Anthropic vs DeepSeek
Complete comparison of Anthropic (9 models) and DeepSeek (8 models) for AI coding projects. Updated April 2026.
Quick Verdict
Anthropic offers 9 models ranging from $0.250 to $15.00 per million input tokens. Cheapest: Claude 3 Haiku.
DeepSeek offers 8 models ranging from $0.140 to $0.550 per million input tokens. Cheapest: DeepSeek V3.
Winner on price: DeepSeek ($0.140/M input). Winner on average: DeepSeek (avg $0.261/M).
Winner Per Scenario
Which provider has the cheapest model for each coding scenario?
| Scenario | Anthropic Best | DeepSeek Best | Winner |
|---|---|---|---|
| Small Script (1K lines) | Claude 3 Haiku — $0.05 | DeepSeek V3 — $0.01 | DeepSeek wins by $0.03 |
| Medium Feature (10K lines) | Claude 3 Haiku — $0.34 | DeepSeek V3 — $0.11 | DeepSeek wins by $0.23 |
| Large Project (50K lines) | Claude 3 Haiku — $1.69 | DeepSeek V3 — $0.53 | DeepSeek wins by $1.16 |
| Code Review (5K lines) | Claude 3 Haiku — $0.07 | DeepSeek V3 — $0.03 | DeepSeek wins by $0.04 |
Head-to-Head Model Comparisons
Each Anthropic model matched against its closest-priced DeepSeek competitor. Medium project cost (500K input + 200K output).
| Anthropic | DeepSeek | Cost | Cost | Savings |
|---|---|---|---|---|
| Claude Sonnet 4 | DeepSeek Reasoner (R1) | $4.66 | $0.63 | DeepSeek Reasoner (R1) saves $4.03 (86%) |
| Claude Opus 4 | DeepSeek Reasoner (R1) | $23.29 | $0.63 | DeepSeek Reasoner (R1) saves $22.66 (97%) |
| Claude 3.5 Sonnet | DeepSeek Reasoner (R1) | $4.66 | $0.63 | DeepSeek Reasoner (R1) saves $4.03 (86%) |
| Claude 3.5 Haiku | DeepSeek Reasoner (R1) | $1.24 | $0.63 | DeepSeek Reasoner (R1) saves $0.61 (49%) |
| Claude 3 Opus | DeepSeek Reasoner (R1) | $20.25 | $0.63 | DeepSeek Reasoner (R1) saves $19.62 (97%) |
| Claude 3 Sonnet | DeepSeek Reasoner (R1) | $4.05 | $0.63 | DeepSeek Reasoner (R1) saves $3.42 (84%) |
| Claude 3 Haiku | DeepSeek Chat V3 | $0.34 | $0.31 | DeepSeek Chat V3 saves $0.02 (7%) |
| Claude 4 Haiku | DeepSeek Reasoner (R1) | $1.24 | $0.63 | DeepSeek Reasoner (R1) saves $0.61 (49%) |
| Claude Sonnet 4 Lite | DeepSeek Reasoner (R1) | $1.55 | $0.63 | DeepSeek Reasoner (R1) saves $0.92 (59%) |
Full Ranking — All 17 Models
Every model from both providers, ranked by medium project cost.
| # | Model | Provider | Input ($/M) | Medium Project |
|---|---|---|---|---|
| 1 | DeepSeek V3 | DeepSeek | $0.140 | $0.11 |
| 2 | DeepSeek R1 | DeepSeek | $0.140 | $0.16 |
| 3 | DeepSeek Jiuge | DeepSeek | $0.150 | $0.17 |
| 4 | DeepSeek Chat V3 | DeepSeek | $0.270 | $0.31 |
| 5 | DeepSeek Coder V2 | DeepSeek | $0.270 | $0.31 |
| 6 | DeepSeek Coder V3 | DeepSeek | $0.270 | $0.31 |
| 7 | Claude 3 Haiku | Anthropic | $0.250 | $0.34 |
| 8 | DeepSeek V3.2 | DeepSeek | $0.300 | $0.34 |
| 9 | DeepSeek Reasoner (R1) | DeepSeek | $0.550 | $0.63 |
| 10 | Claude 3.5 Haiku | Anthropic | $0.800 | $1.24 |
| 11 | Claude 4 Haiku | Anthropic | $0.800 | $1.24 |
| 12 | Claude Sonnet 4 Lite | Anthropic | $1.00 | $1.55 |
| 13 | Claude 3 Sonnet | Anthropic | $3.00 | $4.05 |
| 14 | Claude Sonnet 4 | Anthropic | $3.00 | $4.66 |
| 15 | Claude 3.5 Sonnet | Anthropic | $3.00 | $4.66 |
| 16 | Claude 3 Opus | Anthropic | $15.00 | $20.25 |
| 17 | Claude Opus 4 | Anthropic | $15.00 | $23.29 |
Explore Individual Comparisons
Detailed side-by-side comparisons between specific models.