Providers and ModelsWinFunc

DeepReasoning

DeepReasoning
WinFunc · Text Generation
POST /v1/chat/completions

Pairs DeepSeek R1 chain-of-thought reasoning with Anthropic Claude creative and code generation behind a unified, data-controlled interface.

At a glance

FieldValue
Model iddeepreasoning
Input modalitiesText
Output modalitiesText
Context window-
Weight precision-
Max output tokens32,000
Featuresreasoning, thinking
Native inferenceYes
NewNo
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages

Pricing

ChargeSpecRate
R1-0528 + Claude Sonnet 4.5 (Default)per 1K tokensIn $0.012 / Out $0.058
R1-0528 + Claude Haiku 4.5per 1K tokensIn $0.0048 / Out $0.023
R1-0528 + Claude Opus 4.5per 1K tokensIn $0.019 / Out $0.092
R1-0528 + Claude Sonnet 4per 1K tokensIn $0.012 / Out $0.058
R1-0528 + Claude Opus 4.1per 1K tokensIn $0.053 / Out $0.26
R1-0528 + Claude Opus 4per 1K tokensIn $0.053 / Out $0.26
Web Search (Linkup)per call when invoked$0.013

Example request

$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":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.7Sampling temperature. Applies to both the R1 reasoning stage and the Claude synthesis stage. · Range: 0 – 2
top_pnumberno0.9Nucleus sampling. Applies to both the R1 reasoning stage and the Claude synthesis stage. · Range: 0 – 1
max_tokensnumberno8192Maximum output tokens for the Claude synthesis stage. · Range: 1 – 65536
anthropic_modelenumno"claude-sonnet-4-5-20250929"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. · Allowed: claude-sonnet-4-5-20250929, claude-haiku-4-5-20251001, claude-opus-4-5-20251101, claude-opus-4-1-20250805, claude-opus-4-20250514, claude-sonnet-4-20250514
web_search_linkupbooleannofalseOptional 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 additional context. Adds a flat $0.013 per request on top of the model’s normal token cost. Disabled by default.
disable_formattingbooleannofalseWhen 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 system that expects no decoration.

Notes

R1-0528 reasoning paired with one of: Claude Sonnet 4.5 (default), Haiku 4.5, Opus 4.5, Sonnet 4, Opus 4.1, Opus 4, Sonnet 3.7, Haiku 3.5, Opus 3.

About “Native Inference” for this model

EmpirioLabs hosts the project’s open-source API/orchestration logic from its GitHub repo on our own infrastructure — that’s the “native” part. The underlying models (R1-0528 reasoning + the Claude completion model you pick) are still dialed via their respective official APIs. We don’t host the model weights themselves.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/deepreasoning.