Sonar Reasoning
vercel/sonar-reasoning提供： vercel · ファミリー: sonar-reasoning · リリース 2025-02-19 · 知識カットオフ: 2025-09
⚠ これはコミュニティのファインチューン / 派生モデルで、ベンダーの公式リリースではありません。
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
機能一覧
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding13
- Tool calling0/40
- Structured output0/20
- Reasoning10/10
- Context window (100K → 1M)2/20
- Provider availability1/10
Agents21
- Tool calling0/35
- Structured output0/25
- Reasoning15/15
- Output token limit5/15
- Provider availability1/10
JSON / structured output18
- Structured output / JSON mode0/50
- Tool calling0/20
- Temperature control10/10
- Price-friendly for high-volume8/20
Cost efficiency43
- Headline price (log-scaled)43/95
- Has prompt-cache pricing0/5
Long context45
- Context window (100K → 2M)35/90
- Has published price for full window10/10
Production-readiness50
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)0/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $7.50 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $15.00 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $4.50 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $13.00 $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $15.00 $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
料金詳細
推奨料金 (提供元): vercel · perplexity/sonar-reasoning
1 か所で利用可能
| プロバイダー | プロバイダーモデルID | 入力 / 1M | 出力 / 1M | コンテキスト | リリース日 |
|---|---|---|---|---|---|
| Vercel AI Gateway vercel | perplexity/sonar-reasoning | $1.00 | $5.00 | 127K | 2025-02-19 |
Frequently asked questions
How much does Sonar Reasoning cost?
Sonar Reasoning costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, sourced from vercel. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Sonar Reasoning?
Sonar Reasoning has a context window of 127K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.
Does Sonar Reasoning support tool calling?
No. Sonar Reasoning does not support tool calling (function calling). If your workflow requires it, look at the /capabilities/tool-calling list for alternatives.
Does Sonar Reasoning support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Sonar Reasoning in our data source. Verify with vercel's official documentation before relying on it in production.
Can Sonar Reasoning accept image input?
No. Sonar Reasoning only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Sonar Reasoning open-weight?
No. Sonar Reasoning is a proprietary model — only vercel (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Sonar Reasoning?
If Sonar Reasoning doesn't fit, consider Trinity Mini, Trinity Large Thinking, Trinity Large Preview. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More vercel models
- Trinity Mini$0.05 in / $0.15 out
- Trinity Large Thinking$0.25 in / $0.90 out
- Trinity Large Preview$0.25 in / $1.00 out
- INTELLECT 3$0.20 in / $1.10 out
- Titan Text Embeddings V2$0.02 in / $0.00 out
最終更新：
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.