Oxyy is an independent API gateway, not affiliated with Google.
Paid Gemini text models run from $0.016 to $0.800 per 1M input tokens and $0.016 to $4.80 per 1M output tokens. Gemini 3.8 Flash costs $0.300 input / $1.50 output per 1M tokens, pay-as-you-go (standard price $0.750 / $3.75). The most used Gemini model on Oxyy over the last 7 days is Gemini 3 Flash.
Prices checked daily · last price change Sep 24, 2026 (discount changed: 70% → 60% off)
| Model | Context | Input | Output | Cached input | Saving | Released |
|---|---|---|---|---|---|---|
| Gemini 3.8 Flashgemini-3.8-flash | 1.05M | Standard price $0.750, on Oxyy $0.300 | Standard price $3.75, on Oxyy $1.50 | $0.030 | 60% | Sep 2, 2026 |
| Gemini 3.6 Flashgemini-3.6-flash | 1.05M | Standard price $0.750, on Oxyy $0.300 | Standard price $3.75, on Oxyy $1.50 | $0.030 | 60% | — |
| Gemini 2.5 Progemini-2.5-pro | 1.05M | Standard price $1.25, on Oxyy $0.500 | Standard price $10.00, on Oxyy $4.00 | $0.050 | 60% | Jun 17, 2025 |
| Gemini 3 Flashgemini-3-flash | 1.05M | Standard price $0.500, on Oxyy $0.200 | Standard price $3.00, on Oxyy $1.20 | $0.020 | 60% | Jan 1, 2026 |
| Gemini 2.5 Flash-Litegemini-2.5-flash-lite | 1.05M | Standard price $0.100, on Oxyy $0.040 | Standard price $0.400, on Oxyy $0.160 | $0.004 | 60% | Jul 22, 2025 |
| Gemini 3.1 Flash-Litegemini-3.1-flash-lite | 1.05M | Standard price $0.250, on Oxyy $0.100 | Standard price $1.50, on Oxyy $0.600 | $0.010 | 60% | — |
| Gemini 2.5 Flashgemini-2.5-flash | 1.05M | Standard price $0.300, on Oxyy $0.120 | Standard price $2.50, on Oxyy $1.00 | $0.012 | 60% | Jun 17, 2025 |
| Gemini 3.5 Flash-Litegemini-3.5-flash-lite | 1.05M | Standard price $0.300, on Oxyy $0.120 | Standard price $2.50, on Oxyy $1.00 | $0.012 | 60% | — |
| Gemini 4 Argongemini-4-argon | 1.05M | Standard price $2.00, on Oxyy $0.800 | Standard price $10.00, on Oxyy $4.00 | $0.040 | 60% | Sep 30, 2026 |
| Gemma 4 26B A4B Instruct (MoE)gemma-4-26b-a4b-it | 262K | Standard price $0.130, on Oxyy $0.052 | Standard price $0.400, on Oxyy $0.160 | $0 | 60% | Apr 2, 2026 |
| Gemini 3.7 Flashgemini-3.7-flash | 1.05M | Standard price $0.750, on Oxyy $0.300 | Standard price $3.75, on Oxyy $1.50 | $0.030 | 60% | — |
| Gemini 3.1 Progemini-3.1-pro | 1.05M | Standard price $2.00, on Oxyy $0.800 | Standard price $12.00, on Oxyy $4.80 | $0.080 | 60% | Feb 1, 2026 |
| Gemma 4 31B Instructgemma-4-31b-it | 262K | Standard price $0.270, on Oxyy $0.108 | Standard price $0.760, on Oxyy $0.304 | $0 | 60% | Apr 2, 2026 |
| Gemini 3.1 Flash TTSgemini-3.1-flash-tts-preview | 33K | Standard price $1.00, on Oxyy $0.400one rate for input and output | — | 60% | Apr 15, 2026 | |
| Gemini 3.8 Flash TTSgemini-3.8-flash-tts | — | Standard price $0.500, on Oxyy $0.200 | Standard price $9.00, on Oxyy $3.60 | $0.050 | 60% | Sep 23, 2026 |
| Nano Banana 2gemini-3.1-flash-image | — | Standard price $0.500, on Oxyy $0.200 | Standard price $60.00, on Oxyy $24.00 | — | 60% | Feb 26, 2026 |
| Gemini 3.8 Flash-Lite TTSgemini-3.8-flash-lite-tts | — | Standard price $0.500, on Oxyy $0.200 | Standard price $6.00, on Oxyy $2.40 | $0.050 | 60% | Sep 23, 2026 |
| Gemini 2.5 Flash TTSgemini-2.5-flash-preview-tts | 8K | Standard price $0.500, on Oxyy $0.200one rate for input and output | — | 60% | May 20, 2025 | |
| Gemini 2.5 Pro TTSgemini-2.5-pro-preview-tts | 8K | Standard price $1.00, on Oxyy $0.400one rate for input and output | — | 60% | May 20, 2025 | |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)gemini-3.1-flash-lite-image | 66K | Standard price $0.250, on Oxyy $0.100 | Standard price $30.00, on Oxyy $12.00 | — | 60% | Jun 30, 2026 |
| Gemini Embedding 2google/gemini-embedding-2 | — | Standard price $0.200, on Oxyy $0.080one rate for input and output | — | 60% | — | |
| Gemini 3.5 Transcribegemini-3.5-transcribe | 96K | Standard price $2.00, on Oxyy $0.800 | Standard price $12.00, on Oxyy $4.80 | — | 60% | Aug 26, 2026 |
| Gemini 3.5 Transcribe Livegemini-3.5-transcribe-live | 96K | Standard price $3.50, on Oxyy $1.40 | Standard price $21.00, on Oxyy $8.40 | — | 60% | Aug 26, 2026 |
| Gemma 4 12B Unifiedgemma-4-12b-it | 262K | Standard price $0.100, on Oxyy $0.040 | Standard price $0.300, on Oxyy $0.120 | $0 | 60% | Apr 2, 2026 |
| Gemma 4 E2Bgemma-4-e2b-it | 131K | Standard price $0.040, on Oxyy $0.016 | Standard price $0.040, on Oxyy $0.016 | $0 | 60% | Apr 2, 2026 |
| Gemma 4 E4Bgemma-4-e4b-it | 131K | Standard price $0.200, on Oxyy $0.080 | Standard price $0.200, on Oxyy $0.080 | $0 | 60% | Apr 2, 2026 |
| Gemini 3.5 Flashgemini-3.5-flash | 1.05M | Standard price $1.50, on Oxyy $0.600 | Standard price $9.00, on Oxyy $3.60 | $0.060 | 60% | — |
| Model | Type | Price | Saving | Released |
|---|---|---|---|---|
| Gemini Omni Flashgemini-omni-1.1-flash | Text to video | Standard price $0.100, on Oxyy $0.040per second of generated video | 60% | — |
| Date | Model | Change |
|---|---|---|
| Sep 24, 2026 | 25 models | Discount changed: 70% → 60% off |
| Sep 22, 2026 | 20 models | Discount started: 70% off |
Estimate a month of Gemini API usage: set your input and output volume and how much of your input is a repeated prompt prefix served from cache, or start from a preset.
Estimated monthly cost for 10M input and 2M output tokens, with 0% of input served from cache.
| Gemini model | At standard price | On Oxyy | You save |
|---|---|---|---|
| Gemini 3.8 Flash | $15.00 | $6.00 | $9.00 (60%) |
| Gemini 3.6 Flash | $15.00 | $6.00 | $9.00 (60%) |
| Gemini 3 Flash | $11.00 | $4.40 | $6.60 (60%) |
| Gemini 2.5 Flash-Lite | $1.80 | $0.72 | $1.08 (60%) |
| Gemini 3.1 Flash-Lite | $5.50 | $2.20 | $3.30 (60%) |
| Gemini 2.5 Flash | $8.00 | $3.20 | $4.80 (60%) |
| Gemini 3.5 Flash-Lite | $8.00 | $3.20 | $4.80 (60%) |
| Gemini 4 Argon | $40.00 | $16.00 | $24.00 (60%) |
For each kind of work, the lowest-priced paid Gemini model tagged for it and the one developers use most on Oxyy.
| Need | Lowest price | Most used on Oxyy |
|---|---|---|
| Coding | Gemma 4 26B A4B Instruct (MoE)$0.052 / $0.160 per 1M tokens | Gemini 4 Argon |
| Reasoning | Gemma 4 26B A4B Instruct (MoE)$0.052 / $0.160 per 1M tokens | Gemini 4 Argon |
| Agents and tool use | Gemma 4 31B Instruct$0.108 / $0.304 per 1M tokens | Gemini 4 Argon |
| Long documents | Gemini 2.5 Flash-Lite$0.040 / $0.160 per 1M tokens | Gemini 3 Flash |
On Oxyy, Gemini 3.8 Flash costs $0.300 input / $1.50 output per 1M tokens at the pay-as-you-go price (standard price $0.750 / $3.75). Across paid Gemini text models, input runs from $0.016 to $0.800 per 1M tokens and output from $0.016 to $4.80. Text to video starts at $0.040 per second of generated video. There is no subscription: you pay only for what you use.
Cached input on Gemini 3.8 Flash costs $0.030 per 1M tokens on Oxyy, against $0.300 for regular input. Writing to the cache costs $0.300 per 1M tokens. The price table on this page lists the cache rate of every model that has one.
Yes. Oxyy's API is OpenAI-compatible: set the base URL to https://api.oxyy.ai/v1, use your Oxyy API key and pass the model id, for example "gemini-3.8-flash", to /v1/chat/completions. Text-to-speech models use /v1/audio/speech, image models use /v1/images/generations, embedding models use /v1/embeddings, transcription models use /v1/audio/transcriptions and video models use /v1/videos/generations.
No. Oxyy is an independent API gateway, not affiliated with or endorsed by Google. It gives you one API key and one bill for models from many AI labs, Google among them.
Legacy first-generation Gemini 3 Flash model providing baseline speed and intelligence with frontier-class multimodal understanding.
Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
Smallest and most cost-effective multimodal model in the 2.5 family, built for at-scale usage.
Cost-efficient multimodal model for high-volume agentic tasks, translation, and simple data extraction where budget and latency are the primary constraints.
Google's first hybrid reasoning model with configurable thinking budgets; best price-performance for low-latency, high-volume tasks that require reasoning.
Fastest, most cost-effective model in the 3.5 family, optimized for high-throughput agentic tasks, translation, and simple data processing.
Google's flagship reasoning model, for complex software engineering, maths and science, autonomous multi-step agents and long decode. Raises the output ceiling to 1M tokens.
Gemma 4's Mixture-of-Experts model. 25.2B total parameters but only 3.8B active per token, so it runs almost as fast as a 4B model while scoring close to the dense 31B.
High-speed, efficient Flash model built for everyday coding, agentic tool use, and reliable multi-step execution.
Third-generation Pro model built for multimodal understanding, agentic capability, and vibe-coding; improved thinking, token efficiency, and factual grounding over Gemini 3 Pro.
The largest Gemma 4 model: a 30.7B-parameter dense multimodal model for reasoning, agentic workflows, coding and multimodal understanding, deployable on consumer GPUs and workstations.
Previous-generation Flash model balancing speed and multimodal capability across general agentic and everyday tasks; strong at code generation, agentic execution, and spatial reasoning.
Powerful, low-latency speech generation with natural outputs, steerable prompts and expressive inline audio tags for precise narration control across 70+ languages.
Google's flagship text-to-speech model for voice design, voice acting and long-form audio.
High-efficiency production-scale image generation and editing, balancing speed with 4K generation, world knowledge and reliable text rendering. The generalist workhorse of the Nano Banana family.
Fast, cost-efficient text-to-speech for high-throughput production and real-time voice agent cascades.
Most advanced model of the 2.5 family, with deep reasoning and coding capability for complex tasks.
Fast and controllable text-to-speech for low-latency, cost-efficient applications and real-time assistants, with fine control over style and pacing.
High-fidelity speech synthesis optimized for quality in structured workflows such as podcasts and audiobooks, with more natural outputs and easier-to-steer prompts.
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image gene…
Google's first multimodal embedding model, mapping text, images, video, audio, and PDFs into a unified embedding space for semantic search and RAG.
High-accuracy, low-latency non-streaming speech-to-text with utterance-based language detection across 85+ languages, speaker diarization, word-level timestamps and custom vocabulary biasing.
Low-latency bidirectional streaming speech-to-text over WebSockets using the Live API, with interim and finalized transcription events, Smart transcription mode and multiple voice-activity-detection strategies.
Encoder-free multimodal Gemma 4 model. Instead of separate vision and audio encoders, it projects raw image patches and audio waveforms straight into the LLM's embedding space through lightweight linear layers, so every…
The smallest Gemma 4 model, built for efficient on-device execution on phones and laptops, with native audio input.
On-device Gemma 4 model for laptops and mobile devices, with native audio input. 'E' stands for effective parameters.
Legacy Flash model providing sustained frontier-level intelligence for real-world tasks; effective for sub-agent deployment, multi-step workflows, and long-horizon tasks at scale.
Fast conversational video generation and editing with native audio, keyframe interpolation and clip extension. Turn text and images into video and refine results through natural language.
