Very long inputs
Choose Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite reads up to 1.05M tokens per request, against 256k for North Mini Code.
Gemini 3.5 Flash-Lite vs North Mini Code: price, context and capabilities
Choose Gemini 3.5 Flash-Lite for very long inputs, the hardest reasoning tasks, reasoning over long documents, images as input and the latest release; on the other points the two are level or the data is missing.
In short
- A price comparison is not possible: one of them has no comparable published price.
- Gemini 3.5 Flash-Lite reads more per request: 1.05M tokens against 256k.
- Gemini 3.5 Flash-Lite is the newer model (July 2026, against Jun 9, 2026).
- Only Gemini 3.5 Flash-Lite offers vision, reasoning, structured output, prompt caching, batch api.
Which should you choose?
Each answer below comes straight from the published prices, specifications and independent benchmark results.
Hardest reasoning tasks
Choose Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite scores 22.2 on the Artificial Analysis Intelligence Index, against 9.9 for North Mini Code.
Reasoning over long documents
Choose Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite scores 76% on Long-context reasoning (AA-LCR), against 37.3% for North Mini Code.
Images as input
Choose Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite accepts images as input; North Mini Code does not.
Latest release
Choose Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is the newer release (July 2026, against Jun 9, 2026 for North Mini Code).
Specifications side by side
| Gemini 3.5 Flash-Lite | North Mini Code | |
|---|---|---|
| Provider | Cohere | |
| Category | Language models | Language models |
| Status | Generally available | Generally available |
| Headline price | $0.85 / 1M tokens | No data |
| Input | $0.30 / 1M tokens | No data |
| Output | $2.50 / 1M tokens | No data |
| Cached input | $0.03 / 1M tokens | No data |
| Context window | 1.05M | 256k |
| Max output | 66k | 64k |
| Released | July 2026 | Jun 9, 2026 |
| Knowledge cutoff | No data | No data |
| Licence | Proprietary | Proprietary |
| Capabilities | Vision, Reasoning, Tool calling, Structured output, Prompt caching, Batch API | Tool calling |
| API model id | gemini-3.5-flash-lite | north-mini-code-1-0 |
Benchmarks side by side
Leader in bold.
| Benchmark | Gemini 3.5 Flash-Lite | North Mini Code |
|---|---|---|
| Intelligence Index | 22.2 | 9.9 |
| SciCode | 41.3% | 38.8% |
| GPQA Diamond | 83.8% | 75.7% |
| Humanity's Last Exam | 18.8% | 11.1% |
| Long-context reasoning (AA-LCR) | 76% | 37.3% |
| MMMU-Pro (visual reasoning) | 79% | No data |
| Terminal-Bench Hard | No data | 31.1% |
| IFBench (instruction following) | No data | 57.6% |
| τ²-Bench (agentic tool use) | No data | 37.4% |
Independent evaluations by Artificial Analysis, run the same way for every model, at the reasoning setting shown. Percentages unless marked as an index.
Frequently asked questions
Should I choose Gemini 3.5 Flash-Lite or North Mini Code?
Choose Gemini 3.5 Flash-Lite for very long inputs, the hardest reasoning tasks, reasoning over long documents, images as input and the latest release; on the other points the two are level or the data is missing.
Which is cheaper, Gemini 3.5 Flash-Lite or North Mini Code?
A price comparison is not possible: one of them has no comparable published price.
Which has the larger context window, Gemini 3.5 Flash-Lite or North Mini Code?
Gemini 3.5 Flash-Lite reads more per request: 1.05M tokens against 256k.
What is the difference between Gemini 3.5 Flash-Lite and North Mini Code?
Gemini 3.5 Flash-Lite is made by Google and North Mini Code by Cohere. A price comparison is not possible: one of them has no comparable published price. Gemini 3.5 Flash-Lite reads more per request: 1.05M tokens against 256k. Gemini 3.5 Flash-Lite is the newer model (July 2026, against Jun 9, 2026). Only Gemini 3.5 Flash-Lite offers vision, reasoning, structured output, prompt caching, batch api.
Which is newer, Gemini 3.5 Flash-Lite or North Mini Code?
Gemini 3.5 Flash-Lite was released on July 2026 and North Mini Code on Jun 9, 2026.