | lfm-2-5-24b-a2b | Rp 924 | Rp 12.936 | — | 128K | |||
| AI model | lfm-2-5-2-6b | Rp 6.468 | Rp 9.240 | — | 128K | |||
| AI model | lfm-3-1-7b | Rp 1.479 | Rp 3.696 | — | 262K | |||
| AI model | ling-3-0-tiny | Rp 278 | Rp 832 | — | 262K | |||
| AI model | ling-3-1-flash | Rp 832 | Rp 2.495 | — | 1.0M | |||
| AI model | ling-flash-2-0 | Rp 2.588 | Rp 10.534 | — | 33K | |||
| AI model | longcat-2-0 | Rp 5.544 | Rp 22.176 | — | 33K | |||
| AI model | longcat-2-0-global | Rp 5.544 | Rp 22.176 | — | 1.0M | |||
| AI model | magnum-v4-72b | Rp 46.200 | Rp 92.400 | — | 33K | |||
| AI model | midm-k-3-0-pro | Rp 3.696 | Rp 14.784 | — | 262K | |||
| AI model | mimo-v2-5 | Rp 7.392 | Rp 36.960 | — | 1.0M | |||
| AI model | mimo-v2-5-pro | Rp 8.871 | Rp 33.264 | — | 1.0M | |||
| AI model | mimo-v2-6-flash | Rp 2.588 | Rp 5.175 | — | 1.1M | |||
| AI model | mimo-v2-6-pro | Rp 73.920 | Rp 147.840 | — | 1.1M | |||
| AI model | mimo-v2-6-pro-ultraspeed | Rp 80.388 | Rp 160.776 | — | 1.0M | |||
| AI model | morph-v3-fast | Rp 14.784 | Rp 22.176 | — | 262K | |||
| AI model | morph-v3-large | Rp 16.632 | Rp 35.112 | — | 262K | |||
| AI model | motif-3 | Rp 5.544 | Rp 22.176 | — | 262K | |||
| AI model | muse-ember | Rp 1.848 | Rp 9.240 | — | 1.0M | |||
| AI model | muse-glimmer-30b | Rp 5.544 | Rp 22.176 | — | 131K | |||
| AI model | muse-spark-1-1 | Rp 23.100 | Rp 78.540 | — | 1.0M | |||
| AI model | muse-spark-1-2 | Rp 23.100 | Rp 78.540 | — | 1.0M | |||
| AI model | muse-spark-1-3 | Rp 23.100 | Rp 78.540 | — | 1.0M | |||
| AI model | muse-spark-open | Rp 23.100 | Rp 78.540 | — | 1.0M | |||
| AI model | muse-wonder | Rp 73.920 | Rp 369.600 | — | 1.0M | |||
| AI model | nemotron-3-5-content-safety | Rp 3.696 | Rp 3.696 | — | 131K | |||
| AI model | nemotron-3-5-lightning | Rp 1.294 | Rp 3.696 | — | 1.0M | |||
| AI model | nemotron-3-5-super-vl | Rp 1.848 | Rp 7.392 | — | 1.0M | |||
| AI model | nemotron-3-nano-30b-a3b | Rp 1.109 | Rp 4.436 | — | 262K | |||
| AI model | nemotron-3-super-120b-a12b | Rp 1.386 | Rp 7.392 | — | 262K | |||
| AI model | nemotron-3-ultra-550b-a55b | Rp 11.088 | Rp 44.352 | — | 262K | |||
| AI model | nemotron-3-ultra-nvfp4 | Rp 11.088 | Rp 44.352 | — | 262K | |||
| AI model | nemotron-lightning-3p5-30b-a3b | Rp 924 | Rp 3.696 | — | 262K | |||
| AI model | nex-n2-5-mini | Rp 462 | Rp 1.848 | — | 262K | |||
| AI model | nex-n2-5-pro | Rp 1.386 | Rp 4.620 | — | 262K | |||
| AI model | nex-n2-6 | Rp 2.218 | Rp 7.392 | — | 262K | |||
| AI model | nex-n2-mini | Rp 462 | Rp 1.848 | — | 262K | |||
| AI model | nex-n2-pro | Rp 4.620 | Rp 18.480 | — | 262K | |||
| AI model | nex-n2-pro-cn | Rp 4.620 | Rp 18.480 | — | 33K | |||
| AI model | pareto-26-10 | Rp 14.784 | Rp 59.136 | — | 1.0M | |||
| AI model | pareto-26-10-preview | Rp 14.784 | Rp 59.136 | — | 1.0M | |||
| AI model | pareto-26-9 | Rp 46.200 | Rp 138.600 | — | 262K | |||
| AI model | particle-1 | Rp 1.109 | Rp 9.240 | — | 1.0M |
— = cached tokens bill at the input price
Showing 60 of 498. Every model also has its own page.
About the Anoman AI models directory
The Anoman AI models directory lists every model you can call through one OpenAI-compatible API: 494 models from OpenAI, Anthropic, Google, Mistral, DeepSeek, Alibaba (Qwen) and other makers. Each model page shows the price Anoman charges per 1M input and output tokens (per image for image models), the context window, the route a call takes and the region where the model's provider processes the request.
Use the filters to narrow the list, or browse every model A–Z. Guarded models come from providers that have confirmed they do not train on your data; community models need an account opt-in, and their provider may use data for training. Calls on every model go through Anoman's guardrails by default, and each call's receipt shows what the guardrails did and what the call cost.
Frequently asked questions
Which prices do the model pages show?
The price Anoman charges, in Rupiah per 1M input tokens and per 1M output tokens. Image models are priced per image. Where a model is served at a disclosed quantization, its page says so.
What is the difference between guarded and community models?
Guarded models come from providers that have confirmed they do not train on your data. Community models are opt-in per account, and their provider may use data for training. Each model page shows which lane the model is in.
Which plan can use a model?
Free includes the free models at Rp0 while quota lasts, plus every budget-class model paid from your signup credit or balance. The Budget Pass covers free- and budget-band models, and the Plus Pass adds plus-band models; free models are usable on both passes while quota lasts. Pro covers Budget, Mid and Premium models; Ultra models are Enterprise only. Each model page lists the plans it is usable on.
Where is my request processed?
Anoman's gateway is hosted in Jakarta, but each request is processed by the model's provider in that model's own region. Every model page lists its processing region(s).
How do I call a model?
Use any OpenAI-compatible SDK with the base URL https://api.anoman.io/v1 and your Anoman API key, and pass the model ID shown on the model page.