DeepSeek V4.1 Flash vs DeepSeek V4 Pro: pricing and benchmarks
DeepSeek V4.1 Flash is 77% cheaper on input tokens ($0.30 vs $1.32 per 1M). DeepSeek V4.1 Flash is 70% cheaper on output tokens ($1.20 vs $3.96 per 1M). On our document Q&A workload (50,000 questions a month), DeepSeek V4.1 Flash costs $156.00 a month versus $646.80 for DeepSeek V4 Pro, 76% less. Roughly tied. DeepSeek V4.1 Flash scores 155.6 and DeepSeek V4 Pro scores 155.3 on the Epoch Capabilities Index, and their confidence intervals overlap.
Prices verified October 25, 2026.
Which should you choose?
Roughly tied. DeepSeek V4.1 Flash scores 155.6 and DeepSeek V4 Pro scores 155.3 on the Epoch Capabilities Index, and their confidence intervals overlap.
DeepSeek V4.1 Flash scores 67.4% on FrontierMath (Tiers 1–3) vs 64.6% for DeepSeek V4 Pro.
DeepSeek V4.1 Flash costs $0.525 per 1M tokens (3:1 input-to-output mix) vs $1.98 for DeepSeek V4 Pro, 73% less.
DeepSeek V4.1 Flash delivers equal or higher overall capability for 73% less.
Pricing and specs
| DeepSeek V4.1 Flash | DeepSeek V4 Pro | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| API model ID | deepseek-flash | deepseek-v4-pro |
| Input / 1M tokens | $0.30 | $1.32 |
| Cached input / 1M tokens | $0.006 | $0.044 |
| Output / 1M tokens | $1.20 | $3.96 |
| Long-context rates | — | — |
| Context window | 1M tokens | 1M tokens |
| Max output | 384K tokens | 384K tokens |
| Batch discount | — | — |
Benchmarks
| DeepSeek V4.1 Flash | DeepSeek V4 Pro | |
|---|---|---|
| Epoch Capabilities Index | 155.6 | 155.3 |
| GPQA Diamond· Science reasoning | 89.8% | 91.7% |
| FrontierMath (Tiers 1–3)· Advanced math | 67.4% | 64.6% |
| SimpleQA Verified· Factual accuracy | 42.9% | 52.9% |
| ARC-AGI-2· Abstract reasoning | 72.9% | 61.3% |
| DeepSWE· Coding | — | — |
| APEX-Agents· Agentic work | 39.5% | 47.3% |
Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks
Monthly cost for real workloads
| Workload | DeepSeek V4.1 Flash | DeepSeek V4 Pro | Difference |
|---|---|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $93.00 | $356.40 | DeepSeek V4.1 Flash 74% cheaper |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $156.00 | $646.80 | DeepSeek V4.1 Flash 76% cheaper |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $61.68 | $249.92 | DeepSeek V4.1 Flash 75% cheaper |
Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.
DeepSeek V4.1 Flash vs DeepSeek V4 Pro cost calculator
- $156.00/mo$0.0031 / request
- DeepSeek V4 ProDeepSeek$646.80/mo$0.01 / request
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.
DeepSeek V4.1 Flash pricing notes
DeepSeek’s low-cost model with thinking and non-thinking modes, tool calls and vision input.
- Prices shown are peak rates. Off-peak rates are half: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday.
- Compatible with both OpenAI-format and Anthropic-format APIs.
- Served by model version DeepSeek-V4.1-Flash-1017; the legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp route to it at the same price.
- Web Search and Fetch cost $0.75 per 1,000 successful requests each; calls made through Claude Code, Codex or DeepSeek Harness are free until November 1, 2026.
DeepSeek V4 Pro pricing notes
DeepSeek’s larger V4 model with thinking and non-thinking modes and tool calls.
- Prices shown are peak rates. Off-peak rates are half: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday.
- Vision input is not supported.
- Web Search and Fetch cost $0.75 per 1,000 successful requests each; calls made through Claude Code, Codex or DeepSeek Harness are free until November 1, 2026.
Frequently asked questions
- Is DeepSeek V4.1 Flash cheaper than DeepSeek V4 Pro?
- DeepSeek V4.1 Flash is 77% cheaper on input tokens ($0.30 vs $1.32 per 1M). DeepSeek V4.1 Flash is 70% cheaper on output tokens ($1.20 vs $3.96 per 1M). On our document Q&A workload (50,000 questions a month), DeepSeek V4.1 Flash costs $156.00 a month versus $646.80 for DeepSeek V4 Pro, 76% less.
- Which is more capable, DeepSeek V4.1 Flash or DeepSeek V4 Pro?
- Roughly tied. DeepSeek V4.1 Flash scores 155.6 and DeepSeek V4 Pro scores 155.3 on the Epoch Capabilities Index, and their confidence intervals overlap.
- How much does DeepSeek V4.1 Flash cost per 1M tokens?
- DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, and $0.006 per 1M cached input tokens on DeepSeek’s standard tier.
- How much does DeepSeek V4 Pro cost per 1M tokens?
- DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens, and $0.044 per 1M cached input tokens on DeepSeek’s standard tier.
- Which has the larger context window, DeepSeek V4.1 Flash or DeepSeek V4 Pro?
- Both offer a 1M-token context window.