DeepSeek Flash
DeepSeek's fast line — vision, a 1M context, and prices at cents.
DeepSeek Flash is the fast line of DeepSeek's pair: vision supported, thinking on by default, a 1M-token context and a 384K output window. Off-peak input (cache miss) is $0.15 per MTok, peak $0.30; output $0.60 off-peak, $1.20 peak.
What it is good at
- Agentic coding at cents per MTok
- Vision input and a 384K output window
- Off-peak hours halve the price — weekdays outside 01:00–04:00 and 06:00–10:00 UTC
What it is less good at
- No benchmarks published by DeepSeek
- Peak-hour pricing doubles; the headline prices are cache-miss input
Reaching it with TeamCLI
TeamCLI runs DeepSeek Flash as DeepSeek V4.1 Flash:
Ways to reach it
| Route | Spends | Status |
|---|---|---|
| Claude Code with a provider endpoint | A DeepSeek API key. | Verified |
| The API directly | DeepSeek's API billing. | Listed — not yet verified |
The seat line
Each route maps to a TeamCLI seat line — the same fields, written generically. No machine paths, no launcher script of anybody's, no team's own seat names.
| Route | cli | vendor | model | version | display | launch |
|---|---|---|---|---|---|---|
| Claude Code with a provider endpoint | claude-code | deepseek | DeepSeek Flash | V4.1 | DeepSeek V4.1 Flash | my-lab-claude |
A seat with model_from: launcher leaves the running model to what the launch runs — the provider's launcher, or Jules — so team doctor reads the model from the seat rather than from the file.
Known quirks
- DeepSeek ships no CLI of its own; its documented route is Claude Code with its endpoint.
Versions
One block per version, the current one first, each with its own anchor. The comparison table puts the costs and the family's benchmark columns side by side; the values are verbatim, and every one is sourced and dated in its version's section below and in the Sources list. A dash means the source publishes no figure, and nothing here is estimated.
No independent intelligence or speed index is republished here: Artificial Analysis measures both across labs, and its terms allow the link but not the copy — its figures live on its own pages.
| Version | Released | Context | Input price | Output price |
|---|---|---|---|---|
| DeepSeek V4.1 Flash — current | — | 1M tokens | $0.30 / MTok peak, $0.15 off-peak (cache miss) | $1.20 / MTok peak, $0.60 off-peak |
DeepSeek V4.1 Flash — current
- Model id:
deepseek-flash
Abilities
- Released: —
- Context window: 1M tokens — DeepSeek — API pricing (read 2026-10-19).
- Max output: 384K tokens — DeepSeek — API pricing (read 2026-10-19).
- Output speed: —
- Latency: —
Costs
- Input price: $0.30 / MTok peak, $0.15 off-peak (cache miss) — DeepSeek — API pricing (read 2026-10-19). Cache hit: $0.006 peak / $0.003 off-peak; vision supported; thinking on by default
- Output price: $1.20 / MTok peak, $0.60 off-peak — DeepSeek — API pricing (read 2026-10-19). Off-peak is half, weekdays outside 01:00–04:00 and 06:00–10:00 UTC
This is the version the seat lines above run.
Sources
- DeepSeek — API pricing — read 2026-10-19
Figures refreshed 2026-10-19; benchmarks are vendor-reported. Prices are per million tokens unless a figure says otherwise.