Gemini 3.5 Flash
TL;DR
PremiumPro-level coding proficiency with parallel agentic execution.
Available on
Not on the Go plan ($1/mo, open-source models only).
Switch with
Pick Gemini 3.5 Flash from the selector.
Intelligence Index
Gemini 3.5 Flash vs the top of the lineup
Claude Fable 5
GPT-5.6 Sol
Claude Opus 4.8
Gemini 3.5 Flash
Speed
~236
tokens / sec
Input
$1.50
per M tokens
Output
$9
per M tokens
Gemini 3.5 Flash in Command Code
Gemini 3.5 Flash is Google's premium model — Pro-level coding proficiency, parallel agentic execution. It runs in Command Code with a 1M-token context window, switchable any time with /model.
It scores 50.2 on the Intelligence Index — #13 of the 38 scored models in the Command Code lineup.
Gemini 3.5 Flash specs at a glance
What Gemini 3.5 Flash accepts, how much it can hold in context, and what you need to run it.
| Spec | Gemini 3.5 Flash |
|---|---|
| Context window | 1M tokens |
| Input modalities | text + images |
| Reasoning | Yes — efforts: low, medium, high |
| Release date | 2026-05-19 |
| Minimum plan | Pro |
Gemini 3.5 Flash vs the Command Code lineup
Gemini 3.5 Flash alongside its nearest real alternatives in the lineup — every price straight from the billing tables.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | 59.9 | 76.5 | ~62 tok/s | $10.00 | $50.00 | $20 | 1M |
| GPT-5.4 | 51.4 | 71.1 | ~164 tok/s | $2.50 | $15.00 | $5.625 | 400K |
| GPT-5.6 Luna | 51.2 | 71.4 | ~234 tok/s | $1.00 | $6.00 | $2.25 | 1.1M |
| GLM-5.2 | 51.1 | 68.8 | ~208 tok/s | $1.40 | $4.40 | $2.15 | 1M |
| Muse Spark 1.1 | 50.6 | 71.3 | ~130 tok/s | $1.25 | $4.25 | $2 | 1M |
| Gemini 3.5 Flash (this page) | 50.2 | 70.1 | ~236 tok/s | $1.50 | $9.00 | $3.375 | 1M |
| Tencent Hy3 | 41.2 | 58.8 | ~58 tok/s | $0.00 | $0.00 | free | 262K |
What Gemini 3.5 Flash is best for
Gemini 3.5 Flash earns its slot in the lineup for fast lookups and quick edits, long-context work across big codebases.
- Fast lookups and quick edits — pick Gemini 3.5 Flash from /model and it applies to the session.
- Long-context work across big codebases — pick Gemini 3.5 Flash from /model and it applies to the session.
When to switch away from Gemini 3.5 Flash
No single model wins every task. These are Gemini 3.5 Flash's computed nearest alternatives — one step up, one step down in cost, one for speed, one from the same family — each switchable mid-session with /model.
Switch to Muse Spark 1.1
Muse Spark 1.1 scores 50.6 on the Intelligence Index to Gemini 3.5 Flash's 50.2 — the nearest genuine step up — at $2 blended per million tokens versus $3.375. Reach for it when a task keeps hitting Gemini 3.5 Flash's ceiling.
Switch to Grok 4.5
Grok 4.5 runs about 11% cheaper blended ($3 versus $3.375 per million tokens) while scoring 53.8 on the Intelligence Index. Switch down for high-volume work where Gemini 3.5 Flash's edge isn't earning its rate.
Switch to Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite streams ~300 tokens/sec to Gemini 3.5 Flash's ~236 at a comparable blended cost ($0.5625 per million tokens). Use it when iteration speed matters more than squeezing out the last point of quality.
What you pay for Gemini 3.5 Flash
Gemini 3.5 Flash is billed per token at the rates below — the same billing tables the Usage page charges against, so this page cannot quote a different price than you pay.
Blended cost (3:1 input:output, the shape of a typical coding session) works out to $3.375 per million tokens.
| Per 1M tokens | Input | Output | Cache read |
|---|---|---|---|
| All requests | $1.50 | $9.00 | $0.15 |
In Command Code: caching and taste-1
Two things change the experience of using this model inside Command Code versus calling it directly through the upstream API.
First, prompt caching is on by default. In an agent loop the same context is read across many steps; cache reads are billed at $0.15 per million tokens versus $1.50 for fresh input.
Second, taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Gemini 3.5 Flash is a premium model — it needs the Pro plan or higher. Not on the Go plan ($1/mo, open-source models only).
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits; credits roll over and never expire, and auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Provider | $15 | Pay as you go | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams Pro | $40 / seat | $40 / seat | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick Gemini 3.5 Flash and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick Gemini 3.5 FlashAll Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is measured output tokens per second. Models without a published score are noted. This table is regenerated from the model registry, so it is always current.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| Claude Fable 5 | Premium | 59.9 | ~62 tok/s |
| GPT-5.6 Sol | Premium | 58.9 | ~77 tok/s |
| Claude Opus 4.8 | Premium | 55.7 | ~55 tok/s |
| GPT-5.6 Terra | Premium | 55 | ~155 tok/s |
| GPT-5.5 | Premium | 54.8 | ~81 tok/s |
| Grok 4.5 | Open-source | 53.8 | ~114 tok/s |
| Claude Opus 4.7 | Premium | 53.5 | ~52 tok/s |
| Claude Sonnet 5 | Premium | 53.4 | ~79 tok/s |
| GPT-5.4 | Premium | 51.4 | ~164 tok/s |
| GPT-5.6 Luna | Premium | 51.2 | ~234 tok/s |
| GLM-5.2 | Open-source | 51.1 | ~208 tok/s |
| Muse Spark 1.1 | Premium | 50.6 | ~130 tok/s |
| Gemini 3.5 Flash (this page) | Premium | 50.2 | ~236 tok/s |
| Claude Sonnet 4.6 | Premium | 47.2 | ~55 tok/s |
| Qwen 3.7 Max | Open-source | 46 | ~196 tok/s |
| MiniMax M3 | Open-source | 44.4 | ~113 tok/s |
| DeepSeek V4 Pro | Open-source | 44.3 | ~62 tok/s |
| GPT-5.3 Codex | Premium | 44.3 | ~106 tok/s |
| Kimi K2.6 | Open-source | 44.2 | ~43 tok/s |
| MiMo V2.5 Pro | Open-source | 42.2 | ~56 tok/s |
| Kimi K2.7 Code | Open-source | 41.9 | ~46 tok/s |
| Tencent Hy3 | Open-source | 41.2 | ~58 tok/s |
| DeepSeek V4 Flash | Open-source | 40.3 | ~106 tok/s |
| GLM-5.1 | Open-source | 40.2 | ~81 tok/s |
| Qwen 3.6 Max Preview | Open-source | 40 | ~46 tok/s |
| GPT-5.4 Mini | Premium | 40 | ~171 tok/s |
| Qwen 3.6 Plus | Open-source | 39.6 | ~53 tok/s |
| GLM-5 | Open-source | 39.5 | ~51 tok/s |
| Qwen 3.7 Plus | Open-source | 39 | ~52 tok/s |
| Kimi K2.5 | Open-source | 38.1 | ~51 tok/s |
| MiniMax M2.7 | Open-source | 38.1 | ~49 tok/s |
| Nemotron 3 Ultra | Open-source | 37.8 | ~204 tok/s |
| MiMo V2.5 | Open-source | 37.2 | ~88 tok/s |
| MiniMax M2.5 | Open-source | 33.7 | ~78 tok/s |
| Step 3.7 Flash | Open-source | 30.3 | ~407 tok/s |
| Step 3.5 Flash | Open-source | 26 | ~207 tok/s |
| Gemini 3.1 Flash Lite | Premium | 25 | ~300 tok/s |
| Claude Haiku 4.5 | Premium | 23.7 | ~103 tok/s |
| Kimi K3 | Open-source | Not yet scored | — |
| Kimi K2.7 Code HighSpeed | Open-source | Not yet scored | — |
| GLM-5.2 Fast | Open-source | Not yet scored | — |
| Inkling | Open-source | Not yet scored | — |
| Fugu Ultra | Premium | Not yet scored | — |
Frequently asked questions
Gemini 3.5 Flash or Muse Spark 1.1?
Muse Spark 1.1 scores higher on the Intelligence Index (50.6 vs 50.2) at $2 blended per million tokens against Gemini 3.5 Flash's $3.375. Default to Gemini 3.5 Flash and switch up when a task keeps stalling.
Gemini 3.5 Flash or Grok 4.5?
Grok 4.5 is about 11% cheaper blended ($3 vs $3.375 per million tokens), scoring 53.8 on the Intelligence Index. Use Grok 4.5 for volume work and Gemini 3.5 Flash where its edge earns the difference.
How much does Gemini 3.5 Flash cost in Command Code?
$1.50 per million input tokens and $9.00 per million output tokens, with cache reads at $0.15. In an agent loop, cached context brings effective input to roughly $0.555 per million tokens.
What plan do I need for Gemini 3.5 Flash?
Gemini 3.5 Flash requires the Pro plan or higher. The Go plan ($1/mo) covers open-source models only.
How good is Gemini 3.5 Flash at coding?
Gemini 3.5 Flash scores 70.1 on the Coding Index — the Artificial Analysis sub-score most predictive of coding-agent performance — alongside 50.2 overall.
Does Gemini 3.5 Flash support image input and reasoning?
Yes — Gemini 3.5 Flash accepts image input alongside text. It supports reasoning with selectable effort (low, medium, high).
Which Command Code model should I use?
Claude Fable 5 currently leads the lineup on the Intelligence Index (59.9). Grok 4.5 (53.8) leads the open-weights tier, available on every plan. For fast lookups, Step 3.7 Flash streams ~407 tok/s. There is no single right answer — switch per session with /model and let the task pick the model.
Can I mix Gemini 3.5 Flash with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep a default model and switch up for hard problems or down for quick lookups as the task calls for it.
Gemini 3.5 Flash or Gemini 3.1 Flash Lite?
3.5 Flash is the stronger model with parallel agentic execution; Flash Lite is the cheaper high-volume workhorse ($0.25 vs $1.50 input). Both carry vision and a 1M context.
Is Gemini 3.5 Flash available on the Go plan?
No. Gemini models are gated as premium, so they require Pro or higher — not the Go plan.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Related reading
- Gemini 3.1 Flash Lite in Command Codehigh-volume workhorse model with implicit caching
- Muse Spark 1.1 in Command Codeagentic performance, tool use, and computer use
- GLM-5.2 in Command Codepowerful coding with 1M context and long-horizon tasks
- Every model, one referenceThe docs list of all Command Code models with ids and context windows.
- Pricing, limits, and dealsThe canonical price table, running deals, and usage estimates.
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.