# AI models, providers and list rates — INFRO model reference

> 293 text, image, video and audio models. Each rate is the vendor's published list price, billed by the customer's own provider account; INFRO adds 0% to model spend. Checked 2026-10-05. Page: https://infro.io/models

## Alibaba

All Alibaba models: https://infro.io/md/models/alibaba.md

- [Qwen3.8 Max](https://infro.io/md/models/qwen/qwen3.8-max.md) `qwen/qwen3.8-max` — $2.00 per 1M input tokens and $6.00 per 1M output tokens
- [Qwen3.8 Flash](https://infro.io/md/models/qwen/qwen3.8-flash.md) `qwen/qwen3.8-flash` — $0.15 per 1M input tokens and $0.47 per 1M output tokens
- [Qwen3.8 27B](https://infro.io/md/models/qwen/qwen3.8-27b.md) `qwen/qwen3.8-27b` — $0.50 per 1M input tokens and $3.00 per 1M output tokens
- [Qwen3-Coder](https://infro.io/md/models/qwen/qwen3-coder.md) `qwen/qwen3-coder` — $1.00 per 1M input tokens and $5.00 per 1M output tokens
- [Qwen3.7 Plus](https://infro.io/md/models/qwen/qwen3.7-plus.md) `qwen/qwen3.7-plus` — $0.40 per 1M input tokens and $1.60 per 1M output tokens
- [Qwen3.7 Max](https://infro.io/md/models/qwen/qwen3.7-max.md) `qwen/qwen3.7-max` — $2.50 per 1M input tokens and $7.50 per 1M output tokens
- [Qwen3-Coder Flash](https://infro.io/md/models/qwen/qwen3-coder-flash.md) `qwen/qwen3-coder-flash` — $0.30 per 1M input tokens and $1.50 per 1M output tokens
- [Qwen3-Coder Next](https://infro.io/md/models/qwen/qwen3-coder-next.md) `qwen/qwen3-coder-next` — $0.30 per 1M input tokens and $1.50 per 1M output tokens
- [Qwen3-VL Plus](https://infro.io/md/models/qwen/qwen3-vl-plus.md) `qwen/qwen3-vl-plus` — $0.20 per 1M input tokens and $1.60 per 1M output tokens
- [Qwen-VL Max](https://infro.io/md/models/qwen/qwen-vl-max.md) `qwen/qwen-vl-max` — $0.80 per 1M input tokens and $3.20 per 1M output tokens
- [Qwen3.5 9B](https://infro.io/md/models/qwen/qwen3.5-9b.md) `qwen/qwen3.5-9b` — $0.17 per 1M input tokens and $0.25 per 1M output tokens
- [Qwen3.6 Plus](https://infro.io/md/models/qwen/qwen3.6-plus.md) `qwen/qwen3.6-plus` — $0.50 per 1M input tokens and $3.00 per 1M output tokens
- [Qwen-Image 3.0](https://infro.io/md/models/qwen/qwen-image-3.md) `qwen/qwen-image-3` — $0.03 per image
- [Qwen-Image 3.0 Pro](https://infro.io/md/models/qwen/qwen-image-3-pro.md) `qwen/qwen-image-3-pro` — $0.04 per image
- [Wan 2.7 Image Pro](https://infro.io/md/models/alibaba/wan-2.7-image-pro.md) `alibaba/wan-2.7-image-pro` — $0.075 per image
- [Wan 2.7 Image](https://infro.io/md/models/alibaba/wan-2.7-image.md) `alibaba/wan-2.7-image` — $0.03 per image
- [Wan 2.7](https://infro.io/md/models/alibaba/wan-2.7.md) `alibaba/wan-2.7` — $0.10 per second of video
- [Wan 3.0](https://infro.io/md/models/alibaba/wan-3.0.md) `alibaba/wan-3.0` — $0.10 per second of video
- [HappyHorse 1.1](https://infro.io/md/models/alibaba/happyhorse-1.1.md) `alibaba/happyhorse-1.1` — $0.14 per second of video
- [Wan 3.0 Prime](https://infro.io/md/models/alibaba/wan-3.0-prime.md) `alibaba/wan-3.0-prime` — $0.14 per second of video
- [Wan 2.6](https://infro.io/md/models/alibaba/wan-2.6.md) `alibaba/wan-2.6` — $0.08 per second of video
- [HappyHorse 1.0](https://infro.io/md/models/alibaba/happyhorse-1.0.md) `alibaba/happyhorse-1.0` — $0.099 per second of video
- [Qwen Audio 3.0 TTS Plus](https://infro.io/md/models/qwen/qwen-audio-3.0-tts-plus.md) `qwen/qwen-audio-3.0-tts-plus` — $20 per 1M characters
- [Qwen Audio 3.0 TTS Flash](https://infro.io/md/models/qwen/qwen-audio-3.0-tts-flash.md) `qwen/qwen-audio-3.0-tts-flash` — $15 per 1M characters
- [Qwen3-ASR Flash](https://infro.io/md/models/qwen/qwen3-asr-flash.md) `qwen/qwen3-asr-flash` — $0.126 per audio hour

## Amazon

All Amazon models: https://infro.io/md/models/amazon.md

- [Amazon Nova 2 Lite](https://infro.io/md/models/amazon/nova-2-lite.md) `amazon/nova-2-lite` — $0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [Amazon Nova Pro](https://infro.io/md/models/amazon/nova-pro.md) `amazon/nova-pro` — $0.80 per 1M input tokens and $3.20 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Amazon Nova Lite](https://infro.io/md/models/amazon/nova-lite.md) `amazon/nova-lite` — $0.06 per 1M input tokens and $0.24 per 1M output tokens, with cached input at $0.015 per 1M tokens
- [Amazon Nova Micro](https://infro.io/md/models/amazon/nova-micro.md) `amazon/nova-micro` — $0.035 per 1M input tokens and $0.14 per 1M output tokens, with cached input at $0.0088 per 1M tokens

## Anthropic

All Anthropic models: https://infro.io/md/models/anthropic.md

- [Claude Fable 5](https://infro.io/md/models/anthropic/claude-fable-5.md) `anthropic/claude-fable-5` — $10 per 1M input tokens and $50 per 1M output tokens, with cached input at $1.00 per 1M tokens
- [Claude Fable 5.1](https://infro.io/md/models/anthropic/claude-fable-5.1.md) `anthropic/claude-fable-5.1` — $10 per 1M input tokens and $50 per 1M output tokens, with cached input at $0.25 per 1M tokens
- [Claude Opus 5.5](https://infro.io/md/models/anthropic/claude-opus-5.5.md) `anthropic/claude-opus-5.5` — $4.00 per 1M input tokens and $20 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Claude Opus 5](https://infro.io/md/models/anthropic/claude-opus-5.md) `anthropic/claude-opus-5` — $5.00 per 1M input tokens and $25 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Claude Sonnet 5.5](https://infro.io/md/models/anthropic/claude-sonnet-5.5.md) `anthropic/claude-sonnet-5.5` — $2.00 per 1M input tokens and $10 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Claude Sonnet 5](https://infro.io/md/models/anthropic/claude-sonnet-5.md) `anthropic/claude-sonnet-5` — $2.00 per 1M input tokens and $10 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Claude Haiku 4.5](https://infro.io/md/models/anthropic/claude-haiku-4.5.md) `anthropic/claude-haiku-4.5` — $1.00 per 1M input tokens and $5.00 per 1M output tokens, with cached input at $0.10 per 1M tokens
- [Claude Opus 4.8](https://infro.io/md/models/anthropic/claude-opus-4.8.md) `anthropic/claude-opus-4.8` — $5.00 per 1M input tokens and $25 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Claude Opus 4.7](https://infro.io/md/models/anthropic/claude-opus-4.7.md) `anthropic/claude-opus-4.7` — $5.00 per 1M input tokens and $25 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Claude Opus 4.6](https://infro.io/md/models/anthropic/claude-opus-4.6.md) `anthropic/claude-opus-4.6` — $5.00 per 1M input tokens and $25 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Claude Opus 4.5](https://infro.io/md/models/anthropic/claude-opus-4.5.md) `anthropic/claude-opus-4.5` — $5.00 per 1M input tokens and $25 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Claude Sonnet 4.6](https://infro.io/md/models/anthropic/claude-sonnet-4.6.md) `anthropic/claude-sonnet-4.6` — $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens

## AssemblyAI

All AssemblyAI models: https://infro.io/md/models/assemblyai.md

- [Universal-3](https://infro.io/md/models/assemblyai/universal-3.md) `assemblyai/universal-3` — $0.27 per audio hour
- [Universal-3.5 Pro](https://infro.io/md/models/assemblyai/universal-3.5-pro.md) `assemblyai/universal-3.5-pro` — $0.45 per audio hour

## Black Forest Labs

All Black Forest Labs models: https://infro.io/md/models/bfl.md

- [FLUX.2 [pro]](https://infro.io/md/models/bfl/flux-2-pro.md) `bfl/flux-2-pro` — $0.03 per image
- [FLUX.2 [dev]](https://infro.io/md/models/bfl/flux-2-dev.md) `bfl/flux-2-dev` — $0.025 per image
- [FLUX.2 [max]](https://infro.io/md/models/bfl/flux-2-max.md) `bfl/flux-2-max` — $0.07 per image
- [FLUX.2 [flex]](https://infro.io/md/models/bfl/flux-2-flex.md) `bfl/flux-2-flex` — $0.05 per image
- [FLUX.2 [klein] 9B](https://infro.io/md/models/bfl/flux-2-klein-9b.md) `bfl/flux-2-klein-9b` — $0.015 per image
- [FLUX.2 [klein] 4B](https://infro.io/md/models/bfl/flux-2-klein-4b.md) `bfl/flux-2-klein-4b` — $0.014 per image
- [FLUX 3](https://infro.io/md/models/bfl/flux-3.md) `bfl/flux-3` — $0.17 per second of video

## Bria

All Bria models: https://infro.io/md/models/bria.md

- [Bria Remove Background](https://infro.io/md/models/bria/remove-background.md) `bria/remove-background` — $0.018 per image
- [Bria Expand](https://infro.io/md/models/bria/expand.md) `bria/expand` — $0.04 per image

## ByteDance

All ByteDance models: https://infro.io/md/models/bytedance.md

- [Seedream 5.0 Pro](https://infro.io/md/models/bytedance/seedream-5-pro.md) `bytedance/seedream-5-pro` — $0.045 per image
- [Seedream 5.0 Lite](https://infro.io/md/models/bytedance/seedream-5-lite.md) `bytedance/seedream-5-lite` — $0.035 per image
- [Seedream 5.0 Flash](https://infro.io/md/models/bytedance/seedream-5-flash.md) `bytedance/seedream-5-flash` — $0.018 per image
- [Seedream 4.5](https://infro.io/md/models/bytedance/seedream-4.5.md) `bytedance/seedream-4.5` — $0.04 per image
- [Seedream 4.0](https://infro.io/md/models/bytedance/seedream-4.md) `bytedance/seedream-4` — $0.03 per image
- [Seedance 2.5](https://infro.io/md/models/bytedance/seedance-2.5.md) `bytedance/seedance-2.5` — $0.231 per second of video
- [Seedance 1.5 Pro](https://infro.io/md/models/bytedance/seedance-1.5-pro.md) `bytedance/seedance-1.5-pro` — $0.052 per second of video
- [OmniHuman 1.5](https://infro.io/md/models/bytedance/omnihuman-1.5.md) `bytedance/omnihuman-1.5` — $0.12 per second of video
- [Seedance 1.0 Pro](https://infro.io/md/models/bytedance/seedance-1.0-pro.md) `bytedance/seedance-1.0-pro` — $0.052 per second of video
- [Seedance 1.0 Pro Fast](https://infro.io/md/models/bytedance/seedance-1.0-pro-fast.md) `bytedance/seedance-1.0-pro-fast` — $0.02 per second of video
- [Seedance 2.0](https://infro.io/md/models/bytedance/seedance-2.0.md) `bytedance/seedance-2.0` — $0.15 per second of video
- [Seedance 2.0 Fast](https://infro.io/md/models/bytedance/seedance-2.0-fast.md) `bytedance/seedance-2.0-fast` — $0.12 per second of video
- [Seedance 2.0 Mini](https://infro.io/md/models/bytedance/seedance-2.0-mini.md) `bytedance/seedance-2.0-mini` — $0.08 per second of video
- [OmniHuman](https://infro.io/md/models/bytedance/omnihuman.md) `bytedance/omnihuman` — $0.14 per second of video
- [Seed Audio](https://infro.io/md/models/bytedance/seed-audio.md) `bytedance/seed-audio` — $0.0025 per second of video

## Canopy Labs

All Canopy Labs models: https://infro.io/md/models/canopylabs.md

- [Orpheus V1 English](https://infro.io/md/models/canopylabs/orpheus-v1-english.md) `canopylabs/orpheus-v1-english` — $22 per 1M characters
- [Orpheus Arabic (Saudi)](https://infro.io/md/models/canopylabs/orpheus-arabic-saudi.md) `canopylabs/orpheus-arabic-saudi` — $40 per 1M characters
- [Orpheus 3B](https://infro.io/md/models/canopylabs/orpheus-3b.md) `canopylabs/orpheus-3b` — $15 per 1M characters

## Cartesia

All Cartesia models: https://infro.io/md/models/cartesia.md

- [Sonic 3](https://infro.io/md/models/cartesia/sonic-3.md) `cartesia/sonic-3` — $55 per 1M characters

## Clarity AI

All Clarity AI models: https://infro.io/md/models/clarity.md

- [Clarity Upscaler](https://infro.io/md/models/clarity/clarity-upscaler.md) `clarity/clarity-upscaler` — unpriced

## Cloudflare

All Cloudflare models: https://infro.io/md/models/cloudflare.md

- [Clef](https://infro.io/md/models/cloudflare/clef.md) `cloudflare/clef` — $0.24 per 1M input tokens and output tokens free
- [Clef Flash](https://infro.io/md/models/cloudflare/clef-flash.md) `cloudflare/clef-flash` — $0.038 per 1M input tokens and output tokens free
- [Clef Omni](https://infro.io/md/models/cloudflare/clef-omni.md) `cloudflare/clef-omni` — $0.15 per 1M input tokens and output tokens free

## Cohere

All Cohere models: https://infro.io/md/models/cohere.md

- [Command R](https://infro.io/md/models/cohere/command-r.md) `cohere/command-r` — $0.15 per 1M input tokens and $0.60 per 1M output tokens
- [Command R7B](https://infro.io/md/models/cohere/command-r7b.md) `cohere/command-r7b` — $0.037 per 1M input tokens and $0.15 per 1M output tokens
- [Command R+](https://infro.io/md/models/cohere/command-r-plus.md) `cohere/command-r-plus` — $2.50 per 1M input tokens and $10 per 1M output tokens
- [Aya Expanse 32B](https://infro.io/md/models/cohere/aya-expanse-32b.md) `cohere/aya-expanse-32b` — $0.50 per 1M input tokens and $1.50 per 1M output tokens

## Deepgram

All Deepgram models: https://infro.io/md/models/deepgram.md

- [Nova-4](https://infro.io/md/models/deepgram/nova-4.md) `deepgram/nova-4` — $0.26 per audio hour
- [Aura-2](https://infro.io/md/models/deepgram/aura-2.md) `deepgram/aura-2` — $30 per 1M characters
- [Flux TTS](https://infro.io/md/models/deepgram/flux-tts.md) `deepgram/flux-tts` — $45 per 1M characters
- [Nova-3](https://infro.io/md/models/deepgram/nova-3.md) `deepgram/nova-3` — $0.258 per audio hour

## DeepSeek

All DeepSeek models: https://infro.io/md/models/deepseek.md

- [DeepSeek Flash (V4.1)](https://infro.io/md/models/deepseek/deepseek-flash.md) `deepseek/deepseek-flash` — $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens
- [DeepSeek V4 Pro](https://infro.io/md/models/deepseek/deepseek-v4-pro.md) `deepseek/deepseek-v4-pro` — $1.32 per 1M input tokens and $3.96 per 1M output tokens, with cached input at $0.044 per 1M tokens
- [DeepSeek V4 Flash](https://infro.io/md/models/deepseek/deepseek-v4-flash.md) `deepseek/deepseek-v4-flash` — $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens

## ElevenLabs

All ElevenLabs models: https://infro.io/md/models/elevenlabs.md

- [ElevenLabs V3](https://infro.io/md/models/elevenlabs/eleven-v3.md) `elevenlabs/eleven-v3` — $80 per 1M characters
- [ElevenLabs V4](https://infro.io/md/models/elevenlabs/eleven-v4.md) `elevenlabs/eleven-v4` — $80 per 1M characters
- [ElevenLabs Flash v2.5](https://infro.io/md/models/elevenlabs/eleven-flash-v2.5.md) `elevenlabs/eleven-flash-v2.5` — $40 per 1M characters
- [Scribe v2](https://infro.io/md/models/elevenlabs/scribe-v2.md) `elevenlabs/scribe-v2` — $0.22 per audio hour
- [ElevenLabs V4 Turbo](https://infro.io/md/models/elevenlabs/eleven-v4-turbo.md) `elevenlabs/eleven-v4-turbo` — $40 per 1M characters
- [ElevenLabs Multilingual v2](https://infro.io/md/models/elevenlabs/eleven-multilingual-v2.md) `elevenlabs/eleven-multilingual-v2` — $80 per 1M characters
- [ElevenLabs Flash v2](https://infro.io/md/models/elevenlabs/eleven-flash-v2.md) `elevenlabs/eleven-flash-v2` — $40 per 1M characters
- [Scribe v2 Medical](https://infro.io/md/models/elevenlabs/scribe-v2-medical.md) `elevenlabs/scribe-v2-medical` — $0.22 per audio hour
- [ElevenLabs Sound Effects v2](https://infro.io/md/models/elevenlabs/sound-effects-v2.md) `elevenlabs/sound-effects-v2` — $0.0020 per second of video
- [Eleven Music](https://infro.io/md/models/elevenlabs/music.md) `elevenlabs/music` — $0.0025 per second of video

## fal

All fal models: https://infro.io/md/models/fal.md

- [Creative Upscaler](https://infro.io/md/models/fal/creative-upscaler.md) `fal/creative-upscaler` — unpriced

## Fireworks

All Fireworks models: https://infro.io/md/models/fireworks.md

- [Ember-1](https://infro.io/md/models/fireworks/ember-1.md) `fireworks/ember-1` — $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens

## Fish Audio

All Fish Audio models: https://infro.io/md/models/fish-audio.md

- [Fish Audio S2.1 Pro](https://infro.io/md/models/fish-audio/s2.1-pro.md) `fish-audio/s2.1-pro` — $15 per 1M characters
- [Fish Audio S2 Pro](https://infro.io/md/models/fish-audio/s2-pro.md) `fish-audio/s2-pro` — $15 per 1M characters
- [Fish Audio S1](https://infro.io/md/models/fish-audio/s1.md) `fish-audio/s1` — $15 per 1M characters
- [Fish Audio Transcribe 1](https://infro.io/md/models/fish-audio/transcribe-1.md) `fish-audio/transcribe-1` — $0.36 per audio hour
- [Fish Audio Transcribe 1 Pro](https://infro.io/md/models/fish-audio/transcribe-1-pro.md) `fish-audio/transcribe-1-pro` — $0.36 per audio hour

## Google

All Google models: https://infro.io/md/models/google.md

- [Gemini 3.1 Pro](https://infro.io/md/models/google/gemini-3.1-pro.md) `google/gemini-3.1-pro` — $2.00 per 1M input tokens and $12 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Gemini 3.8 Flash](https://infro.io/md/models/google/gemini-3.8-flash.md) `google/gemini-3.8-flash` — $0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [Gemini 3.7 Flash](https://infro.io/md/models/google/gemini-3.7-flash.md) `google/gemini-3.7-flash` — $0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [Gemini 3.6 Flash](https://infro.io/md/models/google/gemini-3.6-flash.md) `google/gemini-3.6-flash` — $0.75 per 1M input tokens and $3.75 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [Gemini 3.5 Flash](https://infro.io/md/models/google/gemini-3.5-flash.md) `google/gemini-3.5-flash` — $1.50 per 1M input tokens and $9.00 per 1M output tokens, with cached input at $0.15 per 1M tokens
- [Gemini 3.5 Flash-Lite](https://infro.io/md/models/google/gemini-3.5-flash-lite.md) `google/gemini-3.5-flash-lite` — $0.30 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.03 per 1M tokens
- [Gemini 3.1 Flash-Lite](https://infro.io/md/models/google/gemini-3.1-flash-lite.md) `google/gemini-3.1-flash-lite` — $0.25 per 1M input tokens and $1.50 per 1M output tokens, with cached input at $0.025 per 1M tokens
- [Gemini 3 Flash (Preview)](https://infro.io/md/models/google/gemini-3-flash.md) `google/gemini-3-flash` — $0.50 per 1M input tokens and $3.00 per 1M output tokens, with cached input at $0.05 per 1M tokens
- [Nano Banana Pro](https://infro.io/md/models/google/nano-banana-pro.md) `google/nano-banana-pro` — $0.134 per image
- [Nano Banana 2](https://infro.io/md/models/google/nano-banana-2.md) `google/nano-banana-2` — $0.067 per image
- [Nano Banana 2 Lite](https://infro.io/md/models/google/nano-banana-2-lite.md) `google/nano-banana-2-lite` — $0.034 per image
- [Nano Banana](https://infro.io/md/models/google/nano-banana.md) `google/nano-banana` — $0.039 per image
- [Veo 3.1](https://infro.io/md/models/google/veo-3.1.md) `google/veo-3.1` — $0.40 per second of video
- [Veo 3.1 Fast](https://infro.io/md/models/google/veo-3.1-fast.md) `google/veo-3.1-fast` — $0.10 per second of video
- [Veo 3.1 Lite](https://infro.io/md/models/google/veo-3.1-lite.md) `google/veo-3.1-lite` — $0.05 per second of video
- [Gemini Omni Flash](https://infro.io/md/models/google/gemini-omni-flash.md) `google/gemini-omni-flash` — $0.101 per second of video
- [Gemini 3.1 Flash TTS](https://infro.io/md/models/google/gemini-3.1-flash-tts.md) `google/gemini-3.1-flash-tts` — $16 per 1M characters
- [Gemini 3.5 Transcribe](https://infro.io/md/models/google/gemini-3.5-transcribe.md) `google/gemini-3.5-transcribe` — $0.30 per audio hour
- [Lyria 3.5](https://infro.io/md/models/google/lyria-3.5.md) `google/lyria-3.5` — $0.08 per track
- [Lyria 3 Clip (Preview)](https://infro.io/md/models/google/lyria-3-clip.md) `google/lyria-3-clip` — $0.04 per track
- [Chirp 3](https://infro.io/md/models/google/chirp-3.md) `google/chirp-3` — $0.96 per audio hour
- [Imagen Upscaler](https://infro.io/md/models/google/imagen-upscaler.md) `google/imagen-upscaler` — $0.02 per image
- [Lyria 2](https://infro.io/md/models/google/lyria-2.md) `google/lyria-2` — $0.0020 per second of video

## HeyGen

All HeyGen models: https://infro.io/md/models/heygen.md

- [HeyGen Video 1](https://infro.io/md/models/heygen/heygen-video-1.md) `heygen/heygen-video-1` — $0.02 per second of video

## IC-Light

All IC-Light models: https://infro.io/md/models/iclight.md

- [IC-Light v2](https://infro.io/md/models/iclight/ic-light-v2.md) `iclight/ic-light-v2` — unpriced

## Ideogram

All Ideogram models: https://infro.io/md/models/ideogram.md

- [Ideogram 3.0](https://infro.io/md/models/ideogram/ideogram-3.md) `ideogram/ideogram-3` — $0.06 per image
- [Ideogram 4.0](https://infro.io/md/models/ideogram/ideogram-4.md) `ideogram/ideogram-4` — $0.06 per image
- [Ideogram 3.0 Reframe](https://infro.io/md/models/ideogram/ideogram-3-reframe.md) `ideogram/ideogram-3-reframe` — $0.06 per image

## Inception

All Inception models: https://infro.io/md/models/inception.md

- [Mercury Decide](https://infro.io/md/models/inception/mercury-decide.md) `inception/mercury-decide` — $0.02 per 1M input tokens and output tokens free

## Kokoro

All Kokoro models: https://infro.io/md/models/hexgrad.md

- [Kokoro 82M](https://infro.io/md/models/hexgrad/kokoro-82m.md) `hexgrad/kokoro-82m` — $4.00 per 1M characters

## Kuaishou

All Kuaishou models: https://infro.io/md/models/kuaishou.md

- [Kling Image 3.0](https://infro.io/md/models/kuaishou/kling-image-3.md) `kuaishou/kling-image-3` — $0.028 per image
- [Kling Image 3.0 Omni](https://infro.io/md/models/kuaishou/kling-image-o3.md) `kuaishou/kling-image-o3` — $0.028 per image
- [Kling O3](https://infro.io/md/models/kuaishou/kling-o3.md) `kuaishou/kling-o3` — $0.084 per second of video
- [Kling 3.0](https://infro.io/md/models/kuaishou/kling-v3.md) `kuaishou/kling-v3` — $0.084 per second of video
- [Kling 3.0 Turbo](https://infro.io/md/models/kuaishou/kling-v3-turbo.md) `kuaishou/kling-v3-turbo` — $0.112 per second of video
- [Kling O1](https://infro.io/md/models/kuaishou/kling-o1.md) `kuaishou/kling-o1` — $0.112 per second of video
- [Kling Lip-Sync](https://infro.io/md/models/kuaishou/kling-lipsync.md) `kuaishou/kling-lipsync` — $0.014 per second of video
- [Kling AI Avatar v2 Pro](https://infro.io/md/models/kuaishou/kling-avatar-v2-pro.md) `kuaishou/kling-avatar-v2-pro` — $0.115 per second of video

## Liquid AI

All Liquid AI models: https://infro.io/md/models/liquid.md

- [d1](https://infro.io/md/models/liquid/d1.md) `liquid/d1` — $0.04 per 1M input tokens and output tokens free

## Luma

All Luma models: https://infro.io/md/models/luma.md

- [Uni-1.1](https://infro.io/md/models/luma/uni-1.md) `luma/uni-1` — $0.04 per image
- [Uni-1.1 Max](https://infro.io/md/models/luma/uni-1-max.md) `luma/uni-1-max` — $0.10 per image
- [Ray 3.2](https://infro.io/md/models/luma/ray-3.2.md) `luma/ray-3.2` — $0.06 per second of video

## Magnific

All Magnific models: https://infro.io/md/models/magnific.md

- [Magnific Precision Upscaler v2](https://infro.io/md/models/magnific/precision-upscaler-v2.md) `magnific/precision-upscaler-v2` — $0.25 per image
- [Magnific Creative Video Upscaler](https://infro.io/md/models/magnific/video-upscaler-creative.md) `magnific/video-upscaler-creative` — $0.168 per second of video

## Meta

All Meta models: https://infro.io/md/models/meta.md

- [Llama 3.3 70B](https://infro.io/md/models/meta/llama-3.3-70b.md) `meta/llama-3.3-70b` — $1.04 per 1M input tokens and $1.04 per 1M output tokens
- [Muse Glimmer 30B](https://infro.io/md/models/meta/muse-glimmer-30b.md) `meta/muse-glimmer-30b` — $0.35 per 1M input tokens and $1.50 per 1M output tokens, with cached input at $0.04 per 1M tokens
- [Muse Voice Transcribe 1.0](https://infro.io/md/models/meta/muse-voice-transcribe-1.0.md) `meta/muse-voice-transcribe-1.0` — $0.18 per audio hour

## Microsoft

All Microsoft models: https://infro.io/md/models/microsoft.md

- [Microsoft-Decision-1](https://infro.io/md/models/microsoft/microsoft-decision-1.md) `microsoft/microsoft-decision-1` — $0.042 per 1M input tokens and output tokens free
- [MAI-Voice 2.1](https://infro.io/md/models/microsoft/mai-voice-2.1.md) `microsoft/mai-voice-2.1` — $22 per 1M characters
- [MAI-Voice 2.1 Flash](https://infro.io/md/models/microsoft/mai-voice-2.1-flash.md) `microsoft/mai-voice-2.1-flash` — $15 per 1M characters
- [MAI-Voice 2](https://infro.io/md/models/microsoft/mai-voice-2.md) `microsoft/mai-voice-2` — $22 per 1M characters
- [MAI-Voice 2 Flash](https://infro.io/md/models/microsoft/mai-voice-2-flash.md) `microsoft/mai-voice-2-flash` — $15 per 1M characters
- [MAI-Transcribe 2](https://infro.io/md/models/microsoft/mai-transcribe-2.md) `microsoft/mai-transcribe-2` — $0.10 per audio hour
- [MAI-Transcribe 1.5](https://infro.io/md/models/microsoft/mai-transcribe-1.5.md) `microsoft/mai-transcribe-1.5` — $0.36 per audio hour

## MiniMax

All MiniMax models: https://infro.io/md/models/minimax.md

- [MiniMax M3](https://infro.io/md/models/minimax/minimax-m3.md) `minimax/minimax-m3` — $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.06 per 1M tokens
- [MiniMax M2.7](https://infro.io/md/models/minimax/minimax-m2.7.md) `minimax/minimax-m2.7` — $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.06 per 1M tokens
- [MiniMax M2.5](https://infro.io/md/models/minimax/minimax-m2.5.md) `minimax/minimax-m2.5` — $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.03 per 1M tokens
- [MiniMax M2.7 Highspeed](https://infro.io/md/models/minimax/minimax-m2.7-highspeed.md) `minimax/minimax-m2.7-highspeed` — $0.60 per 1M input tokens and $2.40 per 1M output tokens, with cached input at $0.06 per 1M tokens
- [MiniMax Image-01](https://infro.io/md/models/minimax/image-01.md) `minimax/image-01` — $0.0035 per image
- [MiniMax H3](https://infro.io/md/models/minimax/hailuo-03.md) `minimax/hailuo-03` — $0.08 per second of video
- [MiniMax H3 Max](https://infro.io/md/models/minimax/h3-max.md) `minimax/h3-max` — $0.08 per second of video
- [MiniMax H3 Max Turbo](https://infro.io/md/models/minimax/h3-max-turbo.md) `minimax/h3-max-turbo` — $0.04 per second of video
- [Hailuo 2.3](https://infro.io/md/models/minimax/hailuo-2.3.md) `minimax/hailuo-2.3` — $0.082 per second of video
- [Speech 2.6](https://infro.io/md/models/minimax/speech-2.6.md) `minimax/speech-2.6` — $35 per 1M characters
- [Speech 2.8 HD](https://infro.io/md/models/minimax/speech-2.8-hd.md) `minimax/speech-2.8-hd` — $100 per 1M characters
- [Speech 2.8 Turbo](https://infro.io/md/models/minimax/speech-2.8-turbo.md) `minimax/speech-2.8-turbo` — $60 per 1M characters
- [MiniMax ASR](https://infro.io/md/models/minimax/asr-1.0.md) `minimax/asr-1.0` — $0.38 per audio hour
- [MiniMax Music 2.5](https://infro.io/md/models/minimax/music-2.5.md) `minimax/music-2.5` — $0.15 per track
- [MiniMax Music 1.5](https://infro.io/md/models/minimax/music-1.5.md) `minimax/music-1.5` — $0.03 per track

## Mistral

All Mistral models: https://infro.io/md/models/mistral.md

- [Mistral Large 3](https://infro.io/md/models/mistral/mistral-large-3.md) `mistral/mistral-large-3` — $0.50 per 1M input tokens and $1.50 per 1M output tokens
- [Mistral Medium 3.5](https://infro.io/md/models/mistral/mistral-medium-3.5.md) `mistral/mistral-medium-3.5` — $1.50 per 1M input tokens and $7.50 per 1M output tokens
- [Mistral Small 4](https://infro.io/md/models/mistral/mistral-small-4.md) `mistral/mistral-small-4` — $0.15 per 1M input tokens and $0.60 per 1M output tokens
- [Ministral 3 14B](https://infro.io/md/models/mistral/ministral-3-14b.md) `mistral/ministral-3-14b` — $0.20 per 1M input tokens and $0.20 per 1M output tokens
- [Ministral 3 8B](https://infro.io/md/models/mistral/ministral-3-8b.md) `mistral/ministral-3-8b` — $0.15 per 1M input tokens and $0.15 per 1M output tokens
- [Ministral 3 3B](https://infro.io/md/models/mistral/ministral-3-3b.md) `mistral/ministral-3-3b` — $0.10 per 1M input tokens and $0.10 per 1M output tokens
- [Codestral](https://infro.io/md/models/mistral/codestral.md) `mistral/codestral` — $0.30 per 1M input tokens and $0.90 per 1M output tokens
- [Voxtral Small](https://infro.io/md/models/mistral/voxtral-small.md) `mistral/voxtral-small` — $0.10 per 1M input tokens and $0.40 per 1M output tokens
- [Voxtral Mini Transcribe 2](https://infro.io/md/models/mistral/voxtral-mini-transcribe-2.md) `mistral/voxtral-mini-transcribe-2` — $0.18 per audio hour
- [Voxtral TTS](https://infro.io/md/models/mistral/voxtral-tts.md) `mistral/voxtral-tts` — $16 per 1M characters

## MMAudio

All MMAudio models: https://infro.io/md/models/mmaudio.md

- [MMAudio v2](https://infro.io/md/models/mmaudio/mmaudio-v2.md) `mmaudio/mmaudio-v2` — $0.0010 per second of video

## Moonshot

All Moonshot models: https://infro.io/md/models/moonshot.md

- [Kimi K3](https://infro.io/md/models/moonshot/kimi-k3.md) `moonshot/kimi-k3` — $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens
- [Kimi K2.7 Code](https://infro.io/md/models/moonshot/kimi-k2.7-code.md) `moonshot/kimi-k2.7-code` — $0.95 per 1M input tokens and $4.00 per 1M output tokens, with cached input at $0.19 per 1M tokens
- [Kimi K2.6](https://infro.io/md/models/moonshot/kimi-k2.6.md) `moonshot/kimi-k2.6` — $0.95 per 1M input tokens and $4.00 per 1M output tokens, with cached input at $0.16 per 1M tokens
- [Kimi K2.7 Code Highspeed](https://infro.io/md/models/moonshot/kimi-k2.7-code-highspeed.md) `moonshot/kimi-k2.7-code-highspeed` — $1.90 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.38 per 1M tokens

## NVIDIA

All NVIDIA models: https://infro.io/md/models/nvidia.md

- [Nemotron 3.5 Lightning 30B A3B](https://infro.io/md/models/nvidia/nemotron-3.5-lightning-30b-a3b.md) `nvidia/nemotron-3.5-lightning-30b-a3b` — $0.05 per 1M input tokens and $0.20 per 1M output tokens, with cached input at $0.01 per 1M tokens
- [Nemotron 3 Ultra](https://infro.io/md/models/nvidia/nemotron-3-ultra.md) `nvidia/nemotron-3-ultra` — $0.60 per 1M input tokens and $2.40 per 1M output tokens, with cached input at $0.12 per 1M tokens
- [Parakeet TDT 0.6B v3](https://infro.io/md/models/nvidia/parakeet-tdt-0.6b-v3.md) `nvidia/parakeet-tdt-0.6b-v3` — $0.09 per audio hour
- [Nemotron 3.5 ASR](https://infro.io/md/models/nvidia/nemotron-3.5-asr.md) `nvidia/nemotron-3.5-asr` — $0.27 per audio hour

## OpenAI

All OpenAI models: https://infro.io/md/models/openai.md

- [GPT-6 Astra](https://infro.io/md/models/openai/gpt-6-astra.md) `openai/gpt-6-astra` — $10 per 1M input tokens and $50 per 1M output tokens, with cached input at $1.00 per 1M tokens
- [GPT-6 Sol](https://infro.io/md/models/openai/gpt-6-sol.md) `openai/gpt-6-sol` — $2.00 per 1M input tokens and $10 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [GPT-6 Luna](https://infro.io/md/models/openai/gpt-6-luna.md) `openai/gpt-6-luna` — $0.10 per 1M input tokens and $0.50 per 1M output tokens, with cached input at $0.01 per 1M tokens
- [GPT-5.6 Sol](https://infro.io/md/models/openai/gpt-5.6-sol.md) `openai/gpt-5.6-sol` — $4.00 per 1M input tokens and $20 per 1M output tokens, with cached input at $0.40 per 1M tokens
- [GPT-5.6 Terra](https://infro.io/md/models/openai/gpt-5.6-terra.md) `openai/gpt-5.6-terra` — $2.00 per 1M input tokens and $12 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [GPT-5.6 Luna](https://infro.io/md/models/openai/gpt-5.6-luna.md) `openai/gpt-5.6-luna` — $0.20 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.02 per 1M tokens
- [gpt-oss-120b](https://infro.io/md/models/openai/gpt-oss-120b.md) `openai/gpt-oss-120b` — $0.15 per 1M input tokens and $0.60 per 1M output tokens
- [GPT-6 Luna (Decisions)](https://infro.io/md/models/openai/gpt-6-luna-decisions.md) `openai/gpt-6-luna-decisions` — $0.10 per 1M input tokens and output tokens free, with cached input at $0.01 per 1M tokens
- [GPT-6.1 Sol](https://infro.io/md/models/openai/gpt-6.1-sol.md) `openai/gpt-6.1-sol` — $2.00 per 1M input tokens and $10 per 1M output tokens, with cached input at $0.10 per 1M tokens
- [GPT-5.5](https://infro.io/md/models/openai/gpt-5.5.md) `openai/gpt-5.5` — $5.00 per 1M input tokens and $30 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [GPT-5.5 Pro](https://infro.io/md/models/openai/gpt-5.5-pro.md) `openai/gpt-5.5-pro` — $30 per 1M input tokens and $180 per 1M output tokens
- [GPT-5.4](https://infro.io/md/models/openai/gpt-5.4.md) `openai/gpt-5.4` — $2.50 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.25 per 1M tokens
- [GPT-5.4 mini](https://infro.io/md/models/openai/gpt-5.4-mini.md) `openai/gpt-5.4-mini` — $0.75 per 1M input tokens and $4.50 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [GPT-5.4 nano](https://infro.io/md/models/openai/gpt-5.4-nano.md) `openai/gpt-5.4-nano` — $0.20 per 1M input tokens and $1.25 per 1M output tokens, with cached input at $0.02 per 1M tokens
- [GPT-5.4 Pro](https://infro.io/md/models/openai/gpt-5.4-pro.md) `openai/gpt-5.4-pro` — $30 per 1M input tokens and $180 per 1M output tokens
- [GPT-5.3 Codex](https://infro.io/md/models/openai/gpt-5.3-codex.md) `openai/gpt-5.3-codex` — $1.75 per 1M input tokens and $14 per 1M output tokens, with cached input at $0.175 per 1M tokens
- [o3](https://infro.io/md/models/openai/o3.md) `openai/o3` — $2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [o3-pro](https://infro.io/md/models/openai/o3-pro.md) `openai/o3-pro` — $20 per 1M input tokens and $80 per 1M output tokens
- [GPT-4.1](https://infro.io/md/models/openai/gpt-4.1.md) `openai/gpt-4.1` — $2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [GPT-4.1 mini](https://infro.io/md/models/openai/gpt-4.1-mini.md) `openai/gpt-4.1-mini` — $0.40 per 1M input tokens and $1.60 per 1M output tokens, with cached input at $0.10 per 1M tokens
- [GPT-4o](https://infro.io/md/models/openai/gpt-4o.md) `openai/gpt-4o` — $2.50 per 1M input tokens and $10 per 1M output tokens, with cached input at $1.25 per 1M tokens
- [GPT-4o mini](https://infro.io/md/models/openai/gpt-4o-mini.md) `openai/gpt-4o-mini` — $0.15 per 1M input tokens and $0.60 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [gpt-oss-20b](https://infro.io/md/models/openai/gpt-oss-20b.md) `openai/gpt-oss-20b` — $0.075 per 1M input tokens and $0.30 per 1M output tokens
- [GPT Image 2](https://infro.io/md/models/openai/gpt-image-2.md) `openai/gpt-image-2` — $0.053 per image
- [GPT Image 2.5 Sunburst](https://infro.io/md/models/openai/gpt-image-2.5-sunburst.md) `openai/gpt-image-2.5-sunburst` — $0.013 per image
- [GPT Image 2.5 Flare](https://infro.io/md/models/openai/gpt-image-2.5-flare.md) `openai/gpt-image-2.5-flare` — $0.013 per image
- [GPT Image 1.5](https://infro.io/md/models/openai/gpt-image-1.5.md) `openai/gpt-image-1.5` — $0.034 per image
- [GPT Image 1 Mini](https://infro.io/md/models/openai/gpt-image-1-mini.md) `openai/gpt-image-1-mini` — $0.011 per image
- [GPT Image 1](https://infro.io/md/models/openai/gpt-image-1.md) `openai/gpt-image-1` — $0.042 per image
- [Whisper v3 Turbo](https://infro.io/md/models/openai/whisper-v3-turbo.md) `openai/whisper-v3-turbo` — $0.04 per audio hour
- [TTS-1](https://infro.io/md/models/openai/tts-1.md) `openai/tts-1` — $15 per 1M characters
- [TTS-1 HD](https://infro.io/md/models/openai/tts-1-hd.md) `openai/tts-1-hd` — $30 per 1M characters
- [GPT-Transcribe](https://infro.io/md/models/openai/gpt-transcribe.md) `openai/gpt-transcribe` — $0.27 per audio hour
- [Whisper Large v3](https://infro.io/md/models/openai/whisper-large-v3.md) `openai/whisper-large-v3` — $0.09 per audio hour
- [Whisper](https://infro.io/md/models/openai/whisper-1.md) `openai/whisper-1` — $0.36 per audio hour
- [GPT-4o Transcribe](https://infro.io/md/models/openai/gpt-4o-transcribe.md) `openai/gpt-4o-transcribe` — $0.36 per audio hour
- [GPT-4o mini Transcribe](https://infro.io/md/models/openai/gpt-4o-mini-transcribe.md) `openai/gpt-4o-mini-transcribe` — $0.18 per audio hour

## Perplexity

All Perplexity models: https://infro.io/md/models/perplexity.md

- [Sonar Pro](https://infro.io/md/models/perplexity/sonar-pro.md) `perplexity/sonar-pro` — $3.00 per 1M input tokens and $15 per 1M output tokens
- [Sonar](https://infro.io/md/models/perplexity/sonar.md) `perplexity/sonar` — $1.00 per 1M input tokens and $1.00 per 1M output tokens
- [pplx-decider v1.1 27B](https://infro.io/md/models/perplexity/pplx-decider-v1.1-27b.md) `perplexity/pplx-decider-v1.1-27b` — $0.02 per 1M input tokens and output tokens free
- [Sonar Reasoning Pro](https://infro.io/md/models/perplexity/sonar-reasoning-pro.md) `perplexity/sonar-reasoning-pro` — $2.00 per 1M input tokens and $8.00 per 1M output tokens
- [Sonar Deep Research](https://infro.io/md/models/perplexity/sonar-deep-research.md) `perplexity/sonar-deep-research` — $2.00 per 1M input tokens and $8.00 per 1M output tokens

## PixVerse

All PixVerse models: https://infro.io/md/models/pixverse.md

- [PixVerse V6](https://infro.io/md/models/pixverse/pixverse-v6.md) `pixverse/pixverse-v6` — $0.045 per second of video
- [PixVerse C1](https://infro.io/md/models/pixverse/pixverse-c1.md) `pixverse/pixverse-c1` — $0.05 per second of video

## Qwen

All Qwen models: https://infro.io/md/models/qwen.md

- [Qwen3-ASR 1.7B](https://infro.io/md/models/qwen/qwen3-asr-1.7b.md) `qwen/qwen3-asr-1.7b` — $0.027 per audio hour
- [Qwen3-ASR 0.6B](https://infro.io/md/models/qwen/qwen3-asr-0.6b.md) `qwen/qwen3-asr-0.6b` — $0.012 per audio hour

## Real-ESRGAN

All Real-ESRGAN models: https://infro.io/md/models/xinntao.md

- [Real-ESRGAN](https://infro.io/md/models/xinntao/real-esrgan.md) `xinntao/real-esrgan` — $0.0020 per image

## Recraft

All Recraft models: https://infro.io/md/models/recraft.md

- [Recraft V3](https://infro.io/md/models/recraft/recraft-v3.md) `recraft/recraft-v3` — $0.04 per image
- [Recraft V4](https://infro.io/md/models/recraft/recraft-v4.md) `recraft/recraft-v4` — $0.04 per image
- [Recraft V4 Pro](https://infro.io/md/models/recraft/recraft-v4-pro.md) `recraft/recraft-v4-pro` — $0.25 per image
- [Recraft V4.1](https://infro.io/md/models/recraft/recraft-v4.1.md) `recraft/recraft-v4.1` — $0.035 per image
- [Recraft V4.1 Pro](https://infro.io/md/models/recraft/recraft-v4.1-pro.md) `recraft/recraft-v4.1-pro` — $0.21 per image
- [Recraft V4.1 Flash](https://infro.io/md/models/recraft/recraft-v4.1-flash.md) `recraft/recraft-v4.1-flash` — $0.0070 per image
- [Recraft Crisp Upscale](https://infro.io/md/models/recraft/crisp-upscale.md) `recraft/crisp-upscale` — $0.0040 per image

## Runway

All Runway models: https://infro.io/md/models/runway.md

- [Runway Gen-4 Image](https://infro.io/md/models/runway/gen-4-image.md) `runway/gen-4-image` — $0.05 per image
- [Runway Gen-4 Image Turbo](https://infro.io/md/models/runway/gen-4-image-turbo.md) `runway/gen-4-image-turbo` — $0.02 per image
- [Runway Gen-4.5](https://infro.io/md/models/runway/gen-4.5.md) `runway/gen-4.5` — $0.12 per second of video
- [Runway Gen-4 Turbo](https://infro.io/md/models/runway/gen-4-turbo.md) `runway/gen-4-turbo` — $0.05 per second of video

## Sesame

All Sesame models: https://infro.io/md/models/sesame.md

- [CSM 1B](https://infro.io/md/models/sesame/csm-1b.md) `sesame/csm-1b` — $7.00 per 1M characters

## Stability AI

All Stability AI models: https://infro.io/md/models/stability.md

- [Stable Audio 2.5](https://infro.io/md/models/stability/stable-audio-2.5.md) `stability/stable-audio-2.5` — $0.20 per track

## Suno

All Suno models: https://infro.io/md/models/suno.md

- [Suno V5.5](https://infro.io/md/models/suno/suno-v5.5.md) `suno/suno-v5.5` — $0.10 per track

## Sync

All Sync models: https://infro.io/md/models/sync.md

- [Lipsync 2](https://infro.io/md/models/sync/lipsync-2.md) `sync/lipsync-2` — $0.05 per second of video
- [Lipsync 2 Pro](https://infro.io/md/models/sync/lipsync-2-pro.md) `sync/lipsync-2-pro` — $0.083 per second of video
- [Sync 3](https://infro.io/md/models/sync/sync-3.md) `sync/sync-3` — $0.134 per second of video
- [React 1](https://infro.io/md/models/sync/react-1.md) `sync/react-1` — $0.167 per second of video

## Thinking Machines

All Thinking Machines models: https://infro.io/md/models/thinkingmachines.md

- [Inkling](https://infro.io/md/models/thinkingmachines/inkling.md) `thinkingmachines/inkling` — $1.00 per 1M input tokens and $4.05 per 1M output tokens, with cached input at $0.17 per 1M tokens

## Topaz Labs

All Topaz Labs models: https://infro.io/md/models/topaz.md

- [Topaz Image Upscale](https://infro.io/md/models/topaz/image-upscale.md) `topaz/image-upscale` — $0.08 per image
- [Topaz Video Upscale](https://infro.io/md/models/topaz/video-upscale.md) `topaz/video-upscale` — $0.01 per second of video

## TypeSafe

All TypeSafe models: https://infro.io/md/models/typesafe.md

- [Jev 1.13](https://infro.io/md/models/typesafe/jev-1.13.md) `typesafe/jev-1.13` — $0.042 per 1M input tokens and output tokens free

## Upstage

All Upstage models: https://infro.io/md/models/upstage.md

- [Solar Decide](https://infro.io/md/models/upstage/solar-decide.md) `upstage/solar-decide` — $0.05 per 1M input tokens and output tokens free
- [Solar Decide Flash](https://infro.io/md/models/upstage/solar-decide-flash.md) `upstage/solar-decide-flash` — $0.05 per 1M input tokens and output tokens free

## xAI

All xAI models: https://infro.io/md/models/xai.md

- [Grok 4.7](https://infro.io/md/models/xai/grok-4.7.md) `xai/grok-4.7` — $2.00 per 1M input tokens and $6.00 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Grok 4.6](https://infro.io/md/models/xai/grok-4.6.md) `xai/grok-4.6` — $2.00 per 1M input tokens and $6.00 per 1M output tokens, with cached input at $0.50 per 1M tokens
- [Grok 4.5](https://infro.io/md/models/xai/grok-4.5.md) `xai/grok-4.5` — $2.00 per 1M input tokens and $6.00 per 1M output tokens, with cached input at $0.30 per 1M tokens
- [Grok 4.3](https://infro.io/md/models/xai/grok-4.3.md) `xai/grok-4.3` — $1.25 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Grok 4.20 Reasoning](https://infro.io/md/models/xai/grok-4.20-0309-reasoning.md) `xai/grok-4.20-0309-reasoning` — $1.25 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Grok 4.20 Non-Reasoning](https://infro.io/md/models/xai/grok-4.20-0309-non-reasoning.md) `xai/grok-4.20-0309-non-reasoning` — $1.25 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Grok 4.20 Multi-Agent (Beta)](https://infro.io/md/models/xai/grok-4.20-multi-agent-0309.md) `xai/grok-4.20-multi-agent-0309` — $1.25 per 1M input tokens and $2.50 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Grok Build 0.1](https://infro.io/md/models/xai/grok-build-0.1.md) `xai/grok-build-0.1` — $1.00 per 1M input tokens and $2.00 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [Grok Imagine 2.0](https://infro.io/md/models/xai/grok-imagine-image-2.md) `xai/grok-imagine-image-2` — $0.04 per image
- [Grok Imagine Image](https://infro.io/md/models/xai/grok-imagine-image.md) `xai/grok-imagine-image` — $0.02 per image
- [Grok Imagine Image Quality](https://infro.io/md/models/xai/grok-imagine-image-quality.md) `xai/grok-imagine-image-quality` — $0.05 per image
- [Grok Imagine 1.5](https://infro.io/md/models/xai/grok-imagine-video-1.5.md) `xai/grok-imagine-video-1.5` — $0.08 per second of video
- [Grok Imagine Video](https://infro.io/md/models/xai/grok-imagine-video.md) `xai/grok-imagine-video` — $0.05 per second of video
- [Grok Imagine Video 1.5 Lite](https://infro.io/md/models/xai/grok-imagine-video-1.5-lite.md) `xai/grok-imagine-video-1.5-lite` — $0.02 per second of video
- [Grok Voice TTS](https://infro.io/md/models/xai/grok-voice-tts-1.0.md) `xai/grok-voice-tts-1.0` — $15 per 1M characters
- [Grok Speech to Text](https://infro.io/md/models/xai/grok-stt-1.0.md) `xai/grok-stt-1.0` — $0.10 per audio hour

## Z.ai

All Z.ai models: https://infro.io/md/models/zai.md

- [GLM-5.3](https://infro.io/md/models/zai/glm-5.3.md) `zai/glm-5.3` — $1.40 per 1M input tokens and $4.40 per 1M output tokens, with cached input at $0.26 per 1M tokens
- [GLM-5.3 Flash](https://infro.io/md/models/zai/glm-5.3-flash.md) `zai/glm-5.3-flash` — $0.15 per 1M input tokens and $0.50 per 1M output tokens, with cached input at $0.03 per 1M tokens
- [GLM-5.2](https://infro.io/md/models/zai/glm-5.2.md) `zai/glm-5.2` — $1.40 per 1M input tokens and $4.40 per 1M output tokens, with cached input at $0.26 per 1M tokens
- [GLM-5.3 FlashX](https://infro.io/md/models/zai/glm-5.3-flashx.md) `zai/glm-5.3-flashx` — $0.37 per 1M input tokens and $1.25 per 1M output tokens, with cached input at $0.075 per 1M tokens
- [GLM-5.1](https://infro.io/md/models/zai/glm-5.1.md) `zai/glm-5.1` — $1.40 per 1M input tokens and $4.40 per 1M output tokens, with cached input at $0.26 per 1M tokens
- [GLM-5](https://infro.io/md/models/zai/glm-5.md) `zai/glm-5` — $1.00 per 1M input tokens and $3.20 per 1M output tokens, with cached input at $0.20 per 1M tokens
- [GLM-4.7](https://infro.io/md/models/zai/glm-4.7.md) `zai/glm-4.7` — $0.60 per 1M input tokens and $2.20 per 1M output tokens, with cached input at $0.11 per 1M tokens
- [GLM-4.7 FlashX](https://infro.io/md/models/zai/glm-4.7-flashx.md) `zai/glm-4.7-flashx` — $0.07 per 1M input tokens and $0.40 per 1M output tokens, with cached input at $0.01 per 1M tokens
- [GLM-4.6](https://infro.io/md/models/zai/glm-4.6.md) `zai/glm-4.6` — $0.60 per 1M input tokens and $2.20 per 1M output tokens, with cached input at $0.11 per 1M tokens
- [GLM-4.5 Air](https://infro.io/md/models/zai/glm-4.5-air.md) `zai/glm-4.5-air` — $0.20 per 1M input tokens and $1.10 per 1M output tokens, with cached input at $0.03 per 1M tokens
- [GLM-4.6V](https://infro.io/md/models/zai/glm-4.6v.md) `zai/glm-4.6v` — $0.30 per 1M input tokens and $0.90 per 1M output tokens, with cached input at $0.05 per 1M tokens
- [GLM-4.6V FlashX](https://infro.io/md/models/zai/glm-4.6v-flashx.md) `zai/glm-4.6v-flashx` — $0.04 per 1M input tokens and $0.40 per 1M output tokens, with cached input at $0.0040 per 1M tokens
- [GLM-Image](https://infro.io/md/models/zai/glm-image.md) `zai/glm-image` — $0.015 per image
- [CogView-4](https://infro.io/md/models/zai/cogview-4.md) `zai/cogview-4` — $0.01 per image
- [GLM-ASR](https://infro.io/md/models/zai/glm-asr-2512.md) `zai/glm-asr-2512` — $0.144 per audio hour