Pricingby GlyphGemma 3 introduces multimodality, supporting vision-language input and text outputs.
Ways to buy 4
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
bf16-flex, bf16 | $0.04 | $0.12 | $0.04 / $0.12Cheapest | n/a | Cheapest |
bf16 | $0.05 | $0.15 | $0.05 / $0.15+25% vs cheapest | n/a | +25% vs cheapest |
| NextBit int4 · cached $0.05 | $0.075 | $0.15 | $0.075 / $0.15+56% vs cheapest | $0.05 | +56% vs cheapest |
bf16-priority, bf16 | $0.075 | $0.225 | $0.075 / $0.225+87% vs cheapest | n/a | +87% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $6.40 direct.
Helicone$6.40+0%
Kong AI Gateway$6.40+0%
LiteLLM$6.40+0%
Neon AI Gateway$6.40+0%
Eden AI$6.75+5.5%
OpenRouter$6.75+5.5%
Cloudflare AI GatewayNot offeredNot offered
RequestyNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Google · 131K | $1.5 | $9 | $1.5 / $9 | $3.38 | 131K | Lab list price | · | Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. |
Google · 131K | $1.5 | $9 | $1.5 / $9 | $3.38 | 131K | Lab list price | · | Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. |
Google · 1MCheapest: $2 on Google Gemini API (flex) | $2 | $10 | $2 / $10 | $4 | 1M | $2 on Google Gemini API (flex) | · | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. |
Google · 66K | $1.5 | $7.5 | $1.5 / $7.5 | $3 | 66K | Lab list price | · | Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
Cohere · 128K | $0.08 | Free | $0.08 / Free | $0.06 | 128K | Lab list price | · | Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). |
Cohere · 128K | $0.12 | Free | $0.12 / Free | $0.09 | 128K | Lab list price | · | Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). |
 Titan Embeddings G1 - TextAmazon Nova · 8K | $0.1 | Free | $0.1 / Free | $0.075 | 8K | Lab list price | · | Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. |
About Gemma 3 12B
Takes text, image in and returns text. First listed Sep 23, 2026. Up to 16K output tokens. Blended price $0.06 per 1M tokens at 3 input to 1 output. Model id gemma-3-12b-it.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does Gemma 3 12B cost?
$0.04 per million input tokens and $0.12 per million output tokens.
What is the context window of Gemma 3 12B?
131K tokens, with up to 16K tokens of output.
Where is Gemma 3 12B cheapest?
Of 4 routes tracked, DeepInfra is cheapest at $0.04 input and $0.12 output per million tokens.
Has Gemma 3 12B's price changed?
Yes. The input price went from $0.05 to $0.075, first seen Nov 1, 2026.