This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.

ServiceNow has launched a newer release, Apriel-v1.6-15B-Thinker. We suggest considering it instead.

•

Open weights model

•

Released September 2025

Apriel-v1.5-15B-Thinker API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of Apriel-v1.5-15B-Thinker for your use-case.

Lowest Time per Task

Time per Intelligence Index task (minutes)

Total 1 provider

Lowest Cost per Task

Cost per Intelligence Index task

Total 1 provider

Apriel-v1.5-15B-Thinker is available through Together AI.

Benchmarks of providers are not available for this model.

Please see the models page for Apriel-v1.5-15B-Thinker for details of the model and its intelligence compared to other models.

Inference time (minutes) per Intelligence Index task · Lower is better
No data available
Weighted average cost (USD) per Intelligence Index task · Lower is better
No data available

Pricing

Cost per Intelligence Index Task: Apriel-v1.5-15B-Thinker

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better
No data available

Pricing: Cache Hit, Input, and Output: Apriel-v1.5-15B-Thinker

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: Apriel-v1.5-15B-Thinker

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
No data available

Speed

Average of the single-request and multi-turn agentic workloads measured

Output Speed: Apriel-v1.5-15B-Thinker

Output tokens divided by total request time · Includes time to first token · Average of the single-request and multi-turn agentic workloads measured · Higher is better
No data available

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: Apriel-v1.5-15B-Thinker

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better
No data available

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: Apriel-v1.5-15B-Thinker

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better
No data available

Key Comparison Metrics & API Features

Together AI logoTogether AI
--
--
--
--
131k
Open

Frequently Asked Questions

Common questions about Apriel-v1.5-15B-Thinker providers