DeepSeek V4 Flash
by DeepSeekChat
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
- Context
- 1.05M tokens
- Max output
- 393,216 tokens
- Parameters
- 291B total, 13B active
- Released
- 2026-10-17
- Weights
- Open
- Licence
- mit
deepseek/deepseek-v4-flash · also seen as deepseek-ai/deepseek-v4-flash, deepseek-v4-flash:free, deepseek/deepseek-v4-flash-fast, deepseek/deepseek-v4-flash-free, +19 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-10-17
- Weights
- Opennot gated
- License
- mit
- Input
- Text
- Output
- Text
- Context window
- 1,050,000 max across endpoints
- Max output
- 393,216
- Providers
- 55 + 26 gateways, not counted as providers
- Epoch Capabilities Index
- 146.1 ± 2.2 against price
- Direct price range
- $0.07–$0.50 in · $0.14–$1.32 out per 1M tokens · 37 of 55 providers have a comparable price
More details
- Last updated
- 2026-10-17
- Knowledge cutoff
- 2025-05
- Weights link
- Hugging Face · deepseek-ai/DeepSeek-V4-Flash
- Parameters
- 291B total, 13B active
- Developer country
- China
- Training compute
- 2.5×10²⁴ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefill
- Temperature
- Streaming
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.07 in / $0.14 out per 1M tokens at StreamLake on every data refresh since then.
Tracked from 19 Oct 2026, the earliest refresh this model's headline price can be rebuilt from. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs DeepSeek V4 Flash |
|---|---|---|---|---|---|
| Seed 2.0 MiniByteDance Seed | $0.0717 | $0.03 | $0.28 | 262K | −2% cheaper |
| Seed 2.0 MiniByteDance Seed | $0.0717 | $0.03 | $0.28 | 256K | −2% cheaper |
| Gemma 4 26B A4B ITGoogle | $0.0717 | $0.042 | $0.22 | 262K | −2% cheaper |
| nemotron-3-nano-30b-a3bNVIDIA | $0.075 | $0.05 | $0.20 | 262K | +3% |
| Qwen TurboAlibaba (Qwen) | $0.0751 | $0.05 | $0.201 | 1M | +3% |
| Qwen3.5 FlashAlibaba (Qwen) | $0.0705 | $0.0282 | $0.282 | 1M | −3% cheaper |
| Laguna XS 2.1Poolside | $0.07 | $0.06 | $0.12 | 262K | −4% cheaper |
| Phi 4 MultimodalMicrosoft | $0.0767 | $0.07 | $0.11 | 131K | +5% |
More from DeepSeek
Newest DeepSeek models in the catalogue. All DeepSeek models
| Model | Released | Context | Listed price |
|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | 2026-10-17 | 1M | from $0.08 |
| DeepSeek V4 Flash Vision Exp | 2026-10-17 | 1.05M | from $0.14 |
| DeepSeek V4.1 Flash | 2026-09-10 | 1.05M | from $0.09 |
| DeepSeek V4 Pro 0813 | 2026-08-12 | 1M | from $0.88 |
| DeepSeek V4 Flash Latest | 2026-07-31 | 1.05M | from $0.04 |
| DeepSeek Pro Latest | 2026-07-06 | 1M | unpriced |
| DeepSeek Latest | 2026-05-03 | 1.05M | $0.145 via NanoGPT |
| DeepSeek V4 Pro | 2026-04-24 | 1M | from $0.45 |