Qwen4-Max
qwen/qwen4-max
Qwen4-Max through Alibaba Cloud Model Studio, with text, reasoning, tools and image input.
Disponível na IteraCompute desde
- Entrada
- $1.50
- Saída
- $4.50
USD / 1 milhão de tokens
Novo Disponível na IteraCompute desde
deepseek/deepseek-v4.1-flash-1017Tokens USD/1 milhão
Catálogo atualizado: 2026-10-29.
Versão de 17 de outubro para código, texto e compreensão de imagens: contexto declarado de 1M e saída máxima de 384K. Escolha a intensidade low/high/max ou desative o raciocínio. Suporta JSON, streaming e chamadas de ferramentas.
https://api.iteracompute.com/v1Authorization: Bearer ITERACOMPUTE_API_KEYChoose 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 | Declared for this model | inputmax_output_tokens | output[] (SDK: output_text) | response.completed |
Anthropic MessagesPOST /v1/messages | Declared for this model | 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.
Includes this model's ID, wire formats and parameter constraints. Check this page's verification scope and current prices before use.
# IteraCompute · deepseek/deepseek-v4.1-flash-1017
Model ID: deepseek/deepseek-v4.1-flash-1017
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
## Responses
POST https://api.iteracompute.com/v1/responses
Input: input
Output budget: max_output_tokens
Read result: output[] (SDK: output_text)
SSE completion: response.completed
Docs: https://iteracompute.com/docs.html#responses-api
## Messages
POST https://api.iteracompute.com/v1/messages
Input: messages; system (top-level)
Output budget: max_tokens (required)
Read result: content[]
SSE completion: message_stop
Docs: https://iteracompute.com/docs.html#anthropic-messages
## Parameters
Configuration and parameter acceptance do not establish semantic capability. Do not invent undisclosed defaults.
Current parameter configuration is unconfirmed. Check the model page and current catalog before calling.
## 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.
V4, V4.1 e versões datadas têm regras diferentes para raciocínio e imagens. Respeite a versão e os limites publicados; compartilhar um protocolo não implica aceitar controles novos.
Use os parâmetros e as evidências publicados para este modelo específico. A revisão da documentação do fornecedor não certifica todos os recursos no gateway.
These parameters and ranges come from the model’s existing default configuration, not live verification of the current route. Published configuration takes precedence.
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 | Reference: supported | [1, 390000] | Output token budget; includes reasoning where applicable. Chat Completions / Messages. | |
| integer | Reference: supported | [1, 390000] | Alternative Chat output budget; use only when accepted by this model. | |
| integer | Reference: supported | [1, 390000] | Responses output budget. Chat acceptance must be checked separately. | |
| number | Reference: supported | [0, 2] | Sampling randomness. An accepted but ignored value does not control generation. | |
| number | Reference: supported | [0, 1] | Nucleus sampling probability threshold. | |
| number | Reference: supported | [-2, 2] | Penalize tokens already present in the generated text. | |
| number | Reference: supported | [-2, 2] | Penalize repeated tokens according to frequency. | |
| integer | Reference: supported | [1, 1] | Number of completions; many routes accept only 1. | |
| boolean | Reference: supported | — | Enable SSE streaming; completion markers depend on the protocol. | |
| array | Reference: supported | — | Tool definitions; the application executes tool calls and returns results. | |
| any | Reference: supported | — | Choose whether and which tool to call; allowed shapes vary by protocol. | |
| object | Reference: supported | — | Text: Chat output format. Images: b64_json only; not text JSON mode. | |
| any | Reference: supported | — | Reasoning control; object or boolean depends on the model and protocol. | |
| enum | Reference: supported | ["none","low","high","max"] | Chat reasoning effort; use the model's listed values, not another protocol's shape. |
POST /v1/chat/completions
{
"model": "deepseek/deepseek-v4.1-flash-1017",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
}Parameter revision:c2c8cf2eab6a
Clique em um parâmetro para copiar seu nome.
| Parâmetros | Uso |
|---|---|
text + image → text | |
| 384K | |
| Omita temperature e as penalidades no modo de raciocínio; elas não controlam sua intensidade. Comece com a amostragem padrão. | |
| Selecione low, high ou max em reasoning_effort; o padrão é high. Use reasoning_effort=none ou reasoning=false para desativar o raciocínio. Os aliases minimal, medium/xhigh e ultra correspondem a low, high e max. Não combine controles conflitantes. Na Responses API, use reasoning={"effort":"none/low/high/max"}. | |
| Defina funções em tools, execute tool_calls e retorne role=tool com o tool_call_id correspondente. Preserve a mensagem assistant completa, incluindo reasoning_content quando presente, durante as chamadas de ferramentas. | |
| Use response_format={"type":"json_object"} e solicite JSON no prompt. Valide o JSON retornado. | |
stream=true, stream_options={"include_usage":true} |
A entrada e a saída solicitada compartilham o limite de contexto. Os tokens de raciocínio contam no uso de saída.
{
"model": "deepseek/deepseek-v4.1-flash-1017",
"messages": [
{
"role": "user",
"content": "What is 17 times 19? Reply only with the integer."
}
],
"max_tokens": 1024,
"reasoning_effort": "high",
"stream": true,
"stream_options": {
"include_usage": true
}
}from openai import OpenAI
client = OpenAI(
api_key="ITERACOMPUTE_API_KEY",
base_url="https://api.iteracompute.com/v1",
)
stream = client.chat.completions.create(
model='deepseek/deepseek-v4.1-flash-1017',
messages=[{'role': 'user',
'content': 'What is 17 times 19? Reply only with the integer.'}],
max_tokens=1024,
reasoning_effort='high',
stream=True,
stream_options={'include_usage': True},
)
for chunk in stream:
print(chunk.model_dump_json(exclude_none=True))
extra_body do SDK mescla seus campos no corpo HTTP. Se o corpo original contiver um objeto extra_body, preserve-o como extra_body aninhado no exemplo do SDK.
| Parâmetros | Uso |
|---|---|
| Chat: use um objeto image_url com url e detail opcional dentro. | |
| Responses: use type=input_image, image_url como texto e detail no mesmo nível. | |
| Use URL pública HTTP(S) ou dados base64 de JPEG, PNG, GIF ou WebP. Substitua a URL de exemplo. low reduz para 512×512; high/original/auto mantêm a imagem original. | |
| Este Gateway não documenta suporte à Files API. Use URL de imagem ou base64. |
Documentação de visão do DeepSeek · 2026-10-26
POST /v1/chat/completions
{
"model": "deepseek/deepseek-v4.1-flash-1017",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Read the text in this screenshot."
},
{
"type": "image_url",
"image_url": {
"url": "https://example.com/screenshot.png",
"detail": "original"
}
}
]
}
],
"max_tokens": 1024,
"reasoning_effort": "low"
}POST /v1/responses
{
"model": "deepseek/deepseek-v4.1-flash-1017",
"input": [
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read the text in this screenshot."
},
{
"type": "input_image",
"image_url": "https://example.com/screenshot.png",
"detail": "original"
}
]
}
],
"max_output_tokens": 1024,
"reasoning": {
"effort": "low"
}
}Referência da interface verificada: 2026-10-23
| Parâmetros | Uso |
|---|---|
| Chat usa max_tokens ou max_completion_tokens; Responses usa max_output_tokens. Use inteiros positivos dentro dos limites do Gateway. | |
| O modo de raciocínio ignora temperature e penalidades. Preserve reasoning_content nas ferramentas. Diferencie esta rota fixa do alias oficial mais recente. |
2026-10-26
Current parameter configuration is unconfirmed; the historical example below has not been verified against the current configuration.
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='deepseek/deepseek-v4.1-flash-1017',
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": "deepseek/deepseek-v4.1-flash-1017",
"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": "deepseek/deepseek-v4.1-flash-1017",
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"max_tokens": 256,
"reasoning_effort": "low"
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.iteracompute.com/v1",
api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.responses.create(
model='deepseek/deepseek-v4.1-flash-1017',
input='Reply OK',
max_output_tokens=256,
reasoning={'effort': 'low'},
)
print(response.output_text)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.iteracompute.com/v1",
apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.responses.create({
"model": "deepseek/deepseek-v4.1-flash-1017",
"input": "Reply OK",
"max_output_tokens": 256,
"reasoning": {
"effort": "low"
}
});
console.log(response.output_text);curl https://api.iteracompute.com/v1/responses \
-H "Authorization: Bearer ITERACOMPUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4.1-flash-1017",
"input": "Reply OK",
"max_output_tokens": 256,
"reasoning": {
"effort": "low"
}
}'import os
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.iteracompute.com",
api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.messages.create(
model='deepseek/deepseek-v4.1-flash-1017',
max_tokens=256,
messages=[{'role': 'user', 'content': 'Reply OK'}],
output_config={'effort': 'low'},
)
print("".join(block.text for block in response.content if block.type == "text"))import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: "https://api.iteracompute.com",
apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.messages.create({
"model": "deepseek/deepseek-v4.1-flash-1017",
"max_tokens": 256,
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"output_config": {
"effort": "low"
}
});
console.log(response.content.filter(block => block.type === "text").map(block => block.text).join(""));curl https://api.iteracompute.com/v1/messages \
-H "x-api-key: ITERACOMPUTE_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4.1-flash-1017",
"max_tokens": 256,
"messages": [
{
"role": "user",
"content": "Reply OK"
}
],
"output_config": {
"effort": "low"
}
}'Os preços e a disponibilidade atuais são exibidos abaixo. Preços ausentes não significam gratuidade.
deepseek/deepseek-v4.1-flash-1017Revisão do backend: não divulgadaUse os parâmetros e as evidências publicados para este modelo específico. A revisão da documentação do fornecedor não certifica todos os recursos no gateway.
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.
A entrada inclui leituras e gravações de cache sem sobreposição. A saída já inclui raciocínio; informe-o como subconjunto, sem somar duas vezes. Conte etapas do agente e novas tentativas como requisições.
Custo mensal
—USDDeepSeek V4.1 Flash 1017
Sem garantia de cache ou capacidade.
Use para pequenas alterações de código, extração de dados de documentos e fluxos limitados de ferramentas. Revise os patches e valide o JSON na aplicação.
Defina base_url como https://api.iteracompute.com/v1 e modele como deepseek/deepseek-v4.1-flash-1017.Autentique com sua chave de API IteraCompute.
Consulte a seção de preços para taxas atuais de entrada, entrada em cache e saída em dólares americanos por 1 milhão de tokens.Verifique o tempo de atualização antes de usar.
Consulte o resumo acima para ver o contexto e a saída máxima desta API. A entrada e a saída solicitada compartilham o limite de contexto.
Crie sua chave, escolha uma ferramenta e obtenha uma primeira resposta não vazia.
Explore os modelos selecionados como novidades, com preços de API, recursos compatíveis e guias de integração.
qwen/qwen4-max
Qwen4-Max through Alibaba Cloud Model Studio, with text, reasoning, tools and image input.
Disponível na IteraCompute desde
USD / 1 milhão de tokens
openai/gpt-6.1-terra
OpenAI text and visual reasoning model for applications, coding and document workflows.
Disponível na IteraCompute desde
USD / 1 milhão de tokens
gemini/gemini-nano-banana-2.1
Generate images from text and edit reference images through one image API, with native image and reasoning usage.
Disponível na IteraCompute desde