DeepSeek V4 Flash vs DeepSeek V4 Pro
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by DeepSeek
3 providers:
DeepSeek $0.140/$0.280
Fireworks $0.140/$0.280
DeepInfra $0.090/$0.180
|
by DeepSeek
3 providers:
DeepSeek $0.435/$0.870
Fireworks $1.74/$3.48
Together $1.74/$3.48
|
|---|---|---|
| Overview | ||
| Status | Current budget | Current mid tier |
| Released | Apr 24, 2026 | Apr 24, 2026 |
| Pricing per million tokens | ||
| Input | $0.140/Mtok | $0.435/Mtok |
| Output | $0.280/Mtok | $0.870/Mtok |
| Blended avg | $0.175/Mtok | $0.544/Mtok |
| Cached input | $0.003/Mtok | $0.004/Mtok |
| Specifications | ||
| Context window | 1M tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks source: Vellum LLM Leaderboard | ||
| Avg benchmark score | 77.5 | 73.5 |
| Perf / dollar | 442.9 | 135.2 |
| GPQA Diamond | 88.1 | 90.1 |
| SWE-Bench Verified | 79 vendor | 80.6 vendor |
| LiveCodeBench | 91.6 | 93.5 |
| MCP Atlas | 69 | 73.6 |
| BrowseComp | 85.9 | 83.4 |
| Humanity's Last Exam | 51.6 | 48.2 |
| ARC-AGI 2 | 18 vendor | 30 |
| AIME 2025 | 58 vendor | 75 |
| MMMLU | 75 vendor | 82 |
| BFCL | 62 vendor | 72 |
| HumanEval | 79 | 80.6 |
| MATH 500 | 68 vendor | 80 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 51.8 | 45.3 |
| AA Agentic Index | 48.4 | 37.8 |
| AA-Omniscience Index (−100–100) | -14.3 | -10.7 |
| GDPval-AA v2 | 1558.4 ELO | 1304.5 ELO |
| LMSYS Chatbot Arena | 1435.8 ELO | 1457.1 ELO |
| Providers | ||
| Available from |
DeepSeek — $0.140/$0.280/Mtok
Fireworks — $0.140/$0.280/Mtok
DeepInfra — $0.090/$0.180/Mtok
|
DeepSeek — $0.435/$0.870/Mtok
Fireworks — $1.74/$3.48/Mtok
Together — $1.74/$3.48/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | DeepSeek V4 Flash | DeepSeek V4 Pro | Savings |
|---|---|---|---|
| 1M tokens | $0.18 | $0.54 | $0.37 (68%) |
| 10M tokens | $1.75 | $5.44 | $3.69 (67.9%) |
| 100M tokens | $17.5 | $54.37 | $36.87 (67.8%) |
| 1000M tokens | $175 | $543.75 | $368.75 (67.8%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.175/Mtok blended vs $0.544 — 67.8% less on the same 50/50 token mix
- raw capability matters more than price: 77.5 vs 73.5 average benchmark score
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.004/Mtok — 99% off its list input price
The cheaper option here — DeepSeek V4 Flash costs $0.175/Mtok blended on DeepSeek.
Summary
DeepSeek V4 Flash by DeepSeek costs $0.140/Mtok input and $0.280/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
DeepSeek V4 Pro by DeepSeek costs $0.435/Mtok input and $0.870/Mtok output, with a 1M-token context window. It supports text input and is available from 3 providers.
On a blended cost basis, DeepSeek V4 Flash is 67.8% cheaper than DeepSeek V4 Pro.
On benchmarks, DeepSeek V4 Flash scores higher (77.5 vs 73.5) on average. In terms of value, DeepSeek V4 Flash has better performance per dollar (442.9 vs 135.2).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.