Claude 3 7 Sonnet Latest
Provider: deepinfra ·
deepinfra/anthropic/claude-3-7-sonnet-latest Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $3.30 |
| Output | $16.50 |
| Cached input (read) | $0.33 |
💡 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
$5.71
per month
Saves $0.89 via caching
Medium
10M in / 2000k out
$57.09
per month
Saves $8.91 via caching
Large
100M in / 20000k out
$571
per month
Saves $89.10 via caching
Context
- Input window
- 200,000 tokens
- Max output
- 200,000 tokens
Capabilities
- ⬜ Vision (image input)
- ✅ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Claude 3 7 Sonnet Latest with similar models
Claude 4 Sonnet
deepinfra
$3.30 in
/ $16.50 out
Hermes 3 Llama 3.1 405B
deepinfra
$1.00 in
/ $1.00 out
Hermes 3 Llama 3.1 70B
deepinfra
$0.30 in
/ $0.30 out
QwQ 32B
deepinfra
$0.15 in
/ $0.40 out
Qwen2.5 VL 32B Instruct
deepinfra
$0.20 in
/ $0.60 out
Qwen3 235B A22B Instruct 2507
deepinfra
$0.09 in
/ $0.60 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.