Google Gemini Free Tier Quotas

Rate limits for free (no-billing) projects · RPM · TPM · RPD

Available free quota 0 (paid / unavailable) N/A or not applicable

Text & Multimodal Models Gemini

gemini-2.5-flash
Best price-performance model. Low-latency, high-volume tasks with reasoning & agentic capabilities.
RPM
5
TPM
250k
RPD
20
gemini-2.5-flash-lite
Fastest & most budget-friendly multimodal model in the 2.5 family. Ideal for high-throughput tasks.
RPM
10
TPM
250k
RPD
20
gemini-2.5-pro
Most advanced 2.5 model for complex reasoning, coding and deep problem-solving.
RPM
0
TPM
0
RPD
0
gemini-3-flash
Frontier-class performance at Flash speed and cost. Strong multimodal & agentic capabilities.
RPM
5
TPM
250k
RPD
20
gemini-3.1-flash-lite
Frontier-class performance rivaling larger models at a fraction of the cost. High throughput.
RPM
15
TPM
250k
RPD
500
gemini-3.1-pro
Advanced intelligence for complex problem-solving, agentic workflows and vibe coding.
RPM
0
TPM
0
RPD
0
gemini-3.5-flash
Most intelligent model for sustained frontier performance on agentic and coding tasks.
RPM
5
TPM
250k
RPD
20
gemini-3.5-flash-lite
Fastest, most cost-effective 3.5 model for high-throughput execution.
RPM
15
TPM
250k
RPD
500
gemini-3.6-flash
Latest balanced model — strong agentic & multimodal performance with improved token efficiency.
RPM
5
TPM
250k
RPD
20
gemini-2-flash
Previous-generation Flash model (legacy). Superseded by 2.5 / 3.x Flash.
RPM
0
TPM
0
RPD
0
gemini-2-flash-lite
Previous-generation lightweight Flash model (legacy).
RPM
0
TPM
0
RPD
0

Text-to-Speech Audio

gemini-2.5-flash-tts
Controllable text-to-speech with fine control over style and pacing. Low-latency.
RPM
3
TPM
10k
RPD
10
gemini-2.5-pro-tts
High-fidelity speech synthesis optimized for quality (podcasts, audiobooks).
RPM
0
TPM
0
RPD
0
gemini-3.1-flash-tts
Powerful low-latency speech generation with natural outputs and expressive control.
RPM
3
TPM
10k
RPD
10

Embeddings Retrieval

gemini-embedding-1
High-quality text embeddings for semantic search, classification and RAG systems.
RPM
100
TPM
30k
RPD
1000
gemini-embedding-2
First multimodal embedding model. Maps text, images, video, audio & PDFs into one unified space.
RPM
100
TPM
30k
RPD
1000

Open Models Gemma

gemma-4-26b
Gemma 4 26B MoE (≈4B active). Efficient open-weight multimodal model for high-throughput reasoning.
RPM
30
TPM
16k
RPD
14.4k
gemma-4-31b
Gemma 4 31B dense. Highest-quality open model in the family — strong reasoning & coding.
RPM
30
TPM
16k
RPD
14.4k

Agents & Specialized Preview

antigravity
Managed agent that plans, reasons, runs code, manages files and browses the web in a secure Linux sandbox.
RPM
60
TPM
100k
RPD
100
deep-research-pro-preview
Deep research agent for multi-step investigation and synthesis of complex topics.
RPM
0
TPM
0
RPD
0
computer-use-preview
Computer-use model that can control a browser / desktop UI for end-to-end task execution.
RPM
0
TPM
0
RPD
0
gemini-robotics-er-1.5-preview
Embodied reasoning model for robotics — understands physical spaces and multi-step robot tasks.
RPM
10
TPM
250k
RPD
20
gemini-robotics-er-1.6-preview
Advanced robotics model with improved spatial reasoning, instrument reading and physical planning.
RPM
5
TPM
250k
RPD
20
gemini-omni-flash-preview
Fast conversational video generation & editing — turn text/images into video via natural language.
RPM
0
TPM
0
RPD
0

Image Generation Imagen / Nano Banana

gemini-2.5-flash-image
Native image generation & editing (Nano Banana) powered by Gemini 2.5 Flash.
RPM
0
TPM
0
RPD
0
gemini-3-pro-image
High-quality native image generation model from the Gemini 3 Pro series.
RPM
0
TPM
0
RPD
0
gemini-3-pro-image-preview
Preview of Gemini 3 Pro native image generation & editing capabilities.
RPM
0
TPM
0
RPD
0
gemini-3.1-flash-image
Efficient native image generation & editing based on Gemini 3.1 Flash.
RPM
0
TPM
0
RPD
0
gemini-3.1-flash-image-preview
Preview of Gemini 3.1 Flash image generation model.
RPM
0
TPM
0
RPD
0
gemini-3.1-flash-lite-image
Lightweight image generation variant of Gemini 3.1 Flash-Lite.
RPM
0
TPM
0
RPD
0
imagen-4-fast
Fast text-to-image model. High clarity up to 2K resolution, optimized for speed.
RPM
—
TPM
—
RPD
25
imagen-4
High-quality text-to-image generation with excellent detail and typography.
RPM
—
TPM
—
RPD
25
imagen-4-ultra
Highest-quality Imagen 4 variant for photorealistic and detailed creative work.
RPM
—
TPM
—
RPD
25

Video Generation Veo

veo-3
State-of-the-art cinematic video generation with synchronized audio and speech.
RPM
0
TPM
—
RPD
0
veo-3-fast
Faster variant of Veo 3 optimized for lower latency video generation.
RPM
0
TPM
—
RPD
0
veo-3-lite
High-efficiency, low-cost developer-first video generation from the Veo 3 family.
RPM
0
TPM
—
RPD
0

Music Generation Lyria

lyria-3-clip
Optimized for short musical clips (≈30 s) from text, images or video prompts.
RPM
0
TPM
0
RPD
0
lyria-3-pro
Flagship music model for full-length songs with complex structure, vocals and lyrics.
RPM
0
TPM
0
RPD
0