Sonar Reasoning
Provider: vercel ai gateway ·
vercel_ai_gateway/perplexity/sonar-reasoning Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $1.00 |
| Output | $5.00 |
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$2.00
per month
Medium
10M in / 2000k out
$20.00
per month
Large
100M in / 20000k out
$200
per month
Context
- Input window
- 127,000 tokens
- Max output
- 8,000 tokens
Capabilities
- ⬜ Vision (image input)
- ⬜ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Sonar Reasoning with similar models
Claude 3.5 Haiku
vercel ai gateway
$0.80 in
/ $4.00 out
Claude Haiku 4.5
vercel ai gateway
$1.00 in
/ $5.00 out
Deepseek R1
vercel ai gateway
$0.55 in
/ $2.19 out
Deepseek R1 Distill Llama 70b
vercel ai gateway
$0.75 in
/ $0.99 out
Deepseek V3
vercel ai gateway
$0.90 in
/ $0.90 out
Llama 3.1 70b
vercel ai gateway
$0.72 in
/ $0.72 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.