Pares DeepSeek R1 chain-of-thought raciocínio com a criação Anthropic Claude e geração de código atrás de uma interface unificada, controlada por dados.
WinFuncGeração de TextoLançado Jan 26, 2025Inferência nativaPares DeepSeek R1 chain-of-thought raciocínio com a criação Anthropic Claude e geração de código atrás de uma interface unificada, controlada por dados.
Também conhecido como WinFunc DeepReasoning
deepreasoningPOST /v1/chat/completionsPOST /v1/responsesPOST /v1/messagesLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
DeepReasoning serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id deepreasoning. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepreasoning",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="deepreasoning",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the DeepReasoning API on EmpirioLabs. Defaults apply when a field is omitted.
| Parâmetro | Tipo | Padrão | Intervalo / valores | Descrição |
|---|---|---|---|---|
| temperature | number | 0.7 | 0 to 2 | Sampling temperature. Applies to both the R1 reasoning stage and the Claude synthesis stage. |
| top_p | number | 0.9 | 0 to 1 | Nucleus sampling. Applies to both the R1 reasoning stage and the Claude synthesis stage. |
| max_tokens | number | 8192 | 1 to 65536 | Maximum output tokens for the Claude synthesis stage. |
| anthropic_model | enum | claude-sonnet-4-5-20250929 | claude-sonnet-4-5-20250929, claude-haiku-4-5-20251001, claude... | Choose the Claude model to pair with DeepSeek R1 0528 reasoning. The R1 model produces the chain-of-thought; the Claude model synthesizes the final answer. |
| web_search_linkup | boolean | false | - | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as... |
| disable_formatting | boolean | false | - | When enabled, the gateway will not append the "Sources" footer to assistant responses that used Linkup web search. Useful when the model output is piped to another... |
R1-0528 raciocínio emparelhado com um dos: Claude Sonnet 4.5 (padrão), Haiku 4.5, Opus 4.5, Sonnet 4, Opus 4.1, Opus 4, Sonnet 3.7, Haiku 3.5, Opus 3. Sobre "Inferência Nativa" para este modelo EmpirioLabs hospeda a lógica open-source do projeto API/orchestration da sua recuperação GitHub em nossa própria infraestrutura - essa é a parte "nativa". Os modelos subjacentes (R1-0528 raciocinando + o modelo de conclusão Claude que você escolher) ainda são discados através de suas respectivas APIs oficiais. Nós não hospedamos os pesos do modelo.
On EmpirioLabs, DeepReasoning is billed pay as you go: R1-0528 + Claude Sonnet 4.5 (Padrão) In $0.012 / Out $0.058 por fichas de 1K; R1-0528 + Claude Haiku 4.5 In $0.0048 / Out $0.023 por fichas de 1K; R1-0528 + Claude Opus 4.5 In $0.019 / Out $0.092 por fichas de 1K. The live rate card on this page always matches what the API charges.
Yes. DeepReasoning serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to deepreasoning.
Yes. The EmpirioLabs playground runs DeepReasoning in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
