Anthropic: Claude 3.5 Haiku vs xAI: Grok 4.20
Head-to-head API pricing and cost comparison between Anthropic’s Anthropic: Claude 3.5 Haiku and xAI’s xAI: Grok 4.20. Prices auto-refresh daily from OpenRouter.
Anthropic: Claude 3.5 Haiku is 36% cheaper for input tokens; xAI: Grok 4.20 wins on output tokens at $2.50/1M.
Side-by-side comparison
| Spec | Anthropic: Claude 3.5 Haiku | xAI: Grok 4.20 |
|---|---|---|
| Input price (per 1M) | $0.80 | $1.25 |
| Cached input (per 1M) | $0.08 | $0.20 |
| Output price (per 1M) | $4.00 | $2.50 |
| Batch input (per 1M) | $0.40 | — |
| Batch output (per 1M) | $2.00 | — |
| Reasoning price (per 1M) | — | — |
| Context window | 200K | 2000K |
| Vision support | Yes | Yes |
| Caching support | Yes | Yes |
| Batch API | Yes | No |
| Reasoning capability | No | No |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | Anthropic: Claude 3.5 Haiku | xAI: Grok 4.20 | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $36.00 | $33.75 | $2.25 xAI: Grok 4.20 wins |
10K req/day 1500in / 500out tokens | $960.00 | $937.50 | $22.50 xAI: Grok 4.20 wins |
100K req/day 3000in / 800out tokens | $16,800 | $17,250 | $450.00 Anthropic: Claude 3.5 Haiku wins |
1M req/day 8000in / 2000out tokens | $432,000 | $450,000 | $18,000 Anthropic: Claude 3.5 Haiku wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
Frequently asked questions
Which is cheaper, Anthropic: Claude 3.5 Haiku or xAI: Grok 4.20?
For input tokens, Anthropic: Claude 3.5 Haiku is roughly 36% cheaper at $0.80/1M vs $1.25/1M. For output tokens, xAI: Grok 4.20 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 3.5 Haiku has a context window of 200K tokens. xAI: Grok 4.20 offers 2000K 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 3.5 Haiku or xAI: Grok 4.20?
Choose Anthropic: Claude 3.5 Haiku if you’re already on the Anthropic stack, want broad ecosystem support, or prefer its lower input price. Choose xAI: Grok 4.20 for xAI’s ecosystem, native vision input, or its cheaper output 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: May 31, 2026.