DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance. The model includes hybrid attention for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.
Model card on Hugging Face- Input / output price
- $0.09 / $0.18 per 1M
- Context
- 1M tokens
- Released
- Apr 24, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
10 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
DeepInfra deepinfra/deepseek-v4-flash | $0.09/M | $0.18/M |
Featherless featherless/deepseek-v4-flash | $0.14/M | $0.28/M |
Parasail parasail/deepseek-v4-flash | $0.14/M | $0.28/M |
MorphLLM morphllm/deepseek-v4-flash | $0.141953/M | $0.399625/M |
Azure Foundry azure_foundry/deepseek-v4-flash | $0.19/M | $0.51/M |
Tera tera/deepseek-v4-flash | $0.19/M | $0.51/M |
Inference.net inference_net/deepseek-v4-flash | $0.23/M | $0.62/M |
IO.net ionet/deepseek-v4-flash | $0.288/M | $0.556/M |
DeepseekRetired deepseek/deepseek-v4-flash | $0.14/M | $0.28/M |
OpenRouter openrouter/deepseek-v4-flash | $0.091/M | $0.182/M |
Is a provider down? DeepSeek status, OpenRouter status
Pricing
Averaged across 10 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.16 per 1M
- Average output
- $0.38 per 1M
- Average cache read
- $0.13 per 1M
- Average cache write
- $0.03 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better102tokens/sacross providers
Time to first token
Lower is better2.0sacross providers
Response latency
Lower is better4.7sacross providers
Benchmarks
The Respan Index plus 29 published scores from 10 sources, each linked to where it was published.
45.3/ 100
Respan Index#56 of 176
- 56DeepSeek V4 Flash45.3
- 55GLM-5.3-Flash45.4
- 57Claude Opus 4.644.9
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Terminal Bench 2.1huggingface.co | 82.7% | huggingface.co | Jul 31, 2026 |
| Cybergymhuggingface.co | 76.7% | huggingface.co | Jul 31, 2026 |
| LiveBench CodingLiveBench | 75% | LiveBench | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 63% | Håvard Tveit Ihle | Oct 5, 2026 |
| DeepSWEhuggingface.co | 54.4% | huggingface.co | Jul 31, 2026 |
| NL2Repohuggingface.co | 54.2% | huggingface.co | Jul 31, 2026 |
| DeepSWE v1.1Datacurve | 53.3% | Datacurve | Oct 5, 2026 |
| Terminal-Bench 4.0Vals AI | 18.7% | Vals AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Toolathlon-VerifiedHKUST | 70.7% | HKUST | Jul 31, 2026 |
| Toolathlon-Verifiedhuggingface.co | 70.3% | huggingface.co | Jul 31, 2026 |
| LiveBench Agentic CodingLiveBench | 46.8% | LiveBench | Oct 5, 2026 |
| Agents' Last Examhuggingface.co | 25.2% | huggingface.co | Jul 31, 2026 |
| AutomationBench Publichuggingface.co | 25.1% | huggingface.co | Jul 31, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 91% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 86.6% | LiveBench | Oct 5, 2026 |
| LiveBench Data AnalysisLiveBench | 79.3% | LiveBench | Oct 5, 2026 |
| SimpleBenchSimpleBench | 61.1% | SimpleBench | Aug 3, 2026 |
| Mystery Game PuzzlesEpoch AI | 34% | Epoch AI | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 32% | Epoch AI | Oct 28, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026MathArena | 95.8% | MathArena | Oct 13, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 94.4% | Epoch AI | Oct 5, 2026 |
| LiveBench MathematicsLiveBench | 86.8% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 57.5% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 24.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 79.2% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 65.5% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 33.6% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1582 Elo · #41 of 124 | LMArena | Nov 19, 2026 |
| LMArena EloLMArena | 1436 Elo · #82 of 191 | LMArena | Nov 19, 2026 |
How DeepSeek compares: Claude vs DeepSeek, DeepSeek vs Qwen, DeepSeek vs Gemini
Compare DeepSeek V4 Flash: DeepSeek V4 Flash vs DeepSeek V4.1 Flash, DeepSeek V4 Flash vs Muse Spark 1.3, DeepSeek V4 Flash vs GPT-6 Luna, DeepSeek V4 Flash vs Claude Sonnet 5.5, DeepSeek V4 Flash vs DeepSeek-V4.1-Flash-1017, DeepSeek V4 Flash vs DeepSeek V4 Pro
Apps
Use DeepSeek V4 Flash in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
DeepSeek V4 Flash FAQ
Short answers, built from the data on this page.
DeepSeek V4 Flash is a model from Deepseek, released on Apr 24, 2026. DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance. The model includes hybrid attention for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.
On the Respan gateway, DeepSeek V4 Flash costs from $0.09 per 1M input tokens and $0.18 per 1M output tokens on DeepInfra, after gateway discounts. Averaged across its 10 providers, it costs $0.16 per 1M input tokens and $0.38 per 1M output tokens.
DeepSeek V4 Flash is available through 10 providers: DeepInfra, Featherless, Parasail, MorphLLM, Azure Foundry, Tera, and 4 more.
DeepSeek V4 Flash accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "deepseek/deepseek-v4-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
DeepSeek V4 Flash scores 45.3 out of 100 on the Respan Index v1.1, ranking #56 of 176 models. By category: Coding 29.7, Agents 58.0, Reasoning 46.1, Knowledge & language 35.5, and Human preference 55.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
DeepSeek V4 Flash has 29 published benchmark scores, including Terminal Bench 2.1 82.7%, Toolathlon-Verified 70.7%, and GPQA Diamond 91%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.