Models
One name per model, however many providers serve it.
Google: Gemini 2.5 Pro TTS
Accepts- Text
Creates- Audio
Gemini 2.5 Pro TTS is a text-to-speech model from Google.
google/gemini-2.5-pro-ttsNov 20, 20268K context30 voicesWAVabout 78,991 Toman per 1,000 charactersGoogle: Gemini 2.5 Flash TTS
Accepts- Text
Creates- Audio
Gemini 2.5 Flash TTS is a text-to-speech model from Google.
google/gemini-2.5-flash-ttsNov 20, 20268K context30 voicesWAVabout 39,495 Toman per 1,000 charactersGoogle: Gemini 4 Neon
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.
google/gemini-4-neonNov 18, 20261M context1,082,872 Toman/M input tokens5,407,528 Toman/M output tokensGoogle: Gemini 4 Hydrogen
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than…
google/gemini-4-hydrogenNov 12, 20261M context543,144 Toman/M input tokens2,705,472 Toman/M output tokensGoogle: Gemini 4 Carbon
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.
google/gemini-4-carbonNov 10, 20261M context720,776 Toman/M input tokens3,603,880 Toman/M output tokensGoogle: Gemini Omni 1.2 Flash
Accepts- Text
- Image
Creates- Video
Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash.
google/gemini-omni-1.2-flashNov 5, 20263–15 s720p · 1080p · 4K · 360pfrom 8,351 Toman/secondGoogle: Gemini Omni 1.1 Flash
Accepts- Text
- Image
Creates- Video
Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview.
google/gemini-omni-1.1-flashNov 4, 20263–10 s720p · 1080p · 4K · 360pfrom 12,179 Toman/secondGoogle: Gemini 4 Argon
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.
google/gemini-4-argonOct 13, 20261M context720,776 Toman/M input tokens3,603,880 Toman/M output tokensGoogle: Nano Banana 2.1
Accepts- Text
- Image
Creates- Text
- Image
ToolsJSONReasoningNano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.
google/gemini-nano-banana-2.1Oct 6, 202666K context543,144 Toman/M input tokens2,705,472 Toman/M output tokensGoogle: Gemini 3.5 Transcribe
Accepts- Audio
Creates- Text
Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers.
google/gemini-3.5-transcribeSep 25, 202698K contextWith segment and word times720,776 Toman/M in · 4,324,656 Toman/M outGoogle: Gemini 3.8 Flash Lite TTS
Accepts- Text
Creates- Audio
Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS.
google/gemini-3.8-flash-lite-ttsSep 23, 202633K context30 voicesWAVabout 23,769 Toman per 1,000 charactersGoogle: Gemini 3.8 Flash TTS
Accepts- Text
Creates- Audio
Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview.
google/gemini-3.8-flash-ttsSep 23, 202633K context30 voicesWAVabout 35,564 Toman per 1,000 charactersGoogle: Gemini 3.8 Flash
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
google/gemini-3.8-flashSep 2, 20261M context300,608 Toman/M input tokens1,489,376 Toman/M output tokensGoogle: Gemini 3.7 Flash
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.
google/gemini-3.7-flashAug 13, 20261M context273,280 Toman/M input tokens1,352,736 Toman/M output tokensGoogle: Gemini 3.6 Flash
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.
google/gemini-3.6-flashJul 21, 20261M context273,280 Toman/M input tokens1,352,736 Toman/M output tokensGoogle: Gemini 3.5 Flash Lite
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
google/gemini-3.5-flash-liteJul 21, 20261M context109,312 Toman/M input tokens901,824 Toman/M output tokensGoogle: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Accepts- Text
- Image
Creates- Text
- Image
JSONReasoningNano 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.
google/gemini-3.1-flash-lite-imageJun 30, 202666K context92,232 Toman/M input tokens543,144 Toman/M output tokensGoogle: Nano Banana 2 (Gemini 3.1 Flash Image)
Accepts- Text
- Image
Creates- Text
- Image
JSONReasoningGemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.
google/gemini-3.1-flash-imageJun 18, 2026131K context181,048 Toman/M input tokens1,082,872 Toman/M output tokensGoogle: Nano Banana Pro (Gemini 3 Pro Image)
Accepts- Text
- Image
Creates- Text
- Image
ToolsJSONReasoningNano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
google/gemini-3-pro-imageJun 18, 2026131K context720,776 Toman/M input tokens4,324,656 Toman/M output tokensGoogle: Gemini Embedding 2
Accepts- Text
CreatesGemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG).
google/gemini-embedding-2May 20, 20268K context72,078 Toman/M tokensGoogle: Gemini 3.5 Flash
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.
google/gemini-3.5-flashMay 19, 20261M context543,144 Toman/M input tokens3,245,200 Toman/M output tokensGoogle: Gemini 3.1 Flash Lite
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.
google/gemini-3.1-flash-liteMay 7, 20261M context92,232 Toman/M input tokens543,144 Toman/M output tokensGoogle: Chirp 3
Accepts- Audio
Creates- Text
Chirp 3 is Google's latest multilingual speech-to-text model.
google/chirp-3May 5, 2026Text only, no times5,766 Toman a minute of audioGoogle: Gemini Pro Latest
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningThis model always redirects to the latest model in the Gemini Pro family.
~google/gemini-pro-latestApr 27, 20261M context720,776 Toman/M input tokens3,603,880 Toman/M output tokensGoogle: Gemini Flash Latest
Accepts- Text
- Image
- Audio
- Video
- File (PDF)
Creates- Text
ToolsJSONReasoningThis model always redirects to the latest model in the Gemini Flash family.
~google/gemini-flash-latestApr 27, 20261M context543,144 Toman/M input tokens2,705,472 Toman/M output tokensGoogle: Gemini 3.1 Flash TTS Preview
Accepts- Text
Creates- Audio
Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a substantial generational step up from Gemini 2.5 Flash TTS.
google/gemini-3.1-flash-tts-previewApr 24, 202633K context30 voicesWAVabout 78,991 Toman per 1,000 charactersGoogle: Veo 3.1 Fast
Accepts- Text
- Image
Creates- Video
Google's mid-tier video generation model balancing speed and quality.
google/veo-3.1-fastApr 24, 20264–8 s720p · 1080p · 4Kfrom 28,831 Toman/secondGoogle: Veo 3.1 Lite
Accepts- Text
- Image
Creates- Video
Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration.
google/veo-3.1-liteApr 23, 20264–8 s720p · 1080pfrom 10,812 Toman/secondGoogle: Gemini Embedding 2 Preview
Accepts- Text
CreatesGemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG).
google/gemini-embedding-2-previewApr 17, 20268K context72,078 Toman/M tokensGoogle: Gemma 4 26B A4B
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
google/gemma-4-26b-a4b-itApr 3, 2026262K context27,328 Toman/M input tokens81,984 Toman/M output tokens
52 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

