DeepSeek: DeepSeek V4 Pro 0813 vs Anthropic: Claude Haiku 4.5
Head-to-head API pricing and cost comparison between DeepSeek’s DeepSeek: DeepSeek V4 Pro 0813 and Anthropic’s Anthropic: Claude Haiku 4.5. Prices auto-refresh daily from OpenRouter.
DeepSeek: DeepSeek V4 Pro 0813 is 56% cheaper for input tokens; DeepSeek: DeepSeek V4 Pro 0813 also wins on output tokens.
Side-by-side comparison
| Spec | DeepSeek: DeepSeek V4 Pro 0813 | Anthropic: Claude Haiku 4.5 |
|---|---|---|
| Input price (per 1M) | $0.43 | $1.00 |
| Cached input (per 1M) | $0.00 | $0.10 |
| Output price (per 1M) | $0.87 | $5.00 |
| Batch input (per 1M) | — | $0.50 |
| Batch output (per 1M) | — | $2.50 |
| Reasoning price (per 1M) | — | — |
| Context window | 1049K | 200K |
| Vision support | No | Yes |
| Caching support | Yes | Yes |
| Batch API | No | Yes |
| Reasoning capability | No | No |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | DeepSeek: DeepSeek V4 Pro 0813 | Anthropic: Claude Haiku 4.5 | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $11.75 | $45.00 | $33.25 DeepSeek: DeepSeek V4 Pro 0813 wins |
10K req/day 1500in / 500out tokens | $326.25 | $1,200 | $873.75 DeepSeek: DeepSeek V4 Pro 0813 wins |
100K req/day 3000in / 800out tokens | $6,003 | $21,000 | $14,997 DeepSeek: DeepSeek V4 Pro 0813 wins |
1M req/day 8000in / 2000out tokens | $156,600 | $540,000 | $383,400 DeepSeek: DeepSeek V4 Pro 0813 wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
- Anthropic: Claude Haiku 4.5 (batch) vs DeepSeek: DeepSeek V4 Pro 0813Compare pricing →
- Anthropic: Claude Opus 4.7 vs DeepSeek: DeepSeek V4 Pro 0813Compare pricing →
- Anthropic: Claude Opus 4.7 (batch) vs DeepSeek: DeepSeek V4 Pro 0813Compare pricing →
- Anthropic: Claude Opus 4.7 (Fast) vs DeepSeek: DeepSeek V4 Pro 0813Compare pricing →
Frequently asked questions
Which is cheaper, DeepSeek: DeepSeek V4 Pro 0813 or Anthropic: Claude Haiku 4.5?
For input tokens, DeepSeek: DeepSeek V4 Pro 0813 is roughly 56% cheaper at $0.43/1M vs $1.00/1M. For output tokens, DeepSeek: DeepSeek V4 Pro 0813 wins at $0.87/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.
What’s the context window difference?
DeepSeek: DeepSeek V4 Pro 0813 has a context window of 1049K tokens. Anthropic: Claude Haiku 4.5 offers 200K 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 DeepSeek: DeepSeek V4 Pro 0813 or Anthropic: Claude Haiku 4.5?
Choose DeepSeek: DeepSeek V4 Pro 0813 if you’re already on the DeepSeek stack, want broad ecosystem support, or prefer its lower input price. Choose Anthropic: Claude Haiku 4.5 for Anthropic’s ecosystem, native vision input, or its differentiated capabilities. 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: Aug 13, 2026.