Computer Use and Tool Support
Google lists function calling and computer use among the model’s tools. Gemini 3.6 Flash reached 83.0% on Google’s OSWorld-Verified evaluation, but computer use remains a preview capability.
Gemini 3.6 Flash
Access the Google Gemini 3.6 Flash API through GPTProto at $0.90 per 1M input tokens and $4.50 per 1M output tokens. The model accepts text, images, video, audio, and PDFs, with a 1,048,576-token input limit, 65,536-token output limit, configurable thinking, and agentic tools.
API Usage Examples
curl --request POST "https://gptproto.com/v1/chat/completions" \
--header "Authorization: Bearer $GPTPROTO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "gemini-3.6-flash",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'Gemini 3.6 Flash pricing
Estimate a request with real work scenarios. GPTProto token pricing is 40% below official rates.
UsageQuantityRateCost
tokens
tokens
tokens
tokens
Cost per request$0.009
Requests
Top-up amount
Top-up $100 and you get:
Top-up credits with permanent validity. You will receive a total of $100.00.
Additional 40% model discount, saving $66.6649 versus direct official Google API calls.
Related Models
All Models
| Model | Input → Output | ||||
|---|---|---|---|---|---|
| 1.05M | $0.90 / $4.50 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: Document Output: Text | |
| — | $8.00 / $40.00 per 1M | $10.00 / $0.80 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.90 / $4.50 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text | ||
| 1M | $9.00 / $45.00 per 1M | $11.25 / $0.23 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1M | $1.80 / $5.40 per 1M | $2.25 / $0.23 per 1M | Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text | ||
| — | 1.31M | $0.15 / $0.50 per 1M | — / $0.03 per 1M | Input: TextInput: ImageInput: VideoInput: Document Output: Text | |
| — | 1.05M | $0.44 / $1.32 per 1M | — / $0.01 per 1M | Input: TextInput: Image Output: Text | |
| 1.31M | $1.26 / $3.96 per 1M | — / $0.23 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.90 / $4.50 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 500K | $1.20 / $3.60 per 1M | — / $0.30 per 1M | Input: TextInput: Image Output: Text | ||
| 1M | $1.80 / $5.40 per 1M | $2.25 / $0.23 per 1M | Input: TextInput: ImageInput: VideoInput: Document Output: Text | ||
| 1M | $4.50 / $22.50 per 1M | $5.63 / $0.45 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.18 / $1.50 per 1M | $0.60 / $0.02 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $2.70 / $13.50 per 1M | $0.27 / $0.27 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $0.16 / $0.96 per 1M | $0.20 / $0.02 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $1.60 / $9.60 per 1M | $2.00 / $0.16 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 500K | $1.20 / $3.60 per 1M | $0.30 / $0.30 per 1M | Input: TextInput: Image Output: Text | ||
| 1M | $1.80 / $9.00 per 1M | $2.25 / $0.18 per 1M | Input: TextInput: Document Output: Text | ||
| 1.05M | $0.48 / $0.96 per 1M | $0.10 / $0.10 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1.05M | $1.26 / $3.96 per 1M | $0.23 / $0.23 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 1M | $0.36 / $1.44 per 1M | $0.07 / $0.07 per 1M | Input: TextInput: Document Output: Text | ||
| 1.05M | $0.90 / $5.40 per 1M | $0.60 / $0.09 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| — | 1.05M | $0.44 / $1.32 per 1M | — / $0.01 per 1M | Input: Text Output: Text | |
| — | 1.05M | $1.32 / $3.96 per 1M | — / $0.04 per 1M | Input: Text Output: Text | |
| 1M | $0.75 / $1.50 per 1M | $0.12 / $0.12 per 1M | Input: TextInput: Image Output: Text | ||
| 262K | $0.85 / $3.60 per 1M | $0.14 / $0.14 per 1M | Input: TextInput: Document Output: Text | ||
| 1.05M | $0.15 / $0.90 per 1M | $0.60 / $0.01 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 205K | $0.24 / $0.96 per 1M | $0.30 / $0.02 per 1M | Input: TextInput: Document Output: Text | ||
| 1.05M | $1.20 / $7.20 per 1M | $2.70 / $0.12 per 1M | Input: TextInput: ImageInput: Document Output: Text | ||
| 262K | $0.54 / $2.70 per 1M | $0.09 / $0.09 per 1M | Input: TextInput: Document Output: Text | ||
| 262K | $0.10 / $0.97 per 1M | — | Input: TextInput: Image Output: Text | ||
| 262K | $0.10 / $0.97 per 1M | — | Input: TextInput: Image Output: Text | ||
| 262K | $0.02 / $0.18 per 1M | — | Input: TextInput: Image Output: Text |
Gemini 3.6 Flash API for Agentic Coding and Multimodal Workflows
Use Google’s generally available Flash model with 1M context, 64K output, four thinking levels, and native tools at 40% below Google’s standard token pricing on GPTProto.
1M Multimodal Context
Process text, images, video, audio, and PDF inputs within a 1,048,576-token window and return up to 65,536 text tokens. For video, 1M-context models support one hour at default media resolution or three hours at low resolution.
More Efficient Agentic Coding
Gemini 3.6 Flash scored 49% on DeepSWE and 58.7% on SWE-Bench Pro in Google-reported evaluations. It makes fewer unwanted code edits and uses 17% fewer output tokens than Gemini 3.5 Flash on Artificial Analysis workloads.
Four Thinking Levels
Set thinking_level to minimal, low, medium, or high to balance latency, token use, and reasoning depth. Medium is the default; use lower levels for routine extraction and higher levels for multi-step coding or analysis.
What Is the Gemini 3.6 Flash API?
The Gemini 3.6 Flash API gives developers programmatic access to Google’s generally available Flash model for coding agents, multimodal analysis, long-context knowledge work, and tool-driven automation. Google released the stable gemini-3.6-flash model on July 21, 2026. Unlike the earlier gemini-3-flash-preview, this is a stable model ID intended for ongoing application use.
Gemini 3.6 Flash accepts text, images, video, audio, and PDF files, but it returns text only. Its 1,048,576-token input window can hold large repositories, long document sets, or extended media inputs, while the 65,536-token output limit supports detailed reports, code, and structured responses. Google lists caching, structured output, function calling, code execution, file search, URL context, Search grounding, Maps grounding, and configurable thinking among the underlying model’s capabilities.
The capability boundaries matter. Gemini 3.6 Flash does not generate images or audio, and it does not support the Live API. Computer use is available as a preview feature rather than a fully stable capability. When an integration depends on a Google-native tool, confirm that the GPTProto compatibility layer exposes it before migration. If your product requires speech-to-speech interaction, native image generation, or strict stability for desktop automation, route that part of the workload to another model.
| Specification | Gemini 3.6 Flash |
|---|---|
| Provider | |
| Status | Generally available |
| Stable model ID | gemini-3.6-flash |
| Input types | Text, image, video, audio, PDF |
| Output type | Text |
| Input token limit | 1,048,576 |
| Output token limit | 65,536 |
| Thinking levels | minimal, low, medium, high |
| Default thinking level | medium |
| Google-listed tools | Function calling, code execution, file search, Search, Maps, URL context |
| Computer use | Supported in preview |
| Not supported | Image generation, audio generation, Live API |
Where Gemini 3.6 Flash Fits Best
Gemini 3.6 Flash is most useful when a task needs both a large working context and repeated tool calls. It is not automatically the cheapest choice for every short prompt, and its default medium thinking level can spend more tokens than a non-reasoning model on simple classification. Match the thinking level and model route to the actual job.
| Workload | Why it fits | Implementation note |
|---|---|---|
| Repository coding agents | Fewer unwanted edits and execution loops than Gemini 3.5 Flash in Google’s testing | Use medium or high thinking and validate changes with tests |
| Multimodal document analysis | Reads PDFs, images, charts, audio, and video in the same request | Ask for structured output when downstream systems need stable fields |
| Long-context research | 1M input tokens and supported context caching | Cache repeated corpora instead of resending unchanged files |
| Browser or desktop automation | Native computer-use tooling and 83.0% OSWorld-Verified in Google’s evaluation | Treat computer use as preview and keep approval gates for consequential actions |
| Grounded assistants | The underlying model supports Search, Maps, file search, and URL context | Enable only the tools each request needs and track resulting token use |
Gemini 3.6 Flash vs Gemini 3.5 Flash
Gemini 3.6 Flash is a direct efficiency upgrade over Gemini 3.5 Flash rather than a larger-context replacement. Both models keep the same 1M context class and default medium thinking level. The difference is task efficiency: Google reports 17% fewer output tokens on Artificial Analysis workloads, fewer reasoning turns and tool calls, and stronger results in coding, machine-learning engineering, computer use, and long-context retrieval.
The official input rate remains $1.50 per 1M tokens, while the official output rate falls from $9.00 to $7.50. On GPTProto, Gemini 3.6 Flash costs $0.90 per 1M input tokens and $4.50 per 1M output tokens; Gemini 3.5 Flash is currently $0.90 and $5.40. For new agentic or multimodal systems, 3.6 Flash is the better default. Keep 3.5 Flash only when you have already validated its behavior and need time to regression-test the migration.
| Metric | Gemini 3.6 Flash | Gemini 3.5 Flash |
|---|---|---|
| Context window | 1,048,576 | 1,048,576 |
| Max output | 65,536 | 65,536 |
| Default thinking | Medium | Medium |
| Google standard input / output per 1M | $1.50 / $7.50 | $1.50 / $9.00 |
| GPTProto input / output per 1M | $0.90 / $4.50 | $0.90 / $5.40 |
| DeepSWE v1.1 | 49.0% | 37.0% |
| MLE-Bench | 63.9% | 49.7% |
| OSWorld-Verified | 83.0% | 78.4% |
| GDM-MRCR v2 at 1M | 54.0% | 26.6% |
Benchmark figures above are provider-reported. Use them to choose candidates, then run both models on your own prompts, tools, and success criteria before moving production traffic.
API Changes to Check Before You Migrate
Do not treat migration to 3.6 Flash as only a model-name replacement if your application uses Google’s native Interactions API. Google changed several generation and conversation fields for the latest models:
- Change the model ID to
gemini-3.6-flash. - Remove
temperature,top_p, andtop_kfrom generation configuration. - Replace
thinking_budgetwiththinking_level; supported values areminimal,low,medium, andhigh. - Remove
candidate_count, which Gemini 3.x does not support. - Do not send prefilled model turns. For multi-turn Interactions API sessions, use the server-side
previous_interaction_id. - Regression-test tool schemas, structured outputs, and file handling before shifting all traffic.
If you use GPTProto’s OpenAI-compatible request format, follow the Quick Start and GPTProto documentation on this page rather than copying Google-native fields directly. The practical advantage is that one GPTProto API key and balance can also call Gemini 3.5 Flash, GPT-5.6 Luna, Claude Opus 4.8, Kimi K3, and 200+ other models, so you can run the same evaluation set without opening separate provider accounts.
Frequently Asked Questions
Is Gemini 3 Flash available via API?
Yes. Gemini 3.6 Flash is generally available through the Gemini API under the stable model ID gemini-3.6-flash, and GPTProto provides access through the model string shown on this page. Do not confuse it with gemini-3-flash-preview, which is an earlier preview model.
How much does the Gemini 3.6 Flash API cost on GPTProto?
GPTProto lists Gemini 3.6 Flash at $0.90 per 1M input tokens and $4.50 per 1M output tokens. Google’s standard rate is $1.50 input and $7.50 output, so GPTProto’s displayed token rates are 40% lower.
How do I get a Gemini 3.6 Flash API key?
Create a GPTProto account, add credit, generate a key in the dashboard, and use the gemini-3.6-flash model string from the Quick Start. The same key and balance work across more than 200 supported models, which makes fallback routing and A/B testing easier.
What inputs, context window, and output limit does Gemini 3.6 Flash support?
The model accepts text, images, video, audio, and PDFs. It supports up to 1,048,576 input tokens and 65,536 output tokens, and returns text. It supports structured output and tools, but it does not natively generate images or audio.
How does Gemini 3.6 Flash compare with Gemini 3.5 Flash?
The context and default thinking level are unchanged, but 3.6 Flash is more efficient. Google reports 17% fewer output tokens, DeepSWE improving from 37% to 49%, and OSWorld-Verified improving from 78.4% to 83.0%. Its official output price also falls from $9.00 to $7.50 per 1M tokens.
Gemini 3.6 Flash vs GPT-5.6, Claude Opus 4.8, or Kimi K3: which should I use?
Choose Gemini 3.6 Flash when you need Google’s multimodal inputs, Search or Maps grounding, computer-use tooling, and a 1M context window at a Flash-tier price. In Google’s published table, GPT-5.6 Luna leads 3.6 Flash on several coding benchmarks, while Gemini leads on OSWorld-Verified and chart reasoning. Google did not publish matched Opus 4.8 or Kimi K3 results in that table, so a universal winner claim would be misleading. Run the same task-level evaluation across the models with one GPTProto key.
Should I use Gemini 3.6 Flash instead of Gemini 3 Pro?
For a new API integration, Gemini 3.6 Flash has the clearer deployment path because it is generally available, lower cost, and optimized for repeated agentic and multimodal work. Gemini 3 Pro was a preview model with a different cost and latency profile. If an existing application depends on its output behavior, compare both on your own evaluation set before migrating.