Migrating from gemini-2.0-flash-001 to gemini-3.6-flash

What changes when you move from gemini-2.0-flash-001 to gemini-3.6-flash: prices, limits, features and parameters, read from each company's own pages.

From: gemini-2.0-flash-001
Status: Retired
Shutdown: Jun 1, 2026 at the earliest
Time left: —

To: gemini-3.6-flash
Status: Active
Shutdown: none announced
Time left: —

Prices

USD per 1M tokens, standard tier

Type	gemini-2.0-flash-001	gemini-3.6-flash	Change
Input	Not published	$0.75first seen October 1, 2026 · source	—
Cached input	Not published	$0.075first seen October 1, 2026 · source	—
Output	Not published	$3.75first seen October 1, 2026 · source	—

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens

Limit	gemini-2.0-flash-001	gemini-3.6-flash	Change
Context window	Not published	1,048,576 tokensin place when tracking began (October 6, 2026) · source	—
Max output tokens	Not published	65,536 tokensin place when tracking began (October 6, 2026) · source	—

Benchmarks

Same benchmark and source on both sides; settings named where they differ

Benchmark	gemini-2.0-flash-001	gemini-3.6-flash	Change
Arena TextArena, high effort (vs no setting). Ranges don't overlap.	1360 ±4	1483 ±4	+123
Arena Text: CodingArena, high effort (vs no setting). Ranges don't overlap.	1363 ±7	1518 ±7	+155
Arena VisionArena, high effort (vs no setting). Ranges don't overlap.	1172 ±7	1281 ±8	+109
GPQA DiamondEpoch AI, high effort (vs no setting). Other settings not run → 86.4% low effort not run → 85.9% minimal effort	64.1%	94.1%	+30.0 pts
OTIS Mock AIME 2024-2025Epoch AI, high effort (vs no setting). Other settings not run → 82.2% low effort not run → 80.0% minimal effort	31.1%	94.2%	+63.1 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for gemini-2.0-flash-001: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window, Max output tokens.

Not published for gemini-3.6-flash: Fine-tuning, temperature parameter, top_p parameter, logprobs.

Free tier

gemini-2.0-flash-001: no free tier listed

gemini-3.6-flash: Free tier, in place when tracking began (October 7, 2026) (source) · All free models

gemini-3.6-flash adds a free tier.

Aliases

All aliases

No aliases point at either model.

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
gemini-3.6-flash	Google Cloud Vertex AI	gemini-3.6-flash	Nov 19, 2026Active	35 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

Change the model string from gemini-2.0-flash-001 to gemini-3.6-flash.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: gemini-2.0-flash-001, gemini-3.6-flash.