Perplexity · mid-range · Released 2023-06-01

Sonar Mini: pricing, context window and benchmarks

Sonar Mini is a mid-range model from Perplexity. It offers a 65,536-token context window, costs $6.52 per million input tokens and $35.69 per million output tokens, and averages 67.9 across the index's benchmark suite.

visionmultimodal
Input price
$6.52
per 1M tokens
Output price
$35.69
per 1M tokens
Context
65,536
tokens
Avg score
67.9
rank #383 of 600
Arena Elo
1334.4
modelled
Max output
16,384
tokens

Pricing

Sonar Mini costs $6.52 per million input tokens and $35.69 per million output tokens. A blended 3:1 input-to-output mix works out to about $13.81 per million tokens. Cached input is listed at $0.67 per million tokens.

ItemPriceNotes
Input$6.52per 1M tokens
Output$35.69per 1M tokens
Cached input$0.67per 1M tokens
Blended 3:1$13.81estimate per 1M tokens
1M in + 1M out$42.21estimate

Benchmarks

Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.

BenchmarkScoreRankPercentileRelative
MMLU-Pro 71.2 388 35th
GPQA Diamond 60.4 401 33th
SWE-bench Verified 56.9 369 39th
HumanEval 70.4 390 35th
MATH-500 72.7 360 40th
AIME 2025 60.4 385 36th
LiveCodeBench 55.1 403 33th
IFEval 77.5 373 38th
TruthfulQA 74.0 354 41th
HellaSwag 81.7 355 41th
MMMU 67.0 360 40th
Arena Elo 1334.4 383 36th

What Sonar Mini is good for

Sonar Mini is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $6.52 per million input tokens with a 65,536-token window, check its benchmark profile against the specific task before committing.

Strengths

  • Accepts more than text, including image input where the provider supports it.

Trade-offs

  • Proprietary licence: you cannot download the weights or self-host the model.
  • Average benchmark score is below the index median; test it on your own task.

How it compares

ModelProviderContextInput / 1MAvg score
Mixtral Groq Base Groq 32768 $2.66 68.4
Hunyuan-Turbo Mini Tencent 8192 $6.59 68.3
Molmo Instruct Allen Institute for AI 32768 $2.53 68.3
Sonar Mini Perplexity 65536 $6.52 67.9
Grok 3 Nano xAI 8192 $7.12 67.8
Arctic Base Snowflake 32768 $2.27 67.5

Browse all comparisons →

FAQ

How much does Sonar Mini cost?

Sonar Mini is listed at $6.52 per million input tokens and $35.69 per million output tokens. Cached input is $0.67 per million tokens. A blended 3:1 input-to-output mix is about $13.81 per million tokens.

What is the context window of Sonar Mini?

Sonar Mini has a context window of 65,536 tokens and can emit up to 16,384 output tokens per request in this index.

Is Sonar Mini open weights?

No. Sonar Mini is a proprietary model with a proprietary licence, so you cannot download the weights.

How does Sonar Mini score on benchmarks?

Sonar Mini averages 67.9 across the scored benchmarks in this index, ranking #383 of 600 models. Its strongest relative result is Arena Elo at 1334.4.

What is Sonar Mini best for?

Sonar Mini is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $6.52 per million input tokens with a 65,536-token window, check its benchmark profile against the specific task before committing.

Related