DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash on our own GPUs: chat with tool calls and visible reasoning, prompt caching, priced per token.

DeepSeek V4.1 Flash 1017 runs on our own pair of B200 GPUs.

Good for chat, function calling (tools), working over long documents and reasoning-heavy answers; repeated prompt prefixes are cached and billed at the cached rate.

Inputs: messages in the native chat format, max_tokens, and optional tools. The answer is the complete native response with its choices, tool calls, reasoning and token usage.

One request body is limited to 262,144 bytes, which sets the practical prompt size through our API (our live check used a 47,182-token prompt); the model's own 1,048,576-token window is not reachable through the API today.

The first request after a quiet period waits for the GPUs to start, which can take about half an hour; requests are served one at a time. There is no streaming and no image or search input.

Price: $0.30 per 1M input tokens, $1.20 per 1M output tokens (reasoning tokens count as output), $0.008 per 1M cached input tokens.

Price: $0.30 per 1M input tokens, $1.20 per 1M output tokens, cached input $0.008 per 1M.

Run DeepSeek V4.1 Flash 1017 via API

DeepSeek V4.1 Flash 1017 is a native model: it runs through the native operations API, not the predict route. Read the current contract revision, create one operation under your own Idempotency-Key, then read that operation until it finishes. The account of the API key pays.

The input is the conversation in the native chat format and the most tokens the model may write; function tools are optional. The answer is one complete response, without streaming.

API="https://backend.flymy.ai/api/v1"
# The model's current contract revision.
REVISION=$(curl -s "$API/model-proxy/catalog/?endpoint_id=flymyai/deepseek-v4-1-flash-1017" \
  -H "X-API-KEY: $FLYMYAI_API_KEY" | jq -r '.items[0].contract_revision')
jq -n --arg revision "$REVISION" \
  '{contract_revision: $revision, inputs: {messages: [{role: "user", content: "What is a vector database?"}], max_tokens: 512}}' > request.json
# One key per request. After a lost response send the same key again: the model never runs twice.
OPERATION_KEY=$(uuidgen)
OPERATION_ID=$(curl -s "$API/model-proxy/operations/" \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -H "Idempotency-Key: $OPERATION_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @request.json | jq -r '.operation.operation_id')
# Read it until its status is succeeded or failed. Waiting for capacity is not an error: do not send it again.
curl -s "$API/model-proxy/operations/$OPERATION_ID/" -H "X-API-KEY: $FLYMYAI_API_KEY"

The example needs curl and jq. Native model API guide

API documentation · Create a free account · Pricing

Related models