Polarison

Claude Sonnet 5 vs DeepSeek V4 Pro: pricing and benchmarks

DeepSeek V4 Pro is 34% cheaper on input tokens ($1.32 vs $2.00 per 1M). DeepSeek V4 Pro is 60% cheaper on output tokens ($3.96 vs $10.00 per 1M). On our document Q&A workload (50,000 questions a month), DeepSeek V4 Pro costs $646.80 a month versus $1,100 for Claude Sonnet 5, 41% less. Roughly tied. Claude Sonnet 5 scores 156.2 and DeepSeek V4 Pro scores 155.5 on the Epoch Capabilities Index, and their confidence intervals overlap.

Prices verified September 14, 2026.

Which should you choose?

Overall capability
Too close to call

Roughly tied. Claude Sonnet 5 scores 156.2 and DeepSeek V4 Pro scores 155.5 on the Epoch Capabilities Index, and their confidence intervals overlap.

Advanced math
Too close to call

About even on FrontierMath (Tiers 1–3): 65.6% for Claude Sonnet 5 and 64.6% for DeepSeek V4 Pro.

Price
DeepSeek V4 Pro

DeepSeek V4 Pro costs $1.98 per 1M tokens (3:1 input-to-output mix) vs $4.00 for Claude Sonnet 5, 51% less.

Best value
DeepSeek V4 Pro

DeepSeek V4 Pro delivers statistically similar overall capability for 51% less.

Pricing and specs

Claude Sonnet 5DeepSeek V4 Pro
ProviderAnthropicDeepSeek
API model IDclaude-sonnet-5deepseek-v4-pro
Input / 1M tokens$2.00$1.32
Cached input / 1M tokens$0.20$0.044
Output / 1M tokens$10.00$3.96
Long-context rates
Context window1M tokens1M tokens
Max output128K tokens384K tokens
Batch discount50% off

Benchmarks

Claude Sonnet 5DeepSeek V4 Pro
Epoch Capabilities Index156.2155.5
GPQA Diamond· Science reasoning87.4%88.9%
FrontierMath (Tiers 1–3)· Advanced math65.6%64.6%
SimpleQA Verified· Factual accuracy33.7%52.9%
ARC-AGI-2· Abstract reasoning61.3%
DeepSWE· Coding53.8%
APEX-Agents· Agentic work32.5%

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

WorkloadClaude Sonnet 5DeepSeek V4 ProDifference
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$700.00$356.40DeepSeek V4 Pro 49% cheaper
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$1,100$646.80DeepSeek V4 Pro 41% 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.
$496.00$249.92DeepSeek V4 Pro 50% 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.

Claude Sonnet 5 vs DeepSeek V4 Pro cost calculator

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.

Claude Sonnet 5 pricing notes

Anthropic’s best combination of speed and intelligence.

  • The $2 / $10 launch price is now the standard price; the planned rise to $3 / $15 will not happen.
  • Cache writes cost $2.50 (5-minute cache) or $4 (1-hour cache) per 1M tokens.
  • Uses Anthropic’s newer tokenizer, which produces roughly 30% more tokens for the same text.
Anthropic official pricing ↗

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.
DeepSeek official pricing ↗

Frequently asked questions

Is Claude Sonnet 5 cheaper than DeepSeek V4 Pro?
DeepSeek V4 Pro is 34% cheaper on input tokens ($1.32 vs $2.00 per 1M). DeepSeek V4 Pro is 60% cheaper on output tokens ($3.96 vs $10.00 per 1M). On our document Q&A workload (50,000 questions a month), DeepSeek V4 Pro costs $646.80 a month versus $1,100 for Claude Sonnet 5, 41% less.
Which is more capable, Claude Sonnet 5 or DeepSeek V4 Pro?
Roughly tied. Claude Sonnet 5 scores 156.2 and DeepSeek V4 Pro scores 155.5 on the Epoch Capabilities Index, and their confidence intervals overlap.
How much does Claude Sonnet 5 cost per 1M tokens?
Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens, and $0.20 per 1M cached input tokens on Anthropic’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, Claude Sonnet 5 or DeepSeek V4 Pro?
Both offer a 1M-token context window.

Related comparisons