DeepSeek V4 Pro vs Sonar
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by DeepSeek
4 providers:
DeepSeek $0.435/$0.870
Fireworks $1.74/$3.48
Together $1.74/$3.48
DeepInfra $1.30/$2.60
|
by Perplexity
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current mid tier |
| Released | Apr 24, 2026 | Feb 1, 2025 |
| Pricing per million tokens | ||
| Input | $0.435/Mtok | $1.00/Mtok |
| Output | $0.870/Mtok | $1.00/Mtok |
| Blended avg | $0.544/Mtok | $1.00/Mtok |
| Cached input | $0.004/Mtok | — |
| Specifications | ||
| Context window | 1M tokens | 200K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Vellum LLM Leaderboard / n/a | ||
| Avg benchmark score | 73.5 | — |
| Perf / dollar | 135.2 | — |
| GPQA Diamond | 90.1 | — |
| SWE-Bench Verified | 80.6 vendor | — |
| LiveCodeBench | 93.5 | — |
| MCP Atlas | 73.6 | — |
| BrowseComp | 83.4 | — |
| Humanity's Last Exam | 48.2 | — |
| ARC-AGI 2 | 30 | — |
| AIME 2025 | 75 | — |
| MMMLU | 82 | — |
| BFCL | 72 | — |
| HumanEval | 80.6 | — |
| MATH 500 | 80 | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 53.2 | — |
| AA Agentic Index | 49.6 | — |
| AA-Omniscience Index (−100–100) | 0.8 | — |
| GDPval-AA v2 | 1590 ELO | — |
| LMSYS Chatbot Arena | 1458.2 ELO | — |
| Providers | ||
| Available from |
DeepSeek — $0.435/$0.870/Mtok
Fireworks — $1.74/$3.48/Mtok
Together — $1.74/$3.48/Mtok
DeepInfra — $1.30/$2.60/Mtok
|
Perplexity — $1.00/$1.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | DeepSeek V4 Pro | Sonar | Savings |
|---|---|---|---|
| 1M tokens | $0.54 | $1 | $0.46 (46%) |
| 10M tokens | $5.44 | $10 | $4.56 (45.6%) |
| 100M tokens | $54.37 | $100 | $45.63 (45.6%) |
| 1000M tokens | $543.75 | $1000 | $456.25 (45.6%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.544/Mtok blended vs $1.00 — 45.6% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.004/Mtok — 99% off its list input price, a discount Sonar doesn't offer
- you need the longer context: 1M tokens vs 200K (5×)
- provider flexibility: available from 4 providers, so you can price-shop hosts or fail over
- this pairing gives Sonar no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
The cheaper option here — DeepSeek V4 Pro costs $0.544/Mtok blended on DeepSeek.
Summary
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 4 providers.
Sonar by Perplexity costs $1.00/Mtok input and $1.00/Mtok output, with a 200K-token context window. It supports text input.
On a blended cost basis, DeepSeek V4 Pro is 45.6% cheaper than Sonar.It also has a larger context window.
The two aren't directly comparable on average benchmark score: DeepSeek V4 Pro has published per-benchmark results, while Sonar does not yet.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.