The Gemini API and Google AI Studio let developers build with Google's Gemini models for text, code, images, video and speech. A free tier covers some models; paid use is billed per million tokens, such as $0.30 in and $2.50 out on Gemini 3.5 Flash-Lite.
The Gemini API is Google's developer interface to its Gemini models, and Google AI Studio is the browser workspace where developers try prompts, get an API key and test models. The model list covers text and code generation, image generation and editing, video generation, real-time audio for voice agents, transcription, live speech translation and text-to-speech. It is separate from the consumer Gemini app: the API is billed by usage, and enterprise deployments run through Google's Gemini Enterprise Agent Platform.
Google offers three levels. The Free tier gives limited access to certain models with free input and output tokens and AI Studio access, but content sent on the free tier may be used to improve Google's products. The Paid tier adds higher rate limits, context caching, a Batch API at half the standard cost and access to Google's most advanced models, and paid content is not used to improve products. As examples of standard paid rates per million tokens, Gemini 3.5 Flash-Lite costs $0.30 input and $2.50 output, Gemini 3.1 Flash-Lite $0.25 and $1.50, and Gemini 3.1 Pro $2 and $12 for prompts up to 200,000 tokens. Gemini 3.8 Flash costs $0.75 and $3.75 through 31 December 2026, then $1.50 and $7.50.
For speech, Gemini 3.8 Flash TTS costs $0.50 per million text input tokens and $9 per million audio output tokens through the end of 2026, with both doubling from 1 January 2027, and a free tier is listed for it. Several rates change on fixed dates, so recheck the pricing page before committing a budget.
There is a Free tier with free input and output tokens on certain models, but content sent on it may be used to improve Google's products. The Paid tier is billed per million tokens and does not use your content that way.
On the Paid tier, Gemini 3.5 Flash-Lite is listed at $0.30 per million input tokens and $2.50 per million output tokens, and it is also available on the Free tier.
Website: https://ai.google.dev/
Company: Google
Google's developer API for Gemini models, with a free tier and per-token paid rates; free-tier prompts may be used by Google. Rates change on fixed dates. 3.5 Flash-Lite $0.30 in / $2.50 out per million tokens.
| Pricing model | Freemium |
|---|---|
| Free tier | Yes · Free tokens on certain models via AI Studio; free-tier content may be used to improve Google products |
| Starting price | Not verified |
| Data residency | Not verified |
| Compliance (as stated by vendor) | Not verified |
| Integrations | Not verified |
| Public API | Yes |
| Self-hostable | No |
| Official site | Not verified |
| Can a general AI assistant replace it? | The Gemini app suits chatting. Use the API when you need Gemini models, including TTS, inside your own code; keep sensitive data on the Paid tier. |
| Last verified | 2026-10-12 by editor |
Open Interpreter is an open-source terminal agent, forked from Codex, that reads and edits files and runs commands inside an OS-level sandbox with approvals. It is free under Apache 2.0 and works with local models through Ollama or LM Studio.
Amazon Polly is the AWS text-to-speech service with Standard, Neural, Long-Form and Generative voices, billed per character. The free tier covers 5 million Standard characters a month; Neural voices cost $16 per million characters.
Azure Speech is Microsoft's cloud speech service for text to speech, speech to text, translation and voice agents, now sold as part of Microsoft Foundry. The free F0 tier includes 0.5 million neural text-to-speech characters a month.
Together AI is a cloud platform for running open models through a per-token serverless API, plus dedicated endpoints, GPU clusters and fine-tuning. Hosted GLM-5.3-Flash, for example, is listed at $0.15 input and $0.50 output per million tokens.
Kimi is Moonshot AI's assistant and model family, offered as the kimi.com agent workspace and as a pay-as-you-go API. The Kimi K2.7 Code model is listed at $0.95 input and $4.00 output per million tokens.
Z.ai offers the GLM model family through a chat app and a developer API billed per million tokens. GLM-5.3-Flash is listed at $0.15 input and $0.50 output, and the API is compatible with the OpenAI SDK.
Need the outcome rather than the software?