Google Gemini models through odnoga
The best price per token of context on the gateway. Gemini is where you go when the job is to read a lot — long documents, long transcripts, whole repositories — and the flash tiers make that affordable at volume.
Context is the reason to be here
Gemini offers the largest context windows on the gateway at the lowest input price, which changes what is worth building. Retrieval stops being mandatory for mid-sized corpora: instead of chunking, embedding and hoping the right passage comes back, you can put the whole document in the prompt and ask directly. Work out the cost first — a million tokens of input is still a million tokens — but at flash prices the arithmetic often favours reading everything.
Flash, lite and pro
The tiers differ far more in price than the names suggest. Lite variants are for volume work where latency and cost matter more than the last few points of quality; pro variants are for the harder reasoning jobs. Because odnoga picks the model by rule, a sensible pattern is lite on the hot path with a pro model as the escalation for the small share of requests that fail a quality check.
Mixed modalities
Part of this range is billed per media unit rather than per token — image and video work priced per output, not per word. Those models show an empty token column on purpose; the media rate is on the pricing page. Everything else in the family is ordinary text billing.
Vendor cost is the list price. Your price is that plus your plan margin — the same figures that appear on your invoice.
Every model here, cheapest first
| Model | Vendor | Context | In / 1M | Out / 1M | Cached in | Your price in | |
|---|---|---|---|---|---|---|---|
| Gemini Embedding 2 gemini-embedding-2 | Google AI | 8K | $0.2 | — | — | $0.215 | Details |
| Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) gemini-3.1-flash-lite-image | Google AI | 66K | $0.25 | $1.50 | — | $0.269 | Details |
| Gemini 3.1 Flash-Lite gemini-3.1-flash-lite | Google AI | 1.0M | $0.25 | $1.50 | $0.025 | $0.269 | Details |
| Gemini 2.5 Flash Image (Nano Banana) gemini-2.5-flash-image | Google AI | 33K | $0.3 | $2.50 | — | $0.323 | Details |
| Gemini 3.5 Flash-Lite gemini-3.5-flash-lite | Google AI | 1.0M | $0.3 | $2.50 | $0.03 | $0.323 | Details |
| Gemini 2.5 Flash Native Audio (Live) gemini-2.5-flash-native-audio-preview-12-2025 | Google AI | 131K | $0.5 | $2 | — | $0.538 | Details |
| Gemini 2.5 Flash TTS gemini-2.5-flash-preview-tts | Google AI | 8K | $0.5 | $10 | — | $0.538 | Details |
| Gemini 3 Flash Preview gemini-3-flash-preview | Google AI | 1.0M | $0.5 | $3 | $0.05 | $0.538 | Details |
| Gemini 3.1 Flash Image (Nano Banana 2) gemini-3.1-flash-image | Google AI | 66K | $0.5 | $3 | — | $0.538 | Details |
| Gemini 3.1 Flash Live gemini-3.1-flash-live-preview | Google AI | 131K | $0.75 | $4.50 | — | $0.806 | Details |
| Gemini 3.6 Flash gemini-3.6-flash | Google AI | 1.0M | $0.75 | $3.75 | $0.075 | $0.806 | Details |
| Gemini 3.7 Flash gemini-3.7-flash | Google AI | 1.0M | $0.75 | $3.75 | $0.075 | $0.806 | Details |
| Gemini 2.5 Computer Use gemini-2.5-computer-use-preview-10-2025 | Google AI | 131K | $1 | $5 | — | $1.08 | Details |
| Gemini 2.5 Pro TTS gemini-2.5-pro-preview-tts | Google AI | 8K | $1 | $20 | — | $1.08 | Details |
| Gemini 3.1 Flash TTS gemini-3.1-flash-tts-preview | Google AI | 8K | $1 | $20 | — | $1.08 | Details |
| Gemini Robotics ER 2 gemini-robotics-er-2-preview | Google AI | 131K | $1 | $5 | $0.1 | $1.08 | Details |
| Gemini 2.5 Pro gemini-2.5-pro | Google AI | 1.0M | $1.25 | $10 | $0.125 | $1.34 | Details |
| Gemini 3.5 Flash gemini-3.5-flash | Google AI | 1.0M | $1.50 | $9 | $0.15 | $1.61 | Details |
| Gemini Omni Flash Preview gemini-omni-flash-preview | Google AI | 131K | $1.50 | $9 | — | $1.61 | Details |
| Gemini 3 Pro Image (Nano Banana Pro) gemini-3-pro-image | Google AI | 131K | $2 | $12 | — | $2.15 | Details |
| Gemini 3.1 Pro Preview gemini-3.1-pro-preview | Google AI | 1.0M | $2 | $12 | $0.2 | $2.15 | Details |
| Gemini Robotics ER 2 Streaming gemini-robotics-er-2-streaming-preview | Google AI | 131K | $2 | $10 | — | $2.15 | Details |
| Gemini 3.5 Live Translate gemini-3.5-live-translate-preview | Google AI | 16K | $3.50 | $21 | — | $3.76 | Details |
| Lyria 3 Clip (30s) lyria-3-clip-preview | Google AI | 1.0M | Billed per media unit — see details | Details | |||
| Lyria 3 Pro (full song) lyria-3-pro-preview | Google AI | 1.0M | Billed per media unit — see details | Details | |||
| Veo 3.1 veo-3.1-generate-preview | Google AI | 480 | Billed per media unit — see details | Details | |||
| Veo 3.1 Fast veo-3.1-fast-generate-preview | Google AI | 480 | Billed per media unit — see details | Details | |||
| Veo 3.1 Lite veo-3.1-lite-generate-preview | Google AI | 480 | Billed per media unit — see details | Details | |||
Your price column is the vendor cost +7%.
Narrow it differently
Models that take 200,000 tokens or more in a single request — roughly a long book, a full codebase, or a year of support tickets.
Models that accept an image alongside the prompt: screenshots, scans, invoices, charts, photographs of paperwork.
The widest range on the gateway, and the widest price range with it — from the cheapest token on odnoga to the most expensive.
Or read how the gateway picks between them: routing and fallback, and what it costs: plans and margins.