SylphxModels

DeepSeek

Flash family

Deepseek Flash

New
deepseek/deepseek-flash

deepseek/deepseek-flash on Sylphx Models · 1.0M of context. One Responses contract, with list prices published per million tokens.

Released
Sep 10, 2026 · 11 days old
Provider
DeepSeek
Context
1,000,000 tokens
Open in the playgroundSee a request sampleRead the docs
Input $0.18 / MOutput $0.72 / MCached input $0.018 / MFull rate sheet
Context window1,000,000tokens per request
Max outputNot publishedtokens per response
Input$0.18 / Mper million tokens
Output$0.72 / Mper million tokens
Requests · 7d838metered on Responses
Avg TPM · 7d12.3K123.9M tokens

Pricing

USD per million tokens
Input
$0.18
Output
$0.72
Cached input
$0.018

$0.32 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 $0.315 per million at a 3:1 mix.

Chat replies · 3:1 input:output
$0.315 / M
Long documents · 9:1 input:output
$0.234 / M
Heavy output · 1:1 input:output
$0.45 / M
Cache write
Not published
Currency and unit
USD / million tokens

Cached input reads cost 90% less than fresh input tokens.

Full rate sheet and billing rules.

Specification

Context window
1,000,000 tokens
Max output
Not published
Input modalities
Not published
Output modalities
Not published
Family
Flash
Version
Not published
Provider
DeepSeek
Released
Sep 10, 2026 · 11 days old
Model id
deepseek/deepseek-flash

Data posture

Standard

Prompts and outputs sent to this model are not used to train models.

Training on what you send
No
Zero Data Retention
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
838
Tokens · last 7 days
123.9M
Average TPM · last 7 days
12.3K
Series total · 14d
838 req · 123.9M tok

14-day total 838 · peak 835 on Sep 21

Sep 8Sep 21
Daily numbers for the last 14 days
Daily requests and tokens metered for deepseek/deepseek-flash
DayRequestsTokens
2026-09-0800
2026-09-0900
2026-09-1000
2026-09-1100
2026-09-1200
2026-09-1300
2026-09-1400
2026-09-1500
2026-09-1600
2026-09-1700
2026-09-1800
2026-09-1900
2026-09-203138
2026-09-21835123,928,805
curl https://api.models.sylphx.ai/v1/responses \
  -H "Authorization: Bearer $SYLPHX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-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.
QuickstartResponses APIErrors 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
838 requests metered on deepseek/deepseek-flash over the last seven daysEvery DeepSeek model →