DeepSeek V4 Pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical.
Model card on Hugging Face- Input / output price
- $0.90 / $1.50 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
16 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Wafer wafer/deepseek-v4-pro | $0.28/M | $3.96/M |
Relace relace/deepseek-v4-pro | $0.45/M | $3.00/M |
Concentrate concentrate/deepseek-v4-pro | $0.50/M | $2.00/M |
Deepseek deepseek/deepseek-v4-pro | $0.66/M | $1.98/M |
DeepInfra deepinfra/deepseek-v4-pro | $1.30/M | $2.60/M |
IO.net ionet/deepseek-v4-pro | $1.4288/M | $2.7996/M |
Featherless featherless/deepseek-v4-pro | $1.60/M | $3.20/M |
Novita novita/deepseek-v4-pro | $1.60/M | $3.20/M |
EmpirioLabs empiriolabs/deepseek-v4-pro | $1.65/M | $3.30/M |
RunAnywhere runanywhere/deepseek-v4-pro-fast | $1.68/M | $3.38/M |
Azure Foundry azure_foundry/deepseek-v4-pro | $1.74/M | $3.48/M |
Nextbit256 nextbit256/deepseek-v4-pro | $1.74/M | $3.48/M |
Tera tera/deepseek-v4-pro | $1.74/M | $3.48/M |
Inference.net inference_net/deepseek-v4-pro | $2.10/M | $4.20/M |
NebiusRetired nebius/deepseek-v4-pro | $1.75/M | $3.50/M |
OpenRouter openrouter/deepseek-v4-pro | $0.90/M | $1.50/M |
Is a provider down? DeepSeek status, OpenRouter status
Pricing
Averaged across 16 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $1.32 per 1M
- Average output
- $3.07 per 1M
- Average cache read
- $0.30 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 better104tokens/sacross providers
Time to first token
Lower is better1.8sacross providers
Response latency
Lower is better6.2sacross providers
Benchmarks
The Respan Index plus 31 published scores from 13 sources, each linked to where it was published.
49.2/ 100
Respan Index#45 of 176
- 45DeepSeek V4 Pro49.2
- 44GPT-5.449.9
- 46GPT-6 Luna48.6
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Terminal-Bench 2.1DeepSeek | 87.9% | DeepSeek | Aug 13, 2026 |
| SWE-bench VerifiedEpoch AI | 77.6% | Epoch AI | Oct 5, 2026 |
| LiveBench CodingLiveBench | 77.2% | LiveBench | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 66.2% | Håvard Tveit Ihle | Oct 5, 2026 |
| DeepSWE v1.1Datacurve | 62.8% | Datacurve | Oct 5, 2026 |
| DeepSWE v1.1DeepSeek | 62.7% | DeepSeek | Aug 13, 2026 |
| SWE-rebench 2026-05-15 to 2026-07-01Nebius | 40.2% | Nebius | Oct 5, 2026 |
| MirrorCodeEpoch AI | 33.3% | Epoch AI | Oct 31, 2026 |
| Terminal-Bench 4.0Vals AI | 14.1% | Vals AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Toolathlon-VerifiedHKUST | 74.4% | HKUST | Aug 13, 2026 |
| LiveBench Agentic CodingLiveBench | 54.9% | LiveBench | Oct 5, 2026 |
| APEX-AgentsMercor | 47.3% | Mercor | Oct 5, 2026 |
| Vending-Bench 2Andon Labs | 3284.52 · #49 of 68 | Andon Labs | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 91.7% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 85.8% | LiveBench | Oct 5, 2026 |
| LiveBench Data AnalysisLiveBench | 79.2% | LiveBench | Oct 5, 2026 |
| Humanity's Last Exam (with tools)DeepSeek | 60% | DeepSeek | Aug 13, 2026 |
| SimpleBenchSimpleBench | 50.9% | SimpleBench | Jun 2, 2026 |
| Chess PuzzlesEpoch AI | 46% | Epoch AI | Oct 28, 2026 |
| Mystery Game PuzzlesEpoch AI | 43% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 98.6% | Epoch AI | Oct 5, 2026 |
| AIME 2026MathArena | 96.7% | MathArena | Sep 17, 2026 |
| LiveBench MathematicsLiveBench | 95.1% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 64.6% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 26.8% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 82.1% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 67.7% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 52.9% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1581 Elo · #43 of 124 | LMArena | Nov 19, 2026 |
| LMArena EloLMArena | 1464 Elo · #50 of 191 | LMArena | Nov 19, 2026 |
| LMArena AgentLMArena | -0.003 · #37 of 68 | LMArena | Nov 4, 2026 |
How DeepSeek compares: Claude vs DeepSeek, DeepSeek vs Qwen, DeepSeek vs Gemini
Compare DeepSeek V4 Pro: DeepSeek V4 Pro vs Claude Sonnet 5.5, DeepSeek V4 Pro vs Gemini 3.8 Flash, DeepSeek V4 Pro vs DeepSeek-V4.1-Flash-1017, DeepSeek V4 Pro vs DeepSeek V4.1 Flash, DeepSeek V4 Pro vs DeepSeek V4 Flash, DeepSeek V4 Pro vs DeepSeek-V4-Flash (Preview)
Apps
Use DeepSeek V4 Pro 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 Pro FAQ
Short answers, built from the data on this page.
DeepSeek V4 Pro is a model from Deepseek, released on Apr 24, 2026. DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks. Built on the same architecture as DeepSeek V4 Flash, it introduces a hybrid attention system for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for complex workloads such as full-codebase analysis, multi-step automation, and large-scale information synthesis, where both capability and efficiency are critical.
On the Respan gateway, input starts at $0.28 per 1M tokens on Wafer, and output starts at $1.50 per 1M tokens on OpenRouter, after gateway discounts. Averaged across its 16 providers, it costs $1.32 per 1M input tokens and $3.07 per 1M output tokens.
DeepSeek V4 Pro is available through 16 providers: Wafer, Relace, Concentrate, Deepseek, DeepInfra, IO.net, and 10 more.
DeepSeek V4 Pro 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-pro". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
DeepSeek V4 Pro scores 49.2 out of 100 on the Respan Index v1.1, ranking #45 of 176 models. By category: Coding 29.8, Agents 59.7, Reasoning 52.8, Knowledge & language 52.6, and Human preference 55.7. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
DeepSeek V4 Pro has 31 published benchmark scores, including Terminal-Bench 2.1 87.9%, Toolathlon-Verified 74.4%, and GPQA Diamond 91.7%. 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.