Choose AI21: Jamba Large 1.7 if…
- you need to fit long inputs in one request — 256K tokens is roughly 384 pages, against 192
AI21: Jamba Large 1.7 vs LiquidAI: LFM2.5-2.6B
Neither wins outright: AI21: Jamba Large 1.7 is the pick when you need to fit long inputs in one request, LiquidAI: LFM2.5-2.6B when cost matters at scale.
Key numbers
| Spec | AI21: Jamba Large 1.7 | LiquidAI: LFM2.5-2.6B |
|---|---|---|
| Provider | AI21 | Liquid |
| Input price (per 1M tokens) | $2.00 | $0.35 |
| Output price (per 1M tokens) | $8.00 | $0.50 |
| Blended price (3:1 input/output) | $3.50 | $0.39 |
| Cheaper than … of all models we track | 18% | 58% |
| Context window | 256K tokens (~384 pages) | 128K tokens (~192 pages) |
| Larger context than … of all models | 44% | 14% |
| Max output per response | 4K tokens (~3,100 words) | 8K tokens (~6,100 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | Yes |
| Listed since | 2025-08-08 | 2026-08-11 |
Advertisement
What it costs for real workloads
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | AI21: Jamba Large 1.7 | LiquidAI: LFM2.5-2.6B | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $310 | $36.25 | LiquidAI: LFM2.5-2.6B saves $274 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $320 | $47.00 | LiquidAI: LFM2.5-2.6B saves $273 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $336 | $48.00 | LiquidAI: LFM2.5-2.6B saves $288 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $208 | $31.00 | LiquidAI: LFM2.5-2.6B saves $177 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $108 | $18.00 | LiquidAI: LFM2.5-2.6B saves $90.00 |
Capabilities side by side
| Capability | AI21: Jamba Large 1.7 | LiquidAI: LFM2.5-2.6B | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | — | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | — | — | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | — | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | — | ✓ Yes | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Price history
- AI21: Jamba Large 1.7: price unchanged since we started tracking it on 2026-03-10.
- LiquidAI: LFM2.5-2.6B: price unchanged since we started tracking it on 2026-10-25.
Which should you choose?
Choose LiquidAI: LFM2.5-2.6B if…
- cost matters at scale — it is 89% cheaper on a typical 3:1 input/output mix ($36.25 vs $310 a month for 50,000 support chats)
- you need reasoning / thinking mode — to spend extra tokens thinking before answering hard problems; AI21: Jamba Large 1.7 does not advertise it
- you need seed (reproducible sampling) — to repeat a generation for tests and evals; AI21: Jamba Large 1.7 does not advertise it
- you need log-probabilities — to read token confidence for classification and scoring; AI21: Jamba Large 1.7 does not advertise it
- you generate long outputs in one go — up to 8K tokens (about 6,100 words) per response
- you want to prototype at zero cost — a free variant is listed
- you want the newer model — released 2026-08-11, 12 months after the other
Frequently asked questions
Is AI21: Jamba Large 1.7 better than LiquidAI: LFM2.5-2.6B?
Neither wins outright: AI21: Jamba Large 1.7 is the pick when you need to fit long inputs in one request, LiquidAI: LFM2.5-2.6B when cost matters at scale. In short: AI21: Jamba Large 1.7 when you need to fit long inputs in one request; LiquidAI: LFM2.5-2.6B when cost matters at scale, you need reasoning / thinking mode, you need seed (reproducible sampling), you need log-probabilities, you generate long outputs in one go, you want to prototype at zero cost, you want the newer model.
Which is cheaper, AI21: Jamba Large 1.7 or LiquidAI: LFM2.5-2.6B?
LiquidAI: LFM2.5-2.6B is cheaper: $0.39 vs $3.50 per 1M tokens at a typical 3:1 input/output mix, 89% less. For 50,000 support conversations a month that is $36.25 against $310.
How much do AI21: Jamba Large 1.7 and LiquidAI: LFM2.5-2.6B cost per million tokens?
AI21: Jamba Large 1.7 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens; LiquidAI: LFM2.5-2.6B costs $0.35 input and $0.50 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, AI21: Jamba Large 1.7 or LiquidAI: LFM2.5-2.6B?
AI21: Jamba Large 1.7: 256K tokens, about 384 pages, against 128K (about 192 pages) for LiquidAI: LFM2.5-2.6B.
Do AI21: Jamba Large 1.7 and LiquidAI: LFM2.5-2.6B support function calling and JSON output?
Tool calling — AI21: Jamba Large 1.7: yes, LiquidAI: LFM2.5-2.6B: yes. JSON-schema structured output — AI21: Jamba Large 1.7: yes, LiquidAI: LFM2.5-2.6B: yes.
Can AI21: Jamba Large 1.7 or LiquidAI: LFM2.5-2.6B read images?
Neither accepts image input — both are text-in models.
Is AI21: Jamba Large 1.7 or LiquidAI: LFM2.5-2.6B free to use?
LiquidAI: LFM2.5-2.6B has a free variant (liquid/lfm-2.5-2.6b:free). Free variants usually carry tighter rate limits.
What is the maximum output length of AI21: Jamba Large 1.7 and LiquidAI: LFM2.5-2.6B?
AI21: Jamba Large 1.7 can write up to 4K tokens (about 3,100 words) per response; LiquidAI: LFM2.5-2.6B up to 8K (about 6,100 words).
When were AI21: Jamba Large 1.7 and LiquidAI: LFM2.5-2.6B released?
AI21: Jamba Large 1.7 was listed on 2025-08-08; LiquidAI: LFM2.5-2.6B on 2026-08-11.
About the two models
AI21: Jamba Large 1.7
Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...
Full AI21: Jamba Large 1.7 specs →LiquidAI: LFM2.5-2.6B
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Full LiquidAI: LFM2.5-2.6B specs →