Build chat, summarization and explanation prototypes with text and bounded document or code excerpts.
- Tool calling
サポートされていますツール呼び出し · サポートされています
- Reasoning
サポートされています推論 · サポートされています
- Vision
サポートされていますビジョン · サポートされています
- Streaming
サポートされていますストリーミング · サポートされています
- JSON mode
サポートされていますJSON モード · サポートされています
USD / 1M tokens
- Input
- $0.00
- Cache read
- $0.00
- Cache write
- —
- Output
- $0.00
- Context
- 256K
- Max output
- 8K
- Price checked
Model availability and prices
Overview
IteraCompute は利用可能な余剰リソースに応じてリクエストを割り当てます。モデル ID には Auto を指定してください。
- 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 endpoint | Model status | Input / output budget | Result | SSE completion |
|---|---|---|---|---|
OpenAI Chat CompletionsPOST /v1/chat/completions | Declared for this model | messagesmax_tokens | choices[0].message.content | [DONE] |
OpenAI ResponsesPOST /v1/responses | Not declared; acceptance pending | inputmax_output_tokens | output[] (SDK: output_text) | response.completed |
Anthropic MessagesPOST /v1/messages | Not declared; acceptance pending | messages; 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.
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.
# 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.
モデルのコンテキスト上限: 262144 tokens
総コンテキストには入力と出力予約分が含まれます。
Free / Starter は合計 131072 トークン、Pro は合計 262144 トークンです。有料プランには各プランの上限が適用されます。
ティア別上限: https://iteracompute.com/ja/free/#auto-tiers
Roo Code の設定例: https://iteracompute.com/ja/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.
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.
| Parameter | Type | Acceptance | Range | Usage / protocol |
|---|---|---|---|---|
| integer | Accepted | [1, 8192] | Output token budget; includes reasoning where applicable. Chat Completions / Messages. | |
| integer | Accepted | [1, 8192] | Alternative Chat output budget; use only when accepted by this model. | |
| integer | Unsupported | [1, 8192] | Responses output budget. Chat acceptance must be checked separately. | |
| number | Accepted | [0, 2] | Sampling randomness. An accepted but ignored value does not control generation. | |
| number | Accepted | (0, 1] | Nucleus sampling probability threshold. | |
| number | Accepted | [-2, 2] | Penalize tokens already present in the generated text. | |
| number | Accepted | [-2, 2] | Penalize repeated tokens according to frequency. | |
| integer | Accepted | [1, 1] | Number of completions; many routes accept only 1. | |
| boolean | Accepted | — | Enable SSE streaming; completion markers depend on the protocol. | |
| array | Accepted | — | Tool definitions; the application executes tool calls and returns results. | |
| any | Accepted | — | Choose whether and which tool to call; allowed shapes vary by protocol. | |
| object | Accepted | — | Text: Chat output format. Images: b64_json only; not text JSON mode. | |
| any | Accepted | — | Reasoning control; object or boolean depends on the model and protocol. | |
| enum | Accepted | ["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
{
"model": "Auto",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
}Parameter revision:0ad2609481be
Technical reference (current configuration takes precedence)
APIパラメータ
パラメーター名をクリックしてコピーします。
Auto[{"role": "user", "content": "Hello!"}]
このルートの追加機能とモデル固有パラメーターは未検証です。本番利用前に必要な機能をテストしてください。
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)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.iteracompute.com/v1",
apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.chat.completions.create({
"model": "Auto",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
});
console.log(response.choices[0].message.content);curl https://api.iteracompute.com/v1/chat/completions \
-H "Authorization: Bearer ITERACOMPUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Auto",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
}'料金
現在の料金と利用可否は以下に表示されます。料金不明は無料を意味しません。
- 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.
料金の出典: 公開 Models API · 価格と精度の根拠は個別に確認します。
キャッシュ読み取り料金は実際のヒットに適用されます。未掲載料金(—)は不明であり、ゼロではありません。アカウントと Gateway のコンテキスト制限は利用制限をご覧ください。
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
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.
ツールを選択
よくある質問
Auto を OpenAI SDK で使用するにはどうすればよいですか?
base_url を https://api.iteracompute.com/v1 に設定し、モデルを Auto に設定します。IteraCompute API キーを使用して認証します。
Autoの価格はいくらですか?
現在の料金と利用可否はリアルタイム料金欄で確認してください。料金がゼロと確認された呼び出しは共有の無料モデル枠を消費し、使い切っても自動的に有料にはなりません。公平利用の制限が適用され、無料容量にSLAはありません。不明または未対応のキャッシュ書き込み料金は別途表示されます。
利用可能なコンテキストの長さはどれくらいですか?
この API のコンテキストと最大出力は上の概要を参照してください。入力と要求した出力でコンテキスト枠を共有します。Free は合計 128K コンテキスト、月 30M tokens です。純チャージ累計 $10 で Starter は月 100M tokens と 128K コンテキスト、$50 で Pro は月 300M tokens と 256K コンテキストを提供します。両チャージティアは待機列で優先されます。全ティアで、アカウント内のすべてのキーと無料ルートを通じ、待機中または生成中のリクエストは 1 件までです。日次トークン上限はありません。最大出力は全ティアで 8,192 tokens です。コンテキストには入力と要求した最大出力が含まれます。共有容量では待機や低速化が発生する場合があります。
最初のリクエストの準備はできましたか?
キーを作成し、ツールを選択すると、空ではない最初の応答が返されます。
既存のチャージ済みユーザーに継続される特典
期限前にチャージを完了したユーザーは、以下の従来のティア特典を引き続き利用できます。11月24日以降の新たなチャージではこれらの特典は付与されません。プラン加入者には各プランに含まれる Auto 利用枠が適用されます。
| 階層 | 期限前のチャージ累計 | 毎月のトークン | コンテキスト | 出力速度 |
|---|---|---|---|---|
| 無料 | $10 未満のチャージ済み | 30M | 128K | 共有容量のため、速度が遅くなる場合があります |
| スターター | 10ドル以上 | 100M | 128K | 共有容量のため、速度が遅くなる場合があります |
| プロ | 50ドル以上 | 300M | 256K | 共有容量のため、速度が遅くなる場合があります |
無料アカウントは、繁忙期にはキューに入れられる場合があります。リチャージされたアカウントはキューの優先順位を受け取ります。容量は共有され、遅延 SLA は提供されません。
毎月の許容量は、アカウント上のすべての API キーにわたる推論を含む入力と出力をカウントします。コンテキストには入力と要求された出力が含まれます。出力の上限は 8,192 トークンです。毎日のノルマはありません。手当は毎月 1 日の 00:00 UTC (北京時間 08:00) にリセットされます。未使用のトークンはロールオーバーされません。リクエストは実行前に最大トークン使用量を予約し、実際の使用量に落ち着きます。超過料金は自動的に支払われません。月ごとの割り当てを使い果たした場合は 429 が返されます。
月間利用枠を使い切った場合は、翌月のリセットをお待ちください。キャンペーン終了後のチャージは引き続き有料 API の利用に充当できますが、共有の無料 Auto 特典の新規付与やアップグレードには適用されません。プランに含まれる Auto 利用枠は別に計算されます。
継続ティアは、期限前に入金が完了した米ドル建てチャージ元本から返金額を差し引いて決まり、支払手数料や特典残高は含みません。ティアが変わっても当月の使用済み量は維持されます。
プランを見る新着モデル
新着モデルに選ばれたモデルの API 料金、対応機能、連携ガイドをご覧ください。
Gemini 4 Hydrogen
gemini/gemini-4-hydrogen
Google Cloud lists Gemini 4 Hydrogen for fast coding assistance, multimodal input and high-volume text generation.
IteraCompute での提供開始日
- 入力
- $1.50
- 出力
- $7.50
USD / 100万トークン
GPT-6.2 Astra
openai/gpt-6.2-astra
OpenAI lists GPT-6.2 Astra for complex engineering and long-horizon reasoning.
IteraCompute での提供開始日
- 入力
- $8.00
- 出力
- $40.00
USD / 100万トークン
GPT-6.2 Sol
openai/gpt-6.2-sol
OpenAI lists GPT-6.2 Sol for everyday coding and agent workflows.
IteraCompute での提供開始日
- 入力
- $2.00
- 出力
- $10.00
USD / 100万トークン