Choose AI21: Jamba Large 1.7 if…
- you need structured output (JSON schema) — to return JSON that validates against your schema; Cohere: North Mini Code (free) does not advertise it
AI21: Jamba Large 1.7 vs Cohere: North Mini Code (free)
Neither wins outright: AI21: Jamba Large 1.7 is the pick when you need structured output (JSON schema), Cohere: North Mini Code (free) when cost matters at scale.
Key numbers
| Spec | AI21: Jamba Large 1.7 | Cohere: North Mini Code (free) |
|---|---|---|
| Provider | AI21 | Cohere |
| Input price (per 1M tokens) | $2.00 | $0 |
| Output price (per 1M tokens) | $8.00 | $0 |
| Blended price (3:1 input/output) | $3.50 | $0 |
| Cheaper than … of all models we track | 18% | 90% |
| Context window | 256K tokens (~384 pages) | 256K tokens (~384 pages) |
| Larger context than … of all models | 45% | 45% |
| Max output per response | 4K tokens (~3,100 words) | 64K tokens (~48,000 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | Yes |
| Listed since | 2025-08-08 | 2026-06-17 |
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 | Cohere: North Mini Code (free) | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $310 | $0 | Cohere: North Mini Code (free) saves $310 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $320 | $0 | Cohere: North Mini Code (free) saves $320 |
| 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 | $0 | Cohere: North Mini Code (free) saves $336 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $208 | $0 | Cohere: North Mini Code (free) saves $208 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $108 | $0 | Cohere: North Mini Code (free) saves $108 |
Capabilities side by side
| Capability | AI21: Jamba Large 1.7 | Cohere: North Mini Code (free) | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ 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 | — | — | 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.
- Cohere: North Mini Code (free): price unchanged since we started tracking it on 2026-08-06.
Which should you choose?
Choose Cohere: North Mini Code (free) if…
- cost matters at scale — it is 100% cheaper on a typical 3:1 input/output mix ($0 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 generate long outputs in one go — up to 64K tokens (about 48,000 words) per response
- you want to prototype at zero cost — a free variant is listed
- you want the newer model — released 2026-06-17, 10 months after the other
Frequently asked questions
Is AI21: Jamba Large 1.7 better than Cohere: North Mini Code (free)?
Neither wins outright: AI21: Jamba Large 1.7 is the pick when you need structured output (JSON schema), Cohere: North Mini Code (free) when cost matters at scale. In short: AI21: Jamba Large 1.7 when you need structured output (JSON schema); Cohere: North Mini Code (free) when cost matters at scale, you need reasoning / thinking mode, you need seed (reproducible sampling), 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 Cohere: North Mini Code (free)?
Cohere: North Mini Code (free) is cheaper: $0 vs $3.50 per 1M tokens at a typical 3:1 input/output mix, 100% less. For 50,000 support conversations a month that is $0 against $310.
How much do AI21: Jamba Large 1.7 and Cohere: North Mini Code (free) cost per million tokens?
AI21: Jamba Large 1.7 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens; Cohere: North Mini Code (free) costs $0 input and $0 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, AI21: Jamba Large 1.7 or Cohere: North Mini Code (free)?
Both take 256K tokens per request — roughly 384 pages of text.
Do AI21: Jamba Large 1.7 and Cohere: North Mini Code (free) support function calling and JSON output?
Tool calling — AI21: Jamba Large 1.7: yes, Cohere: North Mini Code (free): yes. JSON-schema structured output — AI21: Jamba Large 1.7: yes, Cohere: North Mini Code (free): not advertised.
Can AI21: Jamba Large 1.7 or Cohere: North Mini Code (free) read images?
Neither accepts image input — both are text-in models.
Is AI21: Jamba Large 1.7 or Cohere: North Mini Code (free) free to use?
Cohere: North Mini Code (free) has a free variant (cohere/north-mini-code:free). Free variants usually carry tighter rate limits.
What is the maximum output length of AI21: Jamba Large 1.7 and Cohere: North Mini Code (free)?
AI21: Jamba Large 1.7 can write up to 4K tokens (about 3,100 words) per response; Cohere: North Mini Code (free) up to 64K (about 48,000 words).
When were AI21: Jamba Large 1.7 and Cohere: North Mini Code (free) released?
AI21: Jamba Large 1.7 was listed on 2025-08-08; Cohere: North Mini Code (free) on 2026-06-17.
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 →Cohere: North Mini Code (free)
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
Full Cohere: North Mini Code (free) specs →