Auto-generated comparison

AI21: Jamba Large 1.7 vs Inception: Mercury 2.5 Preview

Inception: Mercury 2.5 Preview wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.

Side-by-side comparison

CapabilityAI21: Jamba Large 1.7Inception: Mercury 2.5 PreviewWinner
Context window
Maximum number of input tokens the model can attend to in a single request.
256K260K🏆 Inception: Mercury 2.5 Preview
Input price (per 1M)
Cost per million input tokens billed by the provider.
$2.00$0.04🏆 Inception: Mercury 2.5 Preview
Output price (per 1M)
Cost per million output tokens billed by the provider.
$8.00$0.15🏆 Inception: Mercury 2.5 Preview
Tool / function calling
First-class support for emitting structured tool calls.
YesYesTie
Vision input
Accepts image inputs alongside text.
Tie
Reasoning mode
Internal chain-of-thought / extended-thinking support.
Yes🏆 Inception: Mercury 2.5 Preview

Frequently asked questions

Is AI21: Jamba Large 1.7 better than Inception: Mercury 2.5 Preview?

Inception: Mercury 2.5 Preview wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.

What's the price difference between AI21: Jamba Large 1.7 and Inception: Mercury 2.5 Preview?

Input: $2.00 vs $0.04 per 1M tokens. Output: $8.00 vs $0.15 per 1M tokens.

What context windows do AI21: Jamba Large 1.7 and Inception: Mercury 2.5 Preview support?

AI21: Jamba Large 1.7 supports up to 256K tokens. Inception: Mercury 2.5 Preview supports up to 260K tokens.

Do both AI21: Jamba Large 1.7 and Inception: Mercury 2.5 Preview support tool calling?

AI21: Jamba Large 1.7: yes. Inception: Mercury 2.5 Preview: yes.

Compare AI21: Jamba Large 1.7 with other models

Compare Inception: Mercury 2.5 Preview with other models