Gemini API pricing
Every Gemini model Inferray offers — 15 from Google — at its list price, with no gateway fee on top. One API key calls all of them, alongside every other model in the catalog.
Gemini models and prices
| Model | Input / 1M | Cached / 1M | Output / 1M | Context | Token Plans |
|---|---|---|---|---|---|
| Gemini 4 ArgonGoogle's frontier model for long-horizon coding and knowledge work. | $4 | $0.2 | $20 | 1.0M | Included |
| Gemini 3.8 FlashFast multimodal reasoning for coding and agents. | $0.75 | $0.075 | $3.75 | 1.0M | Included |
| Gemini 3.7 FlashGemini 3.7 Flash for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $0.75 | $0.075 | $3.75 | 1.0M | Pay-as-you-go |
| Gemini 3.5 Flash LiteThe fastest, cheapest 3.5 model for high-throughput work. | $0.3 | $0.03 | $2.5 | 1.0M | Included |
| Gemini 3.6 FlashGemini 3.6 Flash for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $0.75 | $0.075 | $3.75 | 1.0M | Pay-as-you-go |
| Gemini 3.5 FlashFrontier intelligence at Flash speed, with search and grounding. | $1.5 | $0.15 | $9 | 1.0M | Included |
| Gemini 3.1 Flash LiteUltra-lightweight Gemini for cost-sensitive volume. | $0.25 | $0.025 | $1.5 | 1.0M | Included |
| Gemma 4 26B A4B ITGemma 4 26B A4B IT for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $0.07 | $0.07 | $0.34 | 262K | Pay-as-you-go |
| Gemma 4 31B ITGemma 4 31B IT for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $0.2 | $0.2 | $0.4 | 262K | Pay-as-you-go |
| Gemini Pro LatestGemini Pro Latest for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $2 | $0.2 | $12 | 1.0M | Pay-as-you-go |
| Gemini 3.1 Pro (Preview)Google's Pro-tier reasoning, in preview. | $2 | $0.2 | $12 | 1.0M | Included |
| Gemini 3 Flash (Preview)Gemini 3 Flash (Preview) for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $0.5 | $0.05 | $3 | 1.0M | Pay-as-you-go |
| Gemini 3.1 Flash Lite ImageGoogle's lowest-cost image model, built for scale. | $0.034 / image | 66K | Included | ||
| Gemini 3.1 Flash Image (Preview)Gemini 3.1 Flash Image (Preview) for OpenAI-style Image Generation, Image editing, OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $0.045 / image | 131K | Pay-as-you-go | ||
| Gemini 3 Pro Image (Preview)Google's most capable image model, up to 4K. | $0.134 / image | 66K | Included | ||
Which Gemini model should I use?
- Gemini 4 Argon is the newest, released September 30, 2026.
- Gemma 4 26B A4B IT costs the least per request: $0.07 in / $0.34 out per 1M tokens.
Each model page has worked cost examples, code, and the full spec.
Call the Gemini API
Point the OpenAI SDK (or the Anthropic SDK, or plain HTTP) at Inferray and name the model. This calls Gemini 4 Argon; swap the id for any model above.
from openai import OpenAI
client = OpenAI(base_url="https://api.inferray.com/v1", api_key="inferray_...")
reply = client.chat.completions.create(
model="gemini-4-argon",
messages=[{"role": "user", "content": "ship it"}],
)Gemini API questions
- How much does the Gemini API cost?
- On Inferray, Gemini models cost $0.07–$4 per 1M input tokens, the list price per model with no gateway fee on top. The table above has every model's input, cached input, and output price.
- Do I need a Google account to use Gemini?
- No. You call Gemini with your Inferray API key and pay from one Inferray balance or Token Plan, the same as for every other model in the catalog.
- Are Gemini models included in Token Plans?
- All of them except Gemini 3.7 Flash, Gemini 3.6 Flash, Gemma 4 26B A4B IT, Gemma 4 31B IT, Gemini Pro Latest, Gemini 3 Flash (Preview), and Gemini 3.1 Flash Image (Preview), which are pay-as-you-go only. Plan credit is spent at list price, so the 20 Solo plan gives you 60 of usage a month.
- Does my credit expire?
- No. Pay-as-you-go credit never expires, and a top-up credits exactly what you pay. Token Plan credit resets each month with the plan.
Other model families
Prices from the catalog as of November 12, 2026.