DeepSeek V4 Flash Latest
by DeepSeekChat
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
- Context
- 1.05M tokens
- Max output
- 393,216 tokens
- Parameters
- 284B total, 13B active
- Released
- 2026-07-31
- Weights
- Open
deepseek/deepseek-v4-flash-0731 · also seen as deepseek-ai/deepseek-v4-flash-0731, deepseek/deepseek-v4-flash-latest, deepseek-v4-flash-0731-fast, @cf/deepseek-ai/deepseek-v4-flash-0731, +24 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-07-31
- Weights
- Open
- Input
- Text
- Output
- Text
- Context window
- 1,048,576 max across endpoints
- Max output
- 393,216
- Providers
- 61 + 15 gateways, not counted as providers
- Epoch Capabilities Index
- 154.5 ± 2.1 against price
- Direct price range
- $0.040–$0.468 in · $0.09–$1.34 out per 1M tokens · 52 of 61 providers have a comparable price
More details
- Last updated
- 2026-09-10
- Knowledge cutoff
- 2025-05
- Parameters
- 284B 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 messagesunknown
- Assistant prefillunknown
- 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 $0.045 in / $0.09 out per 1M tokens at engy on every data refresh since then.
Tracked from 19 Oct 2026. 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 Latest |
|---|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B A3BNVIDIA | $0.0408 | $0.025 | $0.12 | 262K | −0% cheaper |
| Gemma 3 4B ITGoogle | $0.0417 | $0.04 | $0.05 | 131K | +2% |
| Llama 3 8B LunarisSao10K | $0.0417 | $0.04 | $0.05 | 8.2K | +2% |
| Ministral 3BMistral AI | $0.04 | $0.04 | $0.04 | 131K | −2% cheaper |
| Voxtral Mini 3B 2507Mistral AI | $0.04 | $0.04 | $0.04 | — | −2% cheaper |
| Qwen3.7 FlashAlibaba (Qwen) | $0.0423 | $0.0282 | $0.113 | 1M | +4% |
| Manta Flash 1.0MegaNova AI | $0.0433 | $0.02 | $0.16 | 16.4K | +6% |
| Manta Mini 1.0MegaNova AI | $0.0433 | $0.02 | $0.16 | 8.2K | +6% |
More from DeepSeek
Newest DeepSeek models in the catalogue. All DeepSeek models
| Model | Released | Context | Listed price |
|---|---|---|---|
| DeepSeek V4 Flash | 2026-10-17 | 1.05M | from $0.07 |
| 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 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 |