Claude 3 Opus
Provider: vercel ai gateway ·
vercel_ai_gateway/anthropic/claude-3-opus Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $15.00 |
| Output | $75.00 |
| Cached input (read) | $1.50 |
| Cache write | $18.75 |
💡 With prompt caching, you save up to 90% on cached input tokens — massive for repeated context like system prompts, RAG retrieval, or long conversations.
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$25.95
per month
Saves $4.05 via caching
Medium
10M in / 2000k out
$260
per month
Saves $40.50 via caching
Large
100M in / 20000k out
$2595
per month
Saves $405 via caching
Context
- Input window
- 200,000 tokens
- Max output
- 4,096 tokens
Capabilities
- ✅ Vision (image input)
- ✅ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ✅ JSON / response schema
Compare Claude 3 Opus with similar models
Claude 4 Opus
vercel ai gateway
$15.00 in
/ $75.00 out
Claude Opus 4
vercel ai gateway
$15.00 in
/ $75.00 out
Claude Opus 4.1
vercel ai gateway
$15.00 in
/ $75.00 out
Gpt 4 Turbo
vercel ai gateway
$10.00 in
/ $30.00 out
O1
vercel ai gateway
$15.00 in
/ $60.00 out
Claude Opus 4.5
vercel ai gateway
$5.00 in
/ $25.00 out
Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.