Gemini 3.5 Flash API model profile
Evidence snapshot:
Gemini 3.5 Flash is a Google model profile with a 1,048,576-token context window. The dated catalog snapshot records text, image, video, file, audio modalities and interfaces for audio input, file input, prompt caching, reasoning, reasoning controls.
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.
Gemini 3.5 Flash is worth reaching for when you need a route carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support.
Gemini 3.5 Flash is available under the Kendr alias kc-gemini-3.5-flash. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy.
Gemini 3.5 Flash accepts text, image, video, file, and audio and returns text. The snapshot records audio input, file input, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, video input, vision, web search, and web search pricing as capabilities or interfaces.
The dated reference snapshot lists $0.75 input and $4.5 output per million tokens. Cached input is $0.075 per million tokens. The separately published provider-route reference is $1.50 / $9.
The 2026-09-06 snapshot includes 2 Artificial Analysis indexes, 21 Design Arena categories, and AutoExacto results for 4 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Gemini 3.5 Flash ranked #71 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Kendr API model
- Kendr API alias
- kc-gemini-3.5-flash
- Model developer
- Kendr route provider
- Context window
- 1M
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- 2025-01-01
- Reference catalog ID
- google/gemini-3.5-flash
When to pick Gemini 3.5 Flash
Gemini 3.5 Flash is worth reaching for when you need a route carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when a whole corpus has to fit in one prompt. The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked.
- Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
- Reach for it when the input is speech. The snapshot records audio input, so recordings can go to this route rather than being transcribed first.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Look elsewhere when the request is trivial and latency-sensitive. Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.
Context, modalities, and identity
Gemini 3.5 Flash accepts text, image, video, file, and audio and returns text. The snapshot records audio input, file input, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, video input, vision, web search, and web search pricing as capabilities or interfaces.
- Model developer
- Kendr route provider
- Context window
- 1M
- Maximum output
- 65,536 tokens
- Input modalities
- text, image, video, file, and audio
- Output modalities
- text
- Knowledge cutoff
- 2025-01-01
Model overview
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.
- Reference model ID
- google/gemini-3.5-flash
- Canonical version
- google/gemini-3.5-flash-20260519
- Hugging Face ID
- Not separately documented
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- Supported parameters
- include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
- audio input
- file input
- prompt caching
- reasoning
- reasoning controls
- structured output
- text generation
- tool calling
- tools
- video input
- vision
- web search
- web search pricing
Dated pricing snapshot
The dated reference snapshot lists $0.75 input and $4.5 output per million tokens. Cached input is $0.075 per million tokens. The separately published provider-route reference is $1.50 / $9.
Reference figures are dated 2026-09-06; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card.
- Price date
- 2026-09-06
- Input
- $0.75 per 1M tokens
- Cached input
- $0.075 per 1M tokens
- Output
- $4.5 per 1M tokens
Provider routes, performance, and uptime
The snapshot retains 7 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 6
- Best p50 latency
- 0.81 s
- Best p50 throughput
- 190 tok/s
- Availability with routing
- 99.47% over the sampled window
- Availability without routing
- 98.25% over the sampled window
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| Google AI Studio Flex | unknown | $0.75 / 1M | $4.5 / 1M | $0.075 / 1M | 1,048,576 tokens | 0.81 s | 51 tok/s | 99.70% |
| Google Vertex | unknown | $1.5 / 1M | $9 / 1M | $0.15 / 1M | 1,048,576 tokens | 1.39 s | 138 tok/s | 99.73% |
| Google AI Studio | unknown | $1.5 / 1M | $9 / 1M | $0.15 / 1M | 1,048,576 tokens | 1.46 s | 108 tok/s | 98.44% |
| Google Vertex (US) | unknown | $1.65 / 1M | $9.9 / 1M | $0.165 / 1M | 1,048,576 tokens | No recent p50 | No recent p50 | No recent uptime |
| Google Vertex Priority | unknown | $2.7 / 1M | $16.2 / 1M | $0.27 / 1M | 1,048,576 tokens | 0.81 s | 91 tok/s | 100.00% |
| Google AI Studio Priority | unknown | $2.7 / 1M | $16.2 / 1M | $0.27 / 1M | 1,048,576 tokens | 1.91 s | 190 tok/s | 99.78% |
| Google Vertex Flex | unknown | $0.75 / 1M | $4.5 / 1M | $0.075 / 1M | 1,048,576 tokens | 12.88 s | 7 tok/s | 83.06% |
Benchmark evidence and limitations
The 2026-09-06 snapshot includes 2 Artificial Analysis indexes, 21 Design Arena categories, and AutoExacto results for 4 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
- Coding Index
- 70.1
- Agentic Index
- 27.4
- AutoExacto coverage
- 4 provider observations over 32 days
| Design Arena category | Elo | Win rate | Rank |
|---|---|---|---|
| agenticgamedev | 1180 | 55.4% | #11 |
| agentichtmlslides | 1162 | 45.8% | #6 |
| agenticslides | 1244 | 57.5% | #3 |
| agenticslides(html) | 1162 | 45.7% | #6 |
| agenticslides(python-pptx) | 1242 | 57.8% | #2 |
| androidnative | 1203 | 58% | #14 |
| fullstack | 1203 | 57.5% | #14 |
| godotgamedev | 1135 | 42.9% | #20 |
| htmlslides | 1150 | 46.6% | #18 |
| mobileapps | 1203 | 51.6% | #14 |
| pptxslides | 1244 | 57.7% | #2 |
| python-pptxslides | 1247 | 57.4% | #7 |
| webapps | 1230 | 53.2% | #16 |
| 3d | 1280 | 57.4% | #24 |
| asciiart | 1280 | 59.4% | #10 |
| codecategories | 1279 | 55% | #24 |
| dataviz | 1256 | 54.2% | #28 |
| gamedev | 1294 | 54.8% | #18 |
| svg | 1289 | 60.6% | #7 |
| uicomponent | 1294 | 55.8% | #18 |
| website | 1275 | 54.1% | #26 |
AutoExacto provider benchmarks
Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.
| Provider | GPQA Diamond | TAU-Bench Airline | Runs |
|---|---|---|---|
| auto-routing | 92.42% | 75.33% | 1 |
| Google AI Studio | 92.59% | 70.67% | 1 |
| Google Vertex | 92.76% | 71.33% | 1 |
| Google Vertex (US) | 92.91% | 74.6% | 2 |
Popularity and market context
Gemini 3.5 Flash ranked #71 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
- Third-party catalog rank
- #71
- Global market share
- Not inferred
- Observation date
- 2026-09-06
OpenAI-compatible API example
This example applies to the published Kendr alias on this hosted profile. Check the live public catalog before use.
curl https://api.kendr.org/v1/chat/completions \
-H "Authorization: Bearer $KENDR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kc-gemini-3.5-flash","messages":[{"role":"user","content":"Hello"}]}'Frequently asked questions
When should I use Gemini 3.5 Flash?
Gemini 3.5 Flash is worth reaching for when you need a route carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support. Reach for it when a whole corpus has to fit in one prompt: The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the input is speech: The snapshot records audio input, so recordings can go to this route rather than being transcribed first. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Look elsewhere when the request is trivial and latency-sensitive: Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.
What is Gemini 3.5 Flash?
Gemini 3.5 Flash is a Google model profile with a 1,048,576-token context window. The dated catalog snapshot records text, image, video, file, audio modalities and interfaces for audio input, file input, prompt caching, reasoning, reasoning controls.
What context window does Gemini 3.5 Flash have?
The dated profile lists 1M of context and up to 65,536 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for Gemini 3.5 Flash?
The 2026-09-06 snapshot includes 2 Artificial Analysis indexes, 21 Design Arena categories, and AutoExacto results for 4 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
What is the Kendr API alias for Gemini 3.5 Flash?
Use kc-gemini-3.5-flash as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes.
How is Gemini 3.5 Flash priced on Kendr?
The dated reference snapshot lists $0.75 input and $4.5 output per million tokens. Cached input is $0.075 per million tokens. The separately published provider-route reference is $1.50 / $9. Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request.
Sources and evidence dates
- Gemini 3.5 Flash third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- Google official model documentation (primary, checked 2026-09-06)
- Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
- Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)
- Gemini 3.5 Flash third-party catalog record (benchmark, checked 2026-09-06)
- Gemini 3.5 Flash provider or route reference (primary, checked 2026-09-06)