DeepSeek-V4-Flash-0731: API Pricing, Context Window & Benchmarks
DeepSeek-V4-Flash-0731 is a language model from DeepSeek, released in July 2026, with a 1.0M-token context window, and pricing from $0.090/M input and $0.180/M output.
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version with substantially stronger agentic capabilities. It retains the V4-Flash architecture and adds an attached DSpark speculative-decoding
DeepSeek-V4-Flash-0731 benchmarks
Rankings
Quality Tracker
DeepSeek-V4-Flash-0731 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Aug 03 2026DeepSeek-V4-Flash-0731 pricing
Providers
DeepSeek-V4-Flash-0731 starts at $0.0900 per million input tokens and $0.180 per million output tokens via DeepInfra. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0900 | $0.180 | 1.0M/65.5K | —/— | —/— | — | / |
 Fireworks | $0.140 | $0.280 | 1.0M/65.5K | —/— | —/— | — | / |
 Novita | $0.140 | $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. Success is calculated from completed versus failed requests over the trailing seven days.
DeepSeek-V4-Flash-0731 model size
DeepSeek-V4-Flash-0731 has 304 billion parameters. See how it compares to other models in the same parameter range.
DeepSeek-V4-Flash-0731 context window
Input and output token limits for DeepSeek-V4-Flash-0731, plus how it ranks on long-context understanding.
DeepSeek-V4-Flash-0731 API
Run a request to see the response
Use it in your code
Billed at $0.09 input / $0.18 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="deepseek-v4-flash-0731",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
DeepSeek-V4-Flash-0731 latency
DeepSeek-V4-Flash-0731 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
DeepSeek-V4-Flash-0731 examples
Recent arena outputs from DeepSeek-V4-Flash-0731, picked from the highest-ranked matchups.
DeepSeek-V4-Flash-0731 license
DeepSeek-V4-Flash-0731 is released under the MIT license, which permits commercial use, has 304.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 304.0B
MIT License - allows commercial use
DeepSeek-V4-Flash-0731 resources
Official sources for DeepSeek-V4-Flash-0731: api documentation, official playground, paper or system card, source repository, model weights.
DeepSeek-V4-Flash-0731 vs other models
The most-compared alternatives to DeepSeek-V4-Flash-0731 are Claude Opus 4.6, Qwen3.7 Max, Claude Opus 4.8. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like DeepSeek-V4-Flash-0731
Models ranked just above and below DeepSeek-V4-Flash-0731 by LLM Stats score.
FAQ
Common questions about DeepSeek-V4-Flash-0731.