All models

Auto

Novo Disponível na IteraCompute desde

Disponível

IteraCompute

Auto
Tool calling
SuportadoChamada de ferramenta · Suportado
Reasoning
SuportadoRaciocínio · Suportado
Vision
SuportadoVisão · Suportado
Streaming
SuportadoTransmissão · Suportado
JSON mode
SuportadoModo JSON · Suportado

USD / 1M tokens

Input
$0.00
Cache read
$0.00
Cache write
—
Output
$0.00
Context
256K
Max output
8K
Price checked

Overview

A IteraCompute distribui as solicitações de acordo com a capacidade ociosa disponível. Use Auto como ID do modelo.

Input / output
text, image / text
Endpoint
/v1/chat/completions

API protocols and integration

Base URL · OpenAI SDK
https://api.iteracompute.com/v1
Authentication
Authorization: Bearer ITERACOMPUTE_API_KEY

Choose request fields, response parsing and stream completion by endpoint. This table describes wire formats; see this model's capabilities and verification scope.

Customer endpointModel statusInput / output budgetResultSSE completion
OpenAI Chat Completions
POST /v1/chat/completions
Declared for this modelmessages
max_tokens
choices[0].message.content[DONE]
OpenAI Responses
POST /v1/responses
Not declared; acceptance pendinginput
max_output_tokens
output[] (SDK: output_text)response.completed
Anthropic Messages
POST /v1/messages
Not declared; acceptance pendingmessages; system (top-level)
max_tokens (required)
content[]message_stop

For the Messages SDK use https://api.iteracompute.com as base URL; max_tokens is required. Do not reuse another protocol's fields.

View docs

Tabela de níveis · Exemplo de configuração do Roo Code

LLMs.txt · Copy for an AI coding assistant

Includes this model's ID, wire formats and parameter constraints. Check this page's verification scope and current prices before use.

LLMs.txt
# IteraCompute · Auto

Model ID: Auto
Base URL (OpenAI SDK): https://api.iteracompute.com/v1
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY
Content-Type: application/json

Use only the customer endpoints below. Request and response formats differ by protocol. An endpoint declaration does not certify every capability.

## Chat Completions
POST https://api.iteracompute.com/v1/chat/completions
Input: messages
Output budget: max_tokens
Read result: choices[0].message.content
SSE completion: [DONE]
Docs: https://iteracompute.com/docs.html#api-reference

Auto uses idle server resources and shared free-model allowances. Speed, latency and response quality are not guaranteed. No ZDR guarantee.

## Auto access eligibility
The free promotion ends at 00:00 Pacific Time on November 24, 2026. Users with positive net recharge completed before this cutoff retain their existing free tier. Afterward, shared free Auto is limited to these users and users with a currently effective plan. Later recharges do not grant or upgrade free benefits. Plan Auto tokens and monthly shared free benefits are separate allowances.
No. Purchased Auto tokens and monthly shared free benefits have separate quotas and usage ledgers. Plan Auto uses priority scheduling and its purchased period and contract limits. Requests use plan Auto first; uncovered requests use shared free benefits only while eligible, on shared capacity with possible queues and slower responses. Buying or renewing a plan does not reset shared free usage. When a plan expires, only users with qualifying pre-cutoff recharge retain shared free access.
Recharge eligibility uses positive net principal from orders fulfilled before 2026-11-24T08:00:00Z; later recharges cannot raise the retained free tier. Existing usage and admitted requests are preserved.

Limite de contexto do modelo: 262144 tokens
O contexto total inclui os tokens de entrada e os reservados para a saída.
Free / Starter: 131072 tokens no total. Pro: 262144 tokens no total. Cada plano pago tem seus próprios limites de contexto.
Tabela de níveis: https://iteracompute.com/pt/free/#auto-tiers
Exemplo de configuração do Roo Code: https://iteracompute.com/pt/integrations/roo-code/?model=Auto#roo-fields

## Parameters
Configuration and parameter acceptance do not establish semantic capability. Do not invent undisclosed defaults.
Parameter revision: 0ad2609481be7694d5d65bf409f949909b910d843bdc63357309a2664f705e7c
Maximum output tokens: 8192
Capability tools: configured enabled (see verification scope)
Capability reasoning: configured enabled (see verification scope)
Capability vision: configured enabled (see verification scope)
Capability streaming: configured enabled (see verification scope)
Capability json_mode: configured enabled (see verification scope)
- max_tokens: integer; accepted; min=1; max=8192; default=Undisclosed. Output token budget; includes reasoning where applicable. Chat Completions / Messages.
- max_completion_tokens: integer; accepted; min=1; max=8192; default=Undisclosed. Alternative Chat output budget; use only when accepted by this model.
- max_output_tokens: integer; unsupported; min=1; max=8192; default=not applicable. Responses output budget. Chat acceptance must be checked separately.
- temperature: number; accepted; min=0; max=2; default=Undisclosed. Sampling randomness. An accepted but ignored value does not control generation.
- top_p: number; accepted; min=0 (exclusive); max=1; default=Undisclosed. Nucleus sampling probability threshold.
- presence_penalty: number; accepted; min=-2; max=2; default=Undisclosed. Penalize tokens already present in the generated text.
- frequency_penalty: number; accepted; min=-2; max=2; default=Undisclosed. Penalize repeated tokens according to frequency.
- n: integer; accepted; min=1; max=1; default=Undisclosed. Number of completions; many routes accept only 1.
- stream: boolean; accepted; min=unknown; max=unknown; default=Undisclosed. Enable SSE streaming; completion markers depend on the protocol.
- tools: array; accepted; min=unknown; max=unknown; default=Undisclosed. Tool definitions; the application executes tool calls and returns results.
- tool_choice: any; accepted; min=unknown; max=unknown; default=Undisclosed. Choose whether and which tool to call; allowed shapes vary by protocol.
- response_format: object; accepted; min=unknown; max=unknown; default=Undisclosed. Text: Chat output format. Images: b64_json only; not text JSON mode.
- reasoning: any; accepted; min=unknown; max=unknown; default=Undisclosed. Reasoning control; object or boolean depends on the model and protocol.
- reasoning_effort: enum; accepted; values=["none","low","medium","xhigh"]; default=xhigh. Chat reasoning effort; use the model's listed values, not another protocol's shape.

## Chat Completions example · JSON body
```json
{
  "model": "Auto",
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ],
  "max_tokens": 256,
  "reasoning_effort": "low"
}
```

## References
Model catalog: https://iteracompute.com/models/
Current prices and billing: https://iteracompute.com/pricing/
Documentation index: https://iteracompute.com/llms.txt
Unknown prices are not zero. Account and subscription limits also apply.
Never include a real API key in an LLM prompt or client-side code.

Open plain text

API parameters

  • Model IDs are case-sensitive: use Auto. The version identifies the routing configuration, not model weights.
  • Context includes input and the requested maximum output. The stricter route or account-tier limit applies; see the parameter limits for maximum output.
  • Default thinking requires an output budget of at least 128 tokens; explicitly disabling thinking permits values from 1. The low, medium and xhigh compatibility values enable thinking on the current backend; separate intensity levels have not been established.
  • Input, cache-read and output retail rates are USD 0 per million tokens. An unknown cache-write price is shown as —, not zero.
  • Tools, reasoning output, two-color image recognition, JSON parsing and streaming text/usage/end markers passed on Auto. Future routes require fresh acceptance and human approval.
  • These examples use Chat Completions. Set the output budget with max_tokens or max_completion_tokens; max_output_tokens is not accepted.

These parameters and ranges describe the current route. Account and context limits also apply. Parameter acceptance does not establish model capability.

Tool calling
Supported
Reasoning
Supported
Vision
Supported
Streaming
Supported
JSON mode
Supported

Parameters and values

Click a parameter to copy its name; scroll the table horizontally to see all columns. Usage notes identify protocol differences; identical names do not guarantee cross-endpoint support.

ParameterTypeAcceptanceRangeUsage / protocol
integerAccepted[1, 8192]Output token budget; includes reasoning where applicable. Chat Completions / Messages.
integerAccepted[1, 8192]Alternative Chat output budget; use only when accepted by this model.
integerUnsupported[1, 8192]Responses output budget. Chat acceptance must be checked separately.
numberAccepted[0, 2]Sampling randomness. An accepted but ignored value does not control generation.
numberAccepted(0, 1]Nucleus sampling probability threshold.
numberAccepted[-2, 2]Penalize tokens already present in the generated text.
numberAccepted[-2, 2]Penalize repeated tokens according to frequency.
integerAccepted[1, 1]Number of completions; many routes accept only 1.
booleanAccepted—Enable SSE streaming; completion markers depend on the protocol.
arrayAccepted—Tool definitions; the application executes tool calls and returns results.
anyAccepted—Choose whether and which tool to call; allowed shapes vary by protocol.
objectAccepted—Text: Chat output format. Images: b64_json only; not text JSON mode.
anyAccepted—Reasoning control; object or boolean depends on the model and protocol.
enumAccepted["none","low","medium","xhigh"]Chat reasoning effort; use the model's listed values, not another protocol's shape.

Current configuration example

POST /v1/chat/completions

Chat Completions request
{
  "model": "Auto",
  "messages": [
    {
      "role": "user",
      "content": "Reply OK"
    }
  ],
  "max_tokens": 256,
  "reasoning_effort": "low"
}

Parameter revision:0ad2609481be

Technical reference (current configuration takes precedence)

Parâmetros de API

Clique em um parâmetro para copiar seu nome.

Auto
[{"role": "user", "content": "Hello!"}]

As capacidades adicionais e os parâmetros específicos do modelo não foram verificados nesta rota. Teste os recursos necessários antes do uso em produção.

API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="Auto",
    messages=[
      {
        "role": "user",
        "content": "Reply OK"
      }
    ],
    max_tokens=256,
    reasoning_effort="low",
)
print(response.choices[0].message.content)

Preços

Os preços e a disponibilidade atuais são exibidos abaixo. Preços ausentes não significam gratuidade.

Input$0.00
Cache read$0.00
Cache write—
Output$0.00
Model ID
Auto
Context
256K
Price checked
Verification scope and sources
View verification scope and sources

2026-11-10 · Auto passed bounded real-model tests for text, tool calls, observable reasoning, two-color image recognition, JSON and streaming. Full-context quality, long-run performance and arbitrary-task accuracy were not evaluated.

Fonte do preço: API pública de modelos · Os preços e a precisão são verificados separadamente.

As tarifas de leitura de cache se aplicam a acertos reais. Uma tarifa ausente (—) é desconhecida, não zero. Consulte os limites de uso para restrições de contexto da conta e do Gateway.

Usage limits

  • Free capacity is shared and may queue during busy periods. Speed, latency, output quality and availability have no SLA.
  • The underlying model may change with resource availability. Evaluate paid models separately for tasks that require consistent quality or performance.
  • Account allowances, concurrency and context restrictions apply together. Changing API keys or model IDs does not add allowance, and exhausted free quota does not become a paid request automatically.
  • Capability checks cover controlled tool, reasoning, color-recognition and JSON cases. They do not establish reliability for arbitrary tasks or full-context inputs.
  • The free service does not promise zero data retention. Follow the data policy and avoid submitting data unsuitable for this service.

Use cases

Build chat, summarization and explanation prototypes with text and bounded document or code excerpts.

Connect structured tool calls, JSON replies and image questions using the verified common capabilities of the current pool.

Integrate standard SDKs and streaming responses, and evaluate application behavior with shared free capacity.

Escolha sua ferramenta

Escolha um modelo e ferramenta para sua tarefaSubsídio e limites gratuitos

Perguntas frequentes

Como uso o Auto com o OpenAI SDK?

Defina base_url como https://api.iteracompute.com/v1 e modele como Auto.Autentique com sua chave de API IteraCompute.

Quanto custa Auto?

Consulte a seção de preços em tempo real para ver as tarifas e a disponibilidade atuais. Chamadas com tarifa zero confirmada usam a cota compartilhada de modelos gratuitos; esgotá-la não transforma automaticamente as solicitações em chamadas pagas. Aplicam-se limites de uso justo, sem SLA para a capacidade gratuita. Preços desconhecidos ou não suportados de gravação em cache são exibidos separadamente.

Qual comprimento de contexto está disponível?

Consulte o resumo acima para ver o contexto e a saída máxima desta API. A entrada e a saída solicitada compartilham o orçamento de contexto. Free: contexto total de 128K e 30M tokens/mês. Após $10 de recarga líquida acumulada, Starter oferece 100M tokens/mês e contexto de 128K; após $50, Pro oferece 300M tokens/mês e contexto de 256K. Ambos os níveis com recarga têm prioridade na fila. Os três níveis permitem uma solicitação na fila ou em geração por conta entre todas as chaves e rotas gratuitas, sem limite de tokens diários. A saída máxima é de 8,192 tokens em todos os níveis; o contexto inclui a entrada e a saída máxima solicitada. A capacidade compartilhada pode causar espera ou lentidão.

Pronto para sua primeira solicitação?

Crie sua chave, escolha uma ferramenta e obtenha uma primeira resposta não vazia.

Benefícios mantidos para usuários que já recarregaram

Quem concluiu uma recarga antes do prazo mantém os benefícios do seu nível indicados abaixo. A partir de 24 de novembro, novas recargas não concedem esses benefícios. Assinantes recebem a cota de Auto incluída no plano.

NívelRecarga anterior ao prazoTokens mensaisContextoVelocidade de saída
GrátisRecarga inferior a $1030M128KCapacidade compartilhada; pode ser lenta
InicianteUS$ 10 ou mais100M128KCapacidade compartilhada; pode ser lenta
PróUS$ 50 ou mais300M256KCapacidade compartilhada; pode ser lenta

Contas gratuitas podem entrar na fila durante períodos de maior movimento.Contas recarregadas recebem prioridade na fila;a capacidade é compartilhada e nenhum SLA de latência é oferecido.

As cotas mensais contam entradas e saídas, incluindo raciocínio, em todas as chaves de API da sua conta.O contexto inclui entrada e saída solicitada;a produção é limitada a 8.192 tokens.Não há cota diária.As licenças são redefinidas no primeiro dia de cada mês às 00:00 UTC (08:00 horário de Pequim);tokens não utilizados não são acumulados.As solicitações reservam seu uso máximo de token antes de serem executadas e depois se contentam com o uso real.Sem excesso pago automaticamente: cota mensal esgotada retorna 429.

Quando sua cota mensal acabar, aguarde a renovação no mês seguinte. Após o fim da promoção, as recargas continuam disponíveis para uso pago da API, mas deixam de conceder ou ampliar os benefícios compartilhados do Auto gratuito. A cota do Auto incluída no seu plano é contabilizada separadamente.

Os níveis mantidos usam o principal em USD de recargas creditadas antes do prazo, menos reembolsos e sem taxas ou créditos promocionais. Mudanças de nível preservam o uso já consumido no mês.

Leia as perguntas frequentes sobre o Auto antes de recarregar.

Ver planos

Novos modelos

Explore os modelos selecionados como novidades, com preços de API, recursos compatíveis e guias de integração.

Ver novos modelos
GoogleNovo

Gemini 4 Hydrogen

gemini/gemini-4-hydrogen

Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.

Disponível na IteraCompute desde

Entrada
$1.50
Saída
$7.50

USD / 1 milhão de tokens

OpenAINovo

GPT-6.2 Astra

openai/gpt-6.2-astra

OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.

Disponível na IteraCompute desde

Entrada
$8.00
Saída
$40.00

USD / 1 milhão de tokens

OpenAINovo

GPT-6.2 Sol

openai/gpt-6.2-sol

OpenAI lists GPT-6.2 Sol for everyday coding and agent workflows.

Disponível na IteraCompute desde

Entrada
$2.00
Saída
$10.00

USD / 1 milhão de tokens