Live pricing — last refreshed Apr 21, 2026

Anthropic: Claude Sonnet 4.6 vs OpenAI: GPT-4o-mini Search Preview

Head-to-head API pricing and cost comparison between Anthropic’s Anthropic: Claude Sonnet 4.6 and OpenAI’s OpenAI: GPT-4o-mini Search Preview. Prices auto-refresh daily from OpenRouter.

Verdict

OpenAI: GPT-4o-mini Search Preview is 95% cheaper for input tokens; OpenAI: GPT-4o-mini Search Preview also wins on output tokens.

Side-by-side comparison

SpecAnthropic: Claude Sonnet 4.6OpenAI: GPT-4o-mini Search Preview
Input price (per 1M)$3.00$0.15
Cached input (per 1M)$0.30
Output price (per 1M)$15.00$0.60
Batch input (per 1M)$1.50$0.07
Batch output (per 1M)$7.50$0.30
Reasoning price (per 1M)
Context window1000K128K
Vision supportYesNo
Caching supportYesNo
Batch APIYesYes
Reasoning capabilityNoNo

Monthly cost at volume

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

VolumeAnthropic: Claude Sonnet 4.6OpenAI: GPT-4o-mini Search PreviewSavings
1K req/day
500in / 200out tokens
$135.00$5.85$129.15
OpenAI: GPT-4o-mini Search Preview wins
10K req/day
1500in / 500out tokens
$3,600$157.50$3,443
OpenAI: GPT-4o-mini Search Preview wins
100K req/day
3000in / 800out tokens
$63,000$2,790$60,210
OpenAI: GPT-4o-mini Search Preview wins
1M req/day
8000in / 2000out tokens
$1,620,000$72,000$1,548,000
OpenAI: GPT-4o-mini Search Preview 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 Sonnet 4.6 or OpenAI: GPT-4o-mini Search Preview?

For input tokens, OpenAI: GPT-4o-mini Search Preview is roughly 95% cheaper at $0.15/1M vs $3.00/1M. For output tokens, OpenAI: GPT-4o-mini Search Preview wins at $0.60/1M. 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 Sonnet 4.6 has a context window of 1000K tokens. OpenAI: GPT-4o-mini Search Preview offers 128K 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 Sonnet 4.6 or OpenAI: GPT-4o-mini Search Preview?

Choose Anthropic: Claude Sonnet 4.6 if you’re already on the Anthropic stack, want broad ecosystem support, or prefer its feature set. Choose OpenAI: GPT-4o-mini Search Preview for OpenAI’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.