chooseaimodel
← All models

Claude 3.5 Haiku vs DeepSeek R1

List-price comparison · Claude 3.5 Haiku details · DeepSeek R1 details

For a typical workload (100,000 requests / mo), DeepSeek R1 costs 43% less $146.00/mo vs $256.00/mo.

 Claude 3.5 HaikuDeepSeek R1
Input / 1M tokens$0.800$0.500
Output / 1M tokens$4.00$2.15
Typical request (1,200 in + 400 out)$0.0026$0.0015
Context window200k tokens163,840 tokens
Max output8,192 tokens32,768 tokens
TierBalancedFlagship
ProviderAnthropicDeepSeek

Projected monthly cost

Rows open both models in the calculator — adjust volume and token counts there.

Claude 3.5 Haiku

Auto-synced from OpenRouter — no editorial write-up yet.

DeepSeek R1

Chain-of-thought reasoning competitive with closed flagship models on math and logic benchmarks, at open-weight pricing.

Emits long reasoning traces that inflate output token counts and cost — cap reasoning length or use a distilled variant for latency-sensitive paths.

More comparisons

Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.