Live pricing — last refreshed Apr 21, 2026

Anthropic: Claude Haiku 4.5 vs DeepSeek: R1

Head-to-head API pricing and cost comparison between Anthropic’s Anthropic: Claude Haiku 4.5 and DeepSeek’s DeepSeek: R1. Prices auto-refresh daily from OpenRouter.

Verdict

DeepSeek: R1 is 30% cheaper for input tokens; DeepSeek: R1 also wins on output tokens.

Side-by-side comparison

SpecAnthropic: Claude Haiku 4.5DeepSeek: R1
Input price (per 1M)$1.00$0.70
Cached input (per 1M)$0.10
Output price (per 1M)$5.00$2.50
Batch input (per 1M)$0.50
Batch output (per 1M)$2.50
Reasoning price (per 1M)
Context window200K64K
Vision supportYesNo
Caching supportYesNo
Batch APIYesNo
Reasoning capabilityNoNo

Monthly cost at volume

Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).

VolumeAnthropic: Claude Haiku 4.5DeepSeek: R1Savings
1K req/day
500in / 200out tokens
$45.00$25.50$19.50
DeepSeek: R1 wins
10K req/day
1500in / 500out tokens
$1,200$690.00$510.00
DeepSeek: R1 wins
100K req/day
3000in / 800out tokens
$21,000$12,300$8,700
DeepSeek: R1 wins
1M req/day
8000in / 2000out tokens
$540,000$318,000$222,000
DeepSeek: R1 wins
Open in interactive calculator →

Adjust input/output token counts, request volume, batch & cached pricing.

Related comparisons

Frequently asked questions

Which is cheaper, Anthropic: Claude Haiku 4.5 or DeepSeek: R1?

For input tokens, DeepSeek: R1 is roughly 30% cheaper at $0.70/1M vs $1.00/1M. For output tokens, DeepSeek: R1 wins at $2.50/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.

What’s the context window difference?

Anthropic: Claude Haiku 4.5 has a context window of 200K tokens. DeepSeek: R1 offers 64K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.

Should I use Anthropic: Claude Haiku 4.5 or DeepSeek: R1?

Choose Anthropic: Claude Haiku 4.5 if you’re already on the Anthropic stack, want broad ecosystem support, or prefer its feature set. Choose DeepSeek: R1 for DeepSeek’s ecosystem, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.

How are these prices kept current?

Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: Apr 21, 2026.