SSyncDev

AI model comparison

North Mini Code vs Gemini 3 Flash Preview

Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.

North Mini Code from Cohere lists 256K context, 64K maximum output, $0.00 input per 1M tokens, $0.00 output per 1M tokens. Gemini 3 Flash Preview from Google lists 1.05M context, 65.54K maximum output, $0.50 input per 1M tokens, $3.00 output per 1M tokens. Compare the inputs, outputs and deployment options below to see which fits your workflow.

Side-by-sideCapabilities and practical differences

Cohere

North Mini Code

North Mini Code from Cohere: Cohere coding model for practical software engineering and agentic edits.

Context
256K
Max output
64K
Input / 1M tokens
$0.00
Output / 1M tokens
$0.00

Accepts

  • Text input

Produces

  • Text output
Full model profilegithub.com ↗
VS

Google

Gemini 3 Flash Preview

Gemini 3 Flash Preview from Google: New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs.

Context
1.05M
Max output
65.54K
Input / 1M tokens
$0.50
Output / 1M tokens
$3.00

Accepts

  • Text input
  • Image input
  • Video input
  • Audio input
  • PDF input

Produces

  • Text output
Full model profilegithub.com ↗

At a glance

Key differences

Compare the available figures below, then try both models on the work you need to do.

North Mini Code

  • Input price: $0.00
  • Output price: $0.00

Gemini 3 Flash Preview

  • Context capacity: 1.05M
  • Maximum output: 65.54K

Context capacity

Higher listed limit

North Mini Code:256K

Gemini 3 Flash Preview:1.05M

Gemini 3 Flash Preview

Maximum output

Higher listed limit

North Mini Code:64K

Gemini 3 Flash Preview:65.54K

Gemini 3 Flash Preview

Input price

Lower listed token rate

North Mini Code:$0.00

Gemini 3 Flash Preview:$0.50

North Mini Code

Output price

Lower listed token rate

North Mini Code:$0.00

Gemini 3 Flash Preview:$3.00

North Mini Code

Specifications

Pricing, limits and capabilities

Specifications for North Mini Code and Gemini 3 Flash Preview. Higher limits and lower prices describe these figures only.
SpecificationNorth Mini CodeGemini 3 Flash Preview
ProviderCohereGoogle
Listed pricing routeCohereGoogle
Model familynorthgemini-flash
Accepted inputstexttext, image, video, audio, pdf
Produced outputstexttext
Context window256K1.05MHigher
Max output64K65.54KHigher
Input price / 1M$0.00Lower$0.50
Output price / 1M$0.00Lower$3.00
Reasoning modeDocumentedDocumented
Tool callingDocumentedDocumented
Image inputNot documentedDocumented
Audio inputNot documentedDocumented
Structured outputDocumentedDocumented
LicenseOpen weightsProprietary

Workload guidance

Which model should you choose?

Consider North Mini Code if you need a lower listed input rate or a lower listed output rate. Consider Gemini 3 Flash Preview if you need larger context or larger maximum output. North Mini Code offers downloadable weights; Gemini 3 Flash Preview is listed as a proprietary model. Compare licence terms and operating costs before choosing a deployment. Test both on the same representative examples and judge the output against your acceptance criteria. Include tool failures, retries and the time to a completed task.

Documentation and model profiles

Explore each model’s features, API requirements and licence terms in the sources below.

Questions people ask

It brings together documented inputs and outputs, token limits, deployment terms and available pricing. When both models have source-linked, verified results on a shared benchmark, those results are shown with their individual sources. The comparison is a starting point for evaluating your own workload.

Compare a different pair

Search by model or provider to explore another comparison.

Open model comparison