DeepSeek V4 Flash — pricing & specs
DeepSeek V4 Flash is a fast model from DeepSeek, at capability tier 4 of 8. Live $/M-token pricing and specs from the Mintok catalog, as of 2026-09-21.
$/M-token pricing
as of 2026-09-21 · DeepSeekWhat DeepSeek V4 Flash costs in practice
At $0.60/M output tokens, DeepSeek V4 Flash is the 3rd-cheapest of 9 priced tier-4 models in the Mintok catalog — about 8% below the tier median of $0.65/M.
| Scenario | Est. cost |
|---|---|
| 1M input + 1M output tokens | $0.750 |
| A 10K-token request (8K in / 2K out) | $0.0024 |
| 1,000 agent runs (~2K in / 500 out each) | $0.600 |
| 1M-token RAG chat session (900K cached in / 100K out) | $0.063 |
Estimated from list price (as of 2026-09-21) at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →
Specifications
- Vendor
- DeepSeek
- Family
- DeepSeek V4 Flash
- Capability tier
- 4 / 8
- Size class
- FAST
- Category
- GENERAL
- Parameters
- 284B total · 13B active (MoE)
- Context window
- 1,000,000 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference Cerebras Cerebras WSE-3 Turbo at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 4
Same capability tier, sorted by output price — the cheaper-capable options.
- LLaMA 4 ScoutMeta$0.30/M out
- Qwen 2.5 72BAlibaba$0.40/M out
- GPT-4o miniOpenAI$0.60/M out
- LLaMA 4 MaverickMeta$0.65/M out
- Qwen 3 235B (MoE)Alibaba$1.82/M out
- Claude Haiku 3.5Anthropic$4/M out
FAQ
How much does DeepSeek V4 Flash cost per token?
DeepSeek V4 Flash costs $0.15 per million input tokens and $0.60 per million output tokens (cached input $0.00/M), via DeepSeek, as of 2026-09-21.
Is DeepSeek V4 Flash expensive?
At $0.60/M output tokens, DeepSeek V4 Flash is the 3rd-cheapest of 9 priced tier-4 models in the Mintok catalog — about 8% below the tier median of $0.65/M.
What does a typical request with DeepSeek V4 Flash cost?
At list price, a 10K-token request (8K in / 2K out) with DeepSeek V4 Flash costs about $0.0024, and 1,000 agent runs (~2K in / 500 out each) about $0.600.
What is DeepSeek V4 Flash's context window?
DeepSeek V4 Flash supports a 1,000,000-token context window.
What capability tier is DeepSeek V4 Flash?
DeepSeek V4 Flash sits at capability tier 4 of 8 on the Mintok scale (FAST size class).
Is DeepSeek V4 Flash open-source or proprietary?
DeepSeek V4 Flash is a proprietary model from DeepSeek, accessed via API.
Put DeepSeek V4 Flash to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.