ZMIME
SDAIA · Released Jan 23, 2025

ALLaM-2-7b

ALLaM-2-7b instruction tuned model by SDAIA.

  • Open weights
Capability
—No ECI score yet
Input
—No listed price
Output
—No listed price
Context
4K4K max output
Pricing

What it costs

No per-token price is published for this model yet.

No per-token price is listed for this model on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for ALLaM-2-7b yet.

Specifications

The details

Lab
SDAIA
Released
Jan 23, 2025
Context window
4,096 tokens
Max output
4,096 tokens
Inputs
Text
Output
Text
Reasoning
No
Tool calling
No
Structured output
No
Availability
1 API providerlisted on models.dev
Questions

About ALLaM-2-7b

How much does ALLaM-2-7b cost?

ALLaM-2-7b has no published per-token API price on models.dev yet.

What is the context window of ALLaM-2-7b?

ALLaM-2-7b accepts up to 4,096 tokens per request and can write up to 4,096 tokens in one response.

How good is ALLaM-2-7b?

Epoch AI has not published a Capabilities Index score for ALLaM-2-7b yet.

Is ALLaM-2-7b open source?

Yes. SDAIA publishes the weights, so it can be downloaded and self-hosted.

What inputs does ALLaM-2-7b support?

ALLaM-2-7b accepts text and replies in text. It is not a dedicated reasoning model, does not support tool calling.

When was ALLaM-2-7b released?

SDAIA released ALLaM-2-7b on Jan 23, 2025.

What are the best alternatives to ALLaM-2-7b?

The closest current models from other labs on capability, price and release date are Qwen2.5-VL 72B Instruct (Alibaba (Qwen), $1.01 / $1.01), MiniMax Text 01 (MiniMax) (MiniMax), Aion-RP 1.0 (8B) (Aion Labs, $0.80 / $1.60) and Saba (Mistral AI, $0.20 / $0.60).