Model selection

By default every call runs on the model Anona serves as standard. You can name a different one (per request, in the dashboard, or as a default for a space), and credits are charged at that model’s own rate rather than a flat tier.

Not to be confused with memory models, which are standing answers a space keeps current. This page is about the LLM that does the work.

Every model is available on every plan

There is no plan gate. A Developer account can select the most expensive model in the catalog, and a Scale account pays the same rate for it. That works because credits are derived from each model’s real per-token cost. A credit balance is therefore a spend cap, and the choice of model cannot move it. It only changes how fast the balance goes down. The same 5,000 credits buy roughly 58M tokens of nova-micro or 2.5M tokens of nova-pro, and cost us the same either way. The practical limit is throughput, not entitlement: request-per-minute quotas are per model, and the premium models carry the least headroom. See requests_per_minute in the table below.

The default

Omit model and you get us.amazon.nova-pro-v1:0, also reachable as the tier name balanced. It is what every call ran on before model selection existed, and its credit rate is unchanged, so leaving the field alone changes nothing about either your results or your bill.

Pick one, and copy the call

Three ways to name a model

A short name, like nova-pro, deepseek or glm, is what you will use most. One per model, and pinned to that model permanently: a short name is never re-pointed at something else. A tier name, like fast or balanced, names an intent rather than a model, and Anona keeps it pointed at a sensible choice as the landscape changes. That re-pointing is the value: ask for fast and you keep getting whatever “fast” should mean. A full model id, like us.amazon.nova-pro-v1:0, also works, and always has. Nothing that already sends one needs to change. GET /v1/models returns the full id for every model, along with its exact credit rates.

The difference between the first two matters. A short name is stable; a tier name may move. If you have measured a model and want that exact behaviour to stay put, name it: nova-pro, not balanced.

{ "space_id": "support", "query": "what does this customer keep asking for?", "model": "nova-lite" }

These all name the same model, and any of them is accepted anywhere model is:

{ "model": "nova-pro" }
{ "model": "balanced" }
{ "model": "us.amazon.nova-pro-v1:0" }

The first two agree today. balanced is an intent that may be re-pointed later; nova-pro is that model permanently.

Using it from the API

Resolution runs request → space default → platform default, so a request always wins over a stored setting.

POST /v1/reason
Authorization: Bearer anona_live_xxx

{ "space_id": "support", "query": "...", "model": "balanced" }

POST /v1/chat/completions
Authorization: Bearer anona_live_xxx

{ "space_id": "support", "model": "fast", "messages": [{ "role": "user", "content": "..." }] }

PUT /v1/spaces/support/reason-settings
{ "model": "fast" }

PUT /v1/spaces/support/chat-settings
{ "chat_model": "fast" }

Because the proxy is drop-in, a stock OpenAI SDK can set it once and forget it:

from openai import OpenAI

client = OpenAI(
    api_key="anona_live_xxx",
    base_url="https://api.anonalabs.com/v1",
    default_headers={"X-Anona-Space-Id": "support"},
)

resp = client.chat.completions.create(
    model="fast",                      # a tier name or a model id
    messages=[{"role": "user", "content": "What did we decide about pricing?"}],
)

A space default is stored as a resolved model id, even when you send a tier name. If fast is later re-pointed at a different model, spaces that already chose it stay where they are. You picked a behaviour, not a subscription to ours. GET /v1/spaces/{space_id}/reason-settings reads the current value; sending {"model": null}, or DELETE, returns the space to the platform default.

PUT /v1/spaces/{id}/chat-settings replaces the whole record, so a field you omit is cleared, not kept. The reason model is a separate resource for exactly this reason, so saving chat defaults never disturbs it.

Using it from the dashboard

Open a space, then the chat defaults tab. Two rows set the model:

Row	What it changes
Chat model	The LLM that answers proxied chat calls (`/v1/chat/completions`, `/v1/responses`, `/v1/messages`) for this space.
Reason model	The LLM that answers `/v1/reason` for this space.

Each row has an override toggle. Left off, the row is inherited: the space follows the platform default, and it keeps following it if that default ever moves. Turn the toggle on and the picker appears, listing every model with its credit rate per 1K tokens so the cost of the choice is visible at the moment you make it. These write the same reason-settings and chat-settings resources the API uses, so a value set here is the value a request sees, and vice versa.

List what you can use

GET /v1/models
Authorization: Bearer anona_live_xxx

{
  "object": "list",
  "data": [
    {
      "id": "us.amazon.nova-lite-v1:0",
      "object": "model",
      "created": 0,
      "owned_by": "anona",
      "short_name": "nova-lite",
      "display_name": "Nova Lite",
      "alias": "fast",
      "default": false,
      "credits_per_1k_input": 0.147,
      "credits_per_1k_output": 0.588,
      "requests_per_minute": 400,
      "relative_cost": 0.07
    }
  ]
}

The envelope is the standard OpenAI list shape, so client.models.list() works unchanged against the proxy. Entries come back cheapest first, ordered by relative_cost. The names, alias, default, the credit rates, requests_per_minute, and relative_cost are Anona’s additions; an SDK that does not know about them ignores them. short_name always names this exact model and never moves; alias names a tier and may be re-pointed. default marks the model you get by omitting the model field. At most one entry carries it, and sometimes none, when this deployment serves a model outside the catalog.

What it costs

Credit rates are derived from each model’s real per-token price, so a model that costs five times more charges roughly five times the credits, with no rounding into tiers. Cost vs default compares against nova-pro, blended 10:1 input:output. It is a shopping aid, not a billing figure: a model’s in/out ratio is its own. Llama 70B charges the same for both, Nova Pro charges 4x more for output, so cost a real workload from the exact credit rates on GET /v1/models, not from the multiplier.

Model	Use in `model`	Tier	Cost vs default
Nova Micro	`nova-micro`	-	0.04x
Nova Lite	`nova-lite`	`fast`	0.07x
GPT-OSS 120B	`gpt-oss`	-	0.19x
Llama 70B	`llama-70b`	-	0.71x
DeepSeek	`deepseek`	-	0.72x
GLM	`glm`	-	0.73x
Nova Pro	`nova-pro`	`balanced`	1x, the default

GET /v1/models is the authoritative list; this table is a snapshot. Reason also carries a flat base of 5 credits, so a short answer on a cheap model costs 5 rather than fractions of one.

A worked example. A reason call reading 4,000 tokens of context and writing 400 on the default costs 5 + (4 × 1.96) + (0.4 × 7.84) ≈ 16 credits. The same call on nova-micro costs 5 + (4 × 0.09) + (0.4 × 0.34) ≈ 5.5 credits, and at that end of the catalog the flat base is most of the bill, not the tokens.

Which model answered

Reason echoes it back, so you can reconcile an answer and its cost against the model that actually produced them rather than the one you asked for:

{
  "insights": "...",
  "model": "us.amazon.nova-lite-v1:0",
  "usage": { "input_tokens": 4120, "output_tokens": 380 }
}

Errors

Anona never quietly substitutes a different model. If the one you named cannot serve the request, the request fails and says so.

Code	Status	Meaning
`unsupported_model`	400	Not a model this deployment serves. The message lists what is.
`model_throttled`	429	That model is at capacity right now. Retry, or use one with more headroom (see `requests_per_minute`).
`model_unavailable`	503	The model is listed but this deployment cannot reach it. Ours to fix.

Request limits are per model, which is also a reason to choose one: the high-throughput models carry twenty times the headroom of the premium ones.

Choosing well

Leave it alone unless you have a reason. The default is the balanced option.
fast for high-volume, low-stakes work: classification, short recall summaries, anything where you would rather have ten answers than one better one.
A premium model for reason over a large space, where the synthesis is the product and a better one is worth several times the credits.
Watch the credit burn, not the plan. Nothing stops a Developer account running any model in the catalog; the dearest simply exhausts the month’s credits about 22 times sooner than nova-micro would.
Measure before pinning an id. Reason is a multi-step agent loop, so a slower model costs more wall time than its per-call latency suggests.

Getting Started

API Essentials

Memory (data plane)

LLM Proxy (drop-in)

Account (control plane)

SDKs & MCP

Integrations

Guides

Changelog

Every model is available on every plan

The default

Pick one, and copy the call

Three ways to name a model

Using it from the API

Using it from the dashboard

List what you can use

What it costs

Which model answered

Errors

Choosing well

​Every model is available on every plan

​The default

​Pick one, and copy the call

​Three ways to name a model

​Using it from the API

​Using it from the dashboard

​List what you can use

​What it costs

​Which model answered

​Errors

​Choosing well

Every model is available on every plan

The default

Pick one, and copy the call

Three ways to name a model

Using it from the API

Using it from the dashboard

List what you can use

What it costs

Which model answered

Errors

Choosing well