Skip to content
Toolsummary LLM price ledger

Sonar Reasoning pricing

Source: litellm · updated 2026-11-17

Short answer: Sonar Reasoning costs $1.00 per million input tokens and $5.00 per million output tokens. That is a 3:1 blended rate of $2.00 per million tokens, ranking it #550 of 823 tracked models by input price.
Input / 1M
$1.00
Output / 1M
$5.00
Output ÷ input
5.00×
Context window
127,000

Price breakdown

MetricUSD
Input, per 1M tokens$1.00
Output, per 1M tokens$5.00
Output ÷ input multiple5.00×
3:1 blended, per 1M tokens$2.00
Context window127,000 tokens
Vendorvercel_ai_gateway

What a typical workload costs

Monthly volumeInput costOutput costTotal
1M in / 250K out$1.00$1.25$2.25
10M in / 2.5M out$10.00$12.50$22.50
100M in / 25M out$100$125$225

Other vercel_ai_gateway models

ModelInputOutput
Ministral 3 B$0.040$0.040
Llama 3.8 B$0.050$0.080
Devstral Small$0.070$0.280
Qwen 3 14 B$0.080$0.240
Qwen 3 30 B$0.100$0.300

Cheaper alternatives

Next cheaper option: GLM 4.5 Airx at $1.10 per 1M input tokens. Next step up: DeepSeek V4 Pro Variant 2 at $1.65 per 1M input tokens.


Spotted a price that is out of date? Submit a correction.