Google model
Gemini 3.6 Flash API
google/gemini-3.6-flash is Google's both-surface Flash id in the NextModel catalog: $1.50 per million input tokens, $7.50 per million output tokens, $0.15 per million cache hits, and a 1,000,000 token context window. Its published price row is identical to google/gemini-3.7-flash's, and the deciding difference is integration, not cost: 3.6 is listed on both the gemini API surface and the OpenAI-compatible chat completions surface, while 3.7 is gemini-only. The row lists Thinking, Function Calling, and Vision as capabilities. Against google/gemini-3.5-flash at $1.50 / $9.00 — the other Flash id that accepts chat completions — input is the same and output is $1.50 per million cheaper, and 3.6 adds a Thinking entry that 3.5's row does not list. No first-party benchmark scores or latency band are published for this id.
ThinkingFunction CallingVision
What is Gemini 3.6 Flash API in NextModel?
google/gemini-3.6-flash is Google's both-surface Flash id in the NextModel catalog: $1.50 per million input tokens, $7.50 per million output tokens, $0.15 per million cache hits, and a 1,000,000 token context window. Its published price row is identical to google/gemini-3.7-flash's, and the deciding difference is integration, not cost: 3.6 is listed on both the gemini API surface and the OpenAI-compatible chat completions surface, while 3.7 is gemini-only. The row lists Thinking, Function Calling, and Vision as capabilities. Against google/gemini-3.5-flash at $1.50 / $9.00 — the other Flash id that accepts chat completions — input is the same and output is $1.50 per million cheaper, and 3.6 adds a Thinking entry that 3.5's row does not list. No first-party benchmark scores or latency band are published for this id.
Gemini 3.6 Flash via NextModel: 1M-token context; $1.50 / 1M tokens in / $7.50 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best use cases
- OpenAI SDK chat-completions code that wants a current-generation Gemini Flash with Thinking and Vision at $1.50 / $7.50 without rewriting to the Gemini request shape — 3.7 Flash cannot take that call, this id can.
- Codebases with mixed callers, some on the Gemini generateContent shape and some on OpenAI SDK shape, that want one id resolving on either surface.
- Output-heavy Gemini work on the chat-compatible ids: $7.50 per million output undercuts gemini-3.5-flash's listed $9.00 at the same $1.50 input.
When not to use
- Code that already speaks the Gemini shape: the both-surface advantage is irrelevant there, and google/gemini-3.7-flash publishes the same $1.50 / $7.50 / $0.15 row.
- Absolute cost-floor traffic: deepseek/deepseek-v4-flash lists $0.14 / $0.28 per million tokens, roughly a tenth of this id's rates on both axes.
- Pipelines that require Streaming or Structured Outputs entries on the catalog row: this id lists Thinking, Function Calling, and Vision only.
OpenAI-compatible code example
request.sh
curl https://api.nextmodel.app/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $NEXTMODEL_API_KEY" \
-d '{"model":"google/gemini-3.6-flash","messages":[{"role":"user","content":"Reply with OK."}]}'Switching models only changes the model field.
Similar alternatives
GoogleCatalog
Gemini 3.5 Flash-Lite via NextModel: 1M-token context; $0.3 / 1M tokens in / $2.50 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
MoonshotaiCatalog
Kimi K3 via NextModel: 1M-token context; $2.95 / 1M tokens in / $14.71 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
QwenCatalog
Qwen3.7 Flash via NextModel: 1M-token context; Starting at $0.03 / 1M tokens in / $0.12 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
Reading
Articles that explain Gemini 3.6 Flash
LLM Gateway: Compare Options and Alternatives
Gemini-shape and OpenAI-shape ids resolve through one base URL and key.
Zhao Yu'an
How to estimate AI API cost before you ship
Output rate dominates at $7.50 per 1M — model the bill before defaulting.
Lin Qiming
FAQ
Gemini 3.6 Flash API questions
What model id and endpoint do I send for Gemini 3.6 Flash?
Send google/gemini-3.6-flash either to the Gemini surface under https://api.nextmodel.app/v1/gemini or to the OpenAI-compatible chat completions endpoint under https://api.nextmodel.app/v1 with your OpenAI SDK. Both surfaces are listed for this id — unlike gemini-3.7-flash, which is gemini-only at the same price.
What does the catalog list for price and context?
$1.50 per million input tokens, $7.50 per million output tokens, and $0.15 per million cache hits. Context window: 1,000,000 tokens. That is the same published row as gemini-3.7-flash; the surface list is what differs.
What should I treat as unverified?
Latency band and first-party benchmark scores are unpublished for this id. The Thinking, Function Calling, and Vision entries come from the catalog row, and the catalog publishes no quality scores behind them.
Start now
Ready to start building?
Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.