DeepSeek-V4-Flash-Max: Benchmarks, Pricing & Context Window
DeepSeek-V4-Flash-Max is a language model from DeepSeek, released in April 2026, with a 1.0M-token context window, and pricing from $0.090/M input, $0.018/M cached input, $0.180/M output.
DeepSeek-V4-Flash-Max is the maximum reasoning effort mode of DeepSeek-V4-Flash, a 284B-parameter MoE model with 13B activated parameters and a 1M-token context window. Sharing the V4 series' hybrid attention architecture (Compressed
DeepSeek-V4-Flash-Max benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for DeepSeek-V4-Flash-Max across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How DeepSeek-V4-Flash-Max holds up as conversations get longer.
Quality Tracker
DeepSeek-V4-Flash-Max Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Sep 09 2026DeepSeek-V4-Flash-Max pricing
Providers
DeepSeek-V4-Flash-Max starts at $0.0900 per million input tokens and $0.180 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.0180 per million cached input tokens. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0900 | $0.0180 | $0.180 | 1.0M/1.0M | — | — | / |
 DeepSeek | $0.140 | $0.0028 | $0.280 | 1.0M/393.2K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
DeepSeek-V4-Flash-Max model size
DeepSeek-V4-Flash-Max has 284 billion parameters and was trained on 32 trillion tokens. See how it compares to other models in the same parameter range.
DeepSeek-V4-Flash-Max context window
Input and output token limits for DeepSeek-V4-Flash-Max, plus how it ranks on long-context understanding.
Try now
huggleMake it with
DeepSeek-V4-Flash-Max.
DeepSeek-V4-Flash-Max latency
DeepSeek-V4-Flash-Max time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
DeepSeek-V4-Flash-Max examples
Recent arena outputs from DeepSeek-V4-Flash-Max, picked from the highest-ranked matchups.
DeepSeek-V4-Flash-Max license
DeepSeek-V4-Flash-Max is released under the MIT license, which permits commercial use, has 284.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 284.0B
MIT License - allows commercial use
DeepSeek-V4-Flash-Max resources
Official sources for DeepSeek-V4-Flash-Max: provider documentation, official playground, source repository, model weights.
DeepSeek-V4-Flash-Max vs other models
The most-compared alternatives to DeepSeek-V4-Flash-Max are Gemini 3 Pro, Gemini 3 Flash, GPT-5 Medium. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like DeepSeek-V4-Flash-Max
Models ranked just above and below DeepSeek-V4-Flash-Max by LLM Stats score.
FAQ
Common questions about DeepSeek-V4-Flash-Max.