← Model list
DeepSeek V4 Pro
deepseek·deepseek/deepseek-v4-pro·BETA·Open weights·deepseek-thinking series
Open MoE flagship with million-token context for coding and long agent runs
At a glance
Official price$0.435 / $0.87 per 1M
Cache read $0.0036 · DeepSeek
Lowest paid$0.348 / $0.696
routing.run Gateway · 6.9× spread
6 more $0 channels
Context1,000,000
⚠ Providers report 128,000–1,050,000; the table below is authoritative
Output limit384,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-05
Released / updated2026-04-24 / 2026-04-24
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning, Max Effort
Intelligence45.3
Value104
Coding59.4
Agentic37.8
Output speed74 tok/s
TTFT1.73 s
Cost per task$0.0474
Value formulaIQ 45.3 ÷ min blended $0.435 = 104
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 31.9 · 76 tok/s
Reasoning, High EffortIQ 43.7 · 75 tok/s
Reasoning, Max EffortIQ 45.3 · 74 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 60 providers51 with public prices · 2 free · 4 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Umans AI Coding Plan umans-deepseek-v4-pro-0813 | Gateway | Subscription | $0 | $0 | 1,048,576 ⚠ | 393,215 | ||
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 1,000,000 | 384,000 | ||
| Kenari | Gateway | Free | — | — | 1,000,000 | 384,000 | ||
| UnoRouter deepseek-v4-pro:free | Gateway | Free | — | — | 1,000,000 | 384,000 | ||
| SCNet Token Plan DeepSeek-V4-Pro | Gateway | Subscription | $0 | — | 1,000,000 | 384,000 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 1,000,000 | 384,000 | ||
| routing.run | Gateway | $0.348 | $0.696 | — | — | 1,000,000 | 64,000 | |
| CrofAI | Gateway | $0.35 | $0.80 | $0.003 | — | 1,000,000 | 131,072 | |
| EBCloud DeepSeek-V4-Pro | Gateway | $0.429 | $0.857 | — | — | 1,000,000 | 384,000 | |
| Nvidia | First-party | $0.435 | $0.87 | $0.0036 | — | 1,048,576 ⚠ | 393,216 | |
| DeepSeekOfficial | First-party | $0.435 | $0.87 | $0.0036 | — | 1,000,000 | 384,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1CrofAI$68.36
2Nvidia$78.74
3DeepSeek · Official$78.74
4Hugging Face$78.74
5Auriko$78.74
6Alibaba (China)$78.74
6 more channels offer $0 (Umans AI Coding Plan, Alibaba Token Plan, Kenari etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to CrofAI to save $10.38/mo (13%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark5 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 80.6 | resolved | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Claude Code · variant: high | 50.1 | average pass@1 | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Claude Code · variant: high | 67.8 | pass@1 | Source ↗ |
| SWE-Bench Pro | harness: Claude Code · variant: high · dataset: hard-aa | 18 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Claude Code · variant: high · v2.1 | 64.7 | pass@1 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)effort = higheffort = maxeffort = xhigheffort = noneeffort = loweffort = mediumeffort = minimalbudget_tokens ≥ 128 ≤ 32,768
11 / 60 providers expose no reasoning control (reasoning_options: []).
Related models
DeepSeek V4 Pro 0813same series$1.65 / $4.95DeepSeek V4 Pro 0813 Thinkingsame series$1.10 / $2.50DeepSeek V4 Pro (Thinking)same series$1.10 / $2.20DeepSeek V4 Flashcheaper alternative$0.14 / $0.28MiMo-V2.5cheaper alternative$0.14 / $0.28Gemini 2.5 Flash-Litecheaper alternative$0.10 / $0.40Qwen Pluscheaper alternative$0.115 / $0.287
Price historyone sample accumulated per data sync
Input listOutput listMin blended