Groq (host) · LLMs & Coding
ALLaM-2-7b
Catalog data · checked Nov 16, 2026
ALLaM-2-7b is a language model from Groq (host), released in January 2025. It reads text and writes text, with a context window of 4.1K tokens and up to 4.1K output tokens per answer. It is currently listed at no charge.
Input price$0per 1M tokens
Output price$0per 1M tokens
Context window4.1Ktokens per request
Max output4.1Ktokens per answer
ReleasedJan 2025Jan 2025
WeightsOpencan be self-hosted
What it can do
- Tool calling
- Structured output
- Reasoning mode
- Image input
- File input
- Audio input
- Video input
- Image output
- Audio output
- Prompt caching
What it costs in practice
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $0 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | too long |
| 10,000 product descriptions300 input and 200 output tokens per text | $0 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $0 |
Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →
Compare ALLaM-2-7b with
Qwen3.8 27BGroq (host)$0.8 / $4Safety GPT OSS 20BGroq (host)$0.075 / $0.3GPT OSS 120BGroq (host)$0.15 / $0.6GPT OSS 20BGroq (host)$0.075 / $0.3Muse EmberMeta$0.1 / $0.5Claude Haiku 5.5Anthropic$0.1 / $0.5Qwen3.8 Omni FlashAlibaba (Qwen)$0.15 / $0.47Qwen3.7 FlashAlibaba (Qwen)$0.03 / $0.13Command R7B ArabicCohere$0.0375 / $0.15Command R7BCohere$0.0375 / $0.15
Questions & answers
How much does ALLaM-2-7b cost?
ALLaM-2-7b is currently listed free of charge in the public API catalog.
How large is the context window of ALLaM-2-7b?
ALLaM-2-7b can process up to 4,096 tokens per request and return up to 4,096 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.
Does ALLaM-2-7b support tool calling?
No tool calling is listed for this model in the catalog.
Can ALLaM-2-7b read images?
No, this model accepts text only.
