DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash

DeepSeek: DeepSeek V4 Flash 0731 on Sylphx Models · 1.0M of context. One Responses contract, with list prices published per million tokens.

Released: Apr 24, 2026 · 150 days old
Provider: DeepSeek
Context: 1,000,000 tokens

Open in the playground See a request sample Read the docs

Input $0.5544 / MOutput $1.663 / MCached input $0.0882 / MFull rate sheet

Context window1,000,000tokens per request

Max output65,536tokens per response

Input$0.5544 / Mper million tokens

Output$1.663 / Mper million tokens

Requests · 7d3metered on Responses

Avg TPM · 7d<1229 tokens

Pricing

USD per million tokens

Input: $0.5544
Output: $1.663
Cached input: $0.0882

$0.83 for 750,000 input and 250,000 output tokens.

Assumption: one batch of 750,000 input plus 250,000 output tokens at the published list prices — recompute for your own mix. Blended $0.8316 per million at a 3:1 mix.

Chat replies · 3:1 input:output: $0.8316 / M
Long documents · 9:1 input:output: $0.6653 / M
Heavy output · 1:1 input:output: $1.109 / M
Cache write: Not published
Currency and unit: USD / million tokens

Cached input reads cost 84% less than fresh input tokens.

Full rate sheet and billing rules.

Specification

Context window: 1,000,000 tokens
Max output: 65,536 tokens
Input modalities: Not published
Output modalities: Not published
Family: Flash
Version: v4.0
Provider: DeepSeek
Released: Apr 24, 2026 · 150 days old
Model id: deepseek/deepseek-v4-flash

Data posture

Consent-trained

The provider may train on data sent to this model, and Zero Data Retention is not available. Keep regulated or confidential material on a standard-posture model.

Training on what you send: Yes
Zero Data Retention: Not available

Traffic

Daily traffic the platform metered on Responses for this exact model id. Totals are the window they name; a day with no traffic is zero, not missing.

Requests · last 7 days: 3
Tokens · last 7 days: 229
Average TPM · last 7 days: <1
Series total · 14d: 30 req · 65.4K tok

14-day total 30 · peak 14 on Sep 10

Sep 7daily requests, oldest to newestSep 20

Daily numbers for the last 14 days

Daily requests and tokens metered for deepseek/deepseek-v4-flash
Day	Requests	Tokens
2026-09-07	0	0
2026-09-08	1	556
2026-09-09	11	60,965
2026-09-10	14	3,569
2026-09-11	1	101
2026-09-12	0	0
2026-09-13	0	0
2026-09-14	1	115
2026-09-15	0	0
2026-09-16	0	0
2026-09-17	0	0
2026-09-18	0	0
2026-09-19	1	101
2026-09-20	1	13

POST https://api.models.sylphx.ai/v1/responses

curl https://api.models.sylphx.ai/v1/responses \
  -H "Authorization: Bearer $SYLPHX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "input": "Summarise this incident report in three bullets.",
    "stream": false
  }'

How to call it

Send the official Responses document to the base URL above with your organization key and this exact model id. Streaming arrives as ordered events with one terminal event.

Retries: send an Idempotency-Key and a retry replays the original response instead of billing twice.
Errors: typed envelopes tell you whether to retry, wait, or fix the request.
Keys: mint and revoke organization keys from the console.

Quickstart Responses API Errors and retries

Related models

Derived from this catalog: same provider first, then the same family, then the nearest neighbours by input price and context window.

More from DeepSeek

Same provider

Similar price and context

Nearest by input price and context window

Independent evaluation

We do not publish benchmark scores for this model — we have not verified any. These external leaderboards run their own tests, so check them against your own workload.

Not our numbers

3 requests metered on deepseek/deepseek-v4-flash over the last seven daysEvery DeepSeek model →