🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

Gemini 3.7 Flash Released 2026-08-13

chatVisionCodeTool callingReasoningPrompt caching

Gemini 3.7 Flash is Google's most capable Flash model, generally available since 13 August 2026 and positioned for agentic workflows and multimodal reasoning.

Input
text image audio video $0.75/M
Output
text $3.75/M
Audio input
$0.75/M
Cache read
$0.075/M
Context
1M
vs GPT-4o
~85% cheaper

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.2775/M. Implicit caching is on by default for current Gemini models (discounted automatically on cache hits), plus an explicit CachedContent API with storage-based billing for guaranteed savings. That cached-read rate is only part of the bill: this vendor also charges separately for keeping the cache.

Price · where it sits among 55 comparable models

Input$0.75/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$3.75/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.075/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,048,576
Max output (vendor spec) 65,536

Prompt caching

How it caches automatic + explicit
Min prefix 1,024

Thinking

Parameter reasoning_effort
Values minimal · low · medium · high accepted set is the provider's

Model

Modalities text + image + audio + video → text
  • Google's most capable Flash model for agentic workflows and multimodal reasoning
  • output price includes thinking tokens, and audio and video input bill at the text rate

per Google official docs ↗

Use Gemini 3.7 Flash in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gemini-3.7-flash",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Gemini 3.7 Flash

  • It takes text, images, audio and video and returns text, so a single call can reason over a screenshot, a recording and a prompt together instead of stitching several models into a pipeline.
  • Two pricing details make it unusually easy to budget for.
  • There is no context-length step: a 900,000-token prompt costs the same per token as a 900-token one, so long-context work does not fall off a cliff partway through a document.
  • And there is no modality surcharge either — audio and video input bill at the text rate, which is the opposite of how most multimodal pricing works and removes the usual reason to downsample media before sending it.
  • The output price includes thinking tokens, so a reasoning-heavy answer is billed on the full trace rather than only the visible text; budget max output tokens with that in mind.
  • Context caching is available at roughly a tenth of the input rate, with a separate hourly storage charge, which makes it worth pinning a stable prefix for agent loops that replay the same system prompt.
  • Grounding with Google Search is included for a monthly allowance shared across the Gemini 3 family before per-request charges begin.
  • Synthorai serves it through the OpenAI-compatible chat completions endpoint, so it drops into an existing integration without a Google-specific client.

FAQ

Is the Gemini 3.7 Flash API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.75/M input tokens, that credit alone covers roughly 166 requests of ~8K tokens against Gemini 3.7 Flash.

What is Gemini 3.7 Flash best at?

Most capable Flash tier for agentic work; text, image, audio and video input; no context-length or modality surcharge. See the About section for the full picture from the vendor's own release notes.

How much does Gemini 3.7 Flash cost?

Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.075/M.

Does Gemini 3.7 Flash support prompt caching?

Yes: automatic caching is on by default, with an explicit mode for guaranteed savings. Cached input tokens bill at $0.075/M vs $0.75/M uncached; prompts need a 1,024-token stable prefix to cache. Prompt caching guide →

How do I get access to Gemini 3.7 Flash?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3.7-flash", and you're done. One API key covers every model on the gateway.

Related models

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your free API key Compare your cost →