impulse

Gemini 3 Flash

Frontier lab
API id gemini-3-flash
Input / 1M
$0.50
at Replicate
Output / 1M
$3.00
at Replicate
Context window
1M
tokens
Max output
66K
tokens per reply
Hosts
3
3 listings
Released
-
date not published

Pricing

List prices at Replicate, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.50$3.00

What it costs a month

At Replicate list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$375
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$348
  • Coding agent1,000 requests a day, 40K in / 2K out$780
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,920
Use your own numbers

Where to run it

3 hosts serve Gemini 3 Flash. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
ReplicateInference
gemini-3-flash
$0.50 / $3.00
databricks-gemini-3-flash
$0.625 / $3.75
+25% vs headline
gemini-3-flash
$0.675 / $4.05
+35% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Replicate.

Smaller Google models

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    59% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    82% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    82% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    39% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    43% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    53% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    57% less

Model line

Newer and older versions, at each lab's own price.

  1. Sep 2026Gemini 3.8 FlashLatest$0.75 / $3.75
  2. Aug 2026Gemini 3.7 Flash$0.75 / $3.75
  3. Jul 2026Gemini 3.6 Flash$0.75 / $3.75
  4. May 2026Gemini 3.5 Flash$1.50 / $9.00
  5. UndatedGemini 3 FlashThis page$0.50 / $3.00
  6. Jun 2025Gemini 2.5 Flash$0.30 / $2.50
  7. UndatedGemini 2.0 Flash$0.15 / $0.60

Call it

Using Replicate's API.

Python
from litellm import completion

response = completion(
    model="replicate/gemini-3-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Gemini 3 Flash cost?

On Replicate, Gemini 3 Flash costs $0.50 per million input tokens and $3.00 per million output tokens.

Which APIs offer Gemini 3 Flash?

Gemini 3 Flash runs on 3 APIs: Replicate, Databricks and Kyma API.

What is Gemini 3 Flash's context window?

1M tokens, with up to 66K tokens in one reply.

Is Gemini 3 Flash being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Gemini 3 Flash?

Yes. Gemini 3.8 Flash is the newest model in this line, released on 2 Sep 2026.

What are cheaper alternatives to Gemini 3 Flash?

Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (24% less), GPT-5.4 Nano on OpenAI (59% less), Claude Haiku 5.5 on Anthropic (82% less) and Kimi K2.7 Code on CLF AI Gateway (39% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Gemini 3 Flash's API model id?

Use gemini-3-flash with Replicate. Other hosts use their own ids: databricks-gemini-3-flash on Databricks.

Sources

Raw catalog entry for gemini-3-flash on Replicate
{
  "input_cost_per_token": 5e-7,
  "litellm_provider": "replicate",
  "mode": "chat",
  "output_cost_per_token": 0.000003,
  "source": "https://replicate.com/google/gemini-3-flash",
  "supports_reasoning": true,
  "supports_system_messages": true,
  "supports_vision": true
}