AiPricingLabmodel pricing
List prices · May 2026

AI model pricing - all in one place.

Side-by-side, source-of-truth pricing for every model in the AiPricingLab catalog. Includes context-tier breakdowns (≤200k vs >200k), image quality tiers (1K / 2K / 4K), multimodal input/output rates, and prompt-caching multipliers.

90
models
10
providers
8
categories
Category
Provider
Showing 90 of 90 models

Language models

63

GPT-5.5

OpenAIgpt-5.5

OpenAI flagship reasoning model (≤272k context).

Input≤272K context$5 / 1M tok
Cached input≤272K context$0.5 / 1M tok
Output≤272K context$30 / 1M tok

GPT-5.5 Pro

OpenAIgpt-5.5-pro
Input≤272K context$30 / 1M tok
Output≤272K context$180 / 1M tok

GPT-5.4

OpenAIgpt-5.4
Input≤272K context$2.5 / 1M tok
Cached input≤272K context$0.25 / 1M tok
Output≤272K context$15 / 1M tok

GPT-5.4 mini

OpenAIgpt-5.4-mini
Input$0.75 / 1M tok
Cached input$0.075 / 1M tok
Output$4.5 / 1M tok

GPT-5.4 nano

OpenAIgpt-5.4-nano
Input$0.2 / 1M tok
Cached input$0.02 / 1M tok
Output$1.25 / 1M tok

GPT-5.4 Pro

OpenAIgpt-5.4-pro
Input≤272K context$30 / 1M tok
Output≤272K context$180 / 1M tok

GPT-5.2

OpenAIgpt-5.2
Input$1.75 / 1M tok
Cached input$0.175 / 1M tok
Output$14 / 1M tok

GPT-5.2 Pro

OpenAIgpt-5.2-pro
Input$21 / 1M tok
Output$168 / 1M tok

GPT-5.1

OpenAIgpt-5.1
Input$1.25 / 1M tok
Cached input$0.125 / 1M tok
Output$10 / 1M tok

GPT-5

OpenAIgpt-5
Input$1.25 / 1M tok
Cached input$0.125 / 1M tok
Output$10 / 1M tok

GPT-5 mini

OpenAIgpt-5-mini
Input$0.25 / 1M tok
Cached input$0.025 / 1M tok
Output$2 / 1M tok

GPT-5 nano

OpenAIgpt-5-nano
Input$0.05 / 1M tok
Cached input$0.005 / 1M tok
Output$0.4 / 1M tok

GPT-5 Pro

OpenAIgpt-5-pro
Input$15 / 1M tok
Output$120 / 1M tok

GPT-4.1

OpenAIgpt-4.1
Input$2 / 1M tok
Cached input$0.5 / 1M tok
Output$8 / 1M tok

GPT-4.1 mini

OpenAIgpt-4.1-mini
Input$0.4 / 1M tok
Cached input$0.1 / 1M tok
Output$1.6 / 1M tok

GPT-4.1 nano

OpenAIgpt-4.1-nano
Input$0.1 / 1M tok
Cached input$0.025 / 1M tok
Output$0.4 / 1M tok

GPT-4o

OpenAIgpt-4o
intext, image, audioouttext
Input$2.5 / 1M tok
Cached input$1.25 / 1M tok
Output$10 / 1M tok

GPT-4o mini

OpenAIgpt-4o-mini
Input$0.15 / 1M tok
Cached input$0.075 / 1M tok
Output$0.6 / 1M tok

o1

OpenAIo1
Input$15 / 1M tok
Cached input$7.5 / 1M tok
Output$60 / 1M tok

o1-pro

OpenAIo1-pro
Input$150 / 1M tok
Output$600 / 1M tok

o3

OpenAIo3
Input$2 / 1M tok
Cached input$0.5 / 1M tok
Output$8 / 1M tok

o3-pro

OpenAIo3-pro
Input$20 / 1M tok
Output$80 / 1M tok

o3-mini

OpenAIo3-mini
Input$1.1 / 1M tok
Cached input$0.55 / 1M tok
Output$4.4 / 1M tok

o4-mini

OpenAIo4-mini
Input$1.1 / 1M tok
Cached input$0.275 / 1M tok
Output$4.4 / 1M tok

GPT-4o (2024-05-13)

deprecated
OpenAIgpt-4o-2024-05-13
Input$5 / 1M tok
Output$15 / 1M tok

o1-mini

OpenAIo1-mini
Input$1.1 / 1M tok
Cached input$0.55 / 1M tok
Output$4.4 / 1M tok

o3-deep-research

OpenAIo3-deep-research
Input$10 / 1M tok
Cached input$2.5 / 1M tok
Output$40 / 1M tok

o4-mini-deep-research

OpenAIo4-mini-deep-research
Input$2 / 1M tok
Cached input$0.5 / 1M tok
Output$8 / 1M tok

computer-use-preview

preview
OpenAIcomputer-use-preview
Input$3 / 1M tok
Output$12 / 1M tok

GPT-4 Turbo (2024-04-09)

deprecated
OpenAIgpt-4-turbo-2024-04-09
Input$10 / 1M tok
Output$30 / 1M tok

GPT-4 0125 Preview

deprecated
OpenAIgpt-4-0125-preview
Input$10 / 1M tok
Output$30 / 1M tok

GPT-4 1106 Preview

deprecated
OpenAIgpt-4-1106-preview
Input$10 / 1M tok
Output$30 / 1M tok

GPT-4 1106 Vision Preview

deprecated
OpenAIgpt-4-1106-vision-preview
Input$10 / 1M tok
Output$30 / 1M tok

GPT-4 0613

deprecated
OpenAIgpt-4-0613
Input$30 / 1M tok
Output$60 / 1M tok

GPT-4 0314

deprecated
OpenAIgpt-4-0314
Input$30 / 1M tok
Output$60 / 1M tok

GPT-4 32k

deprecated
OpenAIgpt-4-32k
Input$60 / 1M tok
Output$120 / 1M tok

GPT-3.5 Turbo

deprecated
OpenAIgpt-3.5-turbo
Input$0.5 / 1M tok
Output$1.5 / 1M tok

GPT-3.5 Turbo 0125

deprecated
OpenAIgpt-3.5-turbo-0125
Input$0.5 / 1M tok
Output$1.5 / 1M tok

GPT-3.5 Turbo 1106

deprecated
OpenAIgpt-3.5-turbo-1106
Input$1 / 1M tok
Output$2 / 1M tok

GPT-3.5 Turbo 0613

deprecated
OpenAIgpt-3.5-turbo-0613
Input$1.5 / 1M tok
Output$2 / 1M tok

GPT-3.5 0301

deprecated
OpenAIgpt-3.5-0301
Input$1.5 / 1M tok
Output$2 / 1M tok

GPT-3.5 Turbo Instruct

deprecated
OpenAIgpt-3.5-turbo-instruct
Input$1.5 / 1M tok
Output$2 / 1M tok

GPT-3.5 Turbo 16k 0613

deprecated
OpenAIgpt-3.5-turbo-16k-0613
Input$3 / 1M tok
Output$4 / 1M tok

davinci-002

deprecated
OpenAIdavinci-002
Input$2 / 1M tok
Output$2 / 1M tok

babbage-002

deprecated
OpenAIbabbage-002
Input$0.4 / 1M tok
Output$0.4 / 1M tok

Claude Opus 4.7

Anthropicclaude-opus-4-7

New tokenizer — may use up to 35% more tokens than 4.6.

Input$5 / 1M tok
Cache write (5 min)$6.25 / 1M tok
Cache write (1 hour)$10 / 1M tok
Cache hit / refresh$0.5 / 1M tok
Output$25 / 1M tok

Claude Opus 4.6

Anthropicclaude-opus-4-6
Input$5 / 1M tok
Cache write (5 min)$6.25 / 1M tok
Cache write (1 hour)$10 / 1M tok
Cache hit / refresh$0.5 / 1M tok
Output$25 / 1M tok

Claude Opus 4.5

Anthropicclaude-opus-4-5
Input$5 / 1M tok
Cache write (5 min)$6.25 / 1M tok
Cache write (1 hour)$10 / 1M tok
Cache hit / refresh$0.5 / 1M tok
Output$25 / 1M tok

Claude Opus 4.1

Anthropicclaude-opus-4-1
Input$15 / 1M tok
Cache write (5 min)$18.75 / 1M tok
Cache write (1 hour)$30 / 1M tok
Cache hit / refresh$1.5 / 1M tok
Output$75 / 1M tok

Claude Opus 4

Anthropicclaude-opus-4
Input$15 / 1M tok
Cache write (5 min)$18.75 / 1M tok
Cache write (1 hour)$30 / 1M tok
Cache hit / refresh$1.5 / 1M tok
Output$75 / 1M tok

Claude Sonnet 4.6

Anthropicclaude-sonnet-4-6
Input$3 / 1M tok
Cache write (5 min)$3.75 / 1M tok
Cache write (1 hour)$6 / 1M tok
Cache hit / refresh$0.3 / 1M tok
Output$15 / 1M tok

Claude Sonnet 4.5

Anthropicclaude-sonnet-4-5
Input$3 / 1M tok
Cache write (5 min)$3.75 / 1M tok
Cache write (1 hour)$6 / 1M tok
Cache hit / refresh$0.3 / 1M tok
Output$15 / 1M tok

Claude Sonnet 4

Anthropicclaude-sonnet-4
Input$3 / 1M tok
Cache write (5 min)$3.75 / 1M tok
Cache write (1 hour)$6 / 1M tok
Cache hit / refresh$0.3 / 1M tok
Output$15 / 1M tok

Claude Sonnet 3.7

deprecated
Anthropicclaude-sonnet-3-7
Input$3 / 1M tok
Cache write (5 min)$3.75 / 1M tok
Cache write (1 hour)$6 / 1M tok
Cache hit / refresh$0.3 / 1M tok
Output$15 / 1M tok

Claude Haiku 4.5

Anthropicclaude-haiku-4-5
Input$1 / 1M tok
Cache write (5 min)$1.25 / 1M tok
Cache write (1 hour)$2 / 1M tok
Cache hit / refresh$0.1 / 1M tok
Output$5 / 1M tok

Claude Haiku 3.5

Anthropicclaude-haiku-3-5
Input$0.8 / 1M tok
Cache write (5 min)$1 / 1M tok
Cache write (1 hour)$1.6 / 1M tok
Cache hit / refresh$0.08 / 1M tok
Output$4 / 1M tok

Claude Opus 3

deprecated
Anthropicclaude-opus-3
Input$15 / 1M tok
Cache write (5 min)$18.75 / 1M tok
Cache write (1 hour)$30 / 1M tok
Cache hit / refresh$1.5 / 1M tok
Output$75 / 1M tok

Claude Haiku 3

deprecated
Anthropicclaude-haiku-3
Input$0.25 / 1M tok
Cache write (5 min)$0.3 / 1M tok
Cache write (1 hour)$0.5 / 1M tok
Cache hit / refresh$0.03 / 1M tok
Output$1.25 / 1M tok

Gemini 3.1 Pro

preview
Googlegemini-3-1-pro

Latest performance, intelligence, and usability improvements for multimodal understanding, agentic capabilities, and vibe-coding.

intext, image, video, audioouttext
Input≤200k tokens$2 / 1M tok
>200k tokens$4 / 1M tok
Output≤200k tokens$12 / 1M tok
>200k tokens$18 / 1M tok
Context cache≤200k tokens$0.2 / 1M tok
>200k tokens$0.4 / 1M tok
Cache storageper hour$4.5 / 1M tok / hour
Grounding (Search)after 5,000 free/month$14 / 1k searches

Gemini 3.1 Flash-Lite

preview
Googlegemini-3-1-flash-lite

Most cost-efficient model, optimized for high-volume agentic tasks, translation, and simple data processing.

intext, image, video, audioouttext
InputText / image / video$0.25 / 1M tok
Audio$0.5 / 1M tok
Output$1.5 / 1M tok
Context cacheText / image / video$0.025 / 1M tok
Audio$0.05 / 1M tok
Cache storageper hour$1 / 1M tok / hour
Grounding (Search)after 5,000 free/month$14 / 1k searches

Gemini 2.5 Pro

Googlegemini-2-5-pro
InputText / image / video$1.25 / 1M tok
Output$10 / 1M tok

Gemini 3 Flash

preview
Googlegemini-3-flash

Most intelligent model built for speed, combining frontier intelligence with superior search and grounding.

intext, image, video, audioouttext
InputText / image / video$0.5 / 1M tok
Audio$1 / 1M tok
Output$3 / 1M tok
Context cacheText / image / video$0.05 / 1M tok
Audio$0.1 / 1M tok
Cache storageper hour$1 / 1M tok / hour
Grounding (Search)after 5,000 free/month$14 / 1k searches

Llama 3.3 70B

Metallama-3-3-70b

Open weights — pricing varies by host (Together AI, Replicate, Bedrock, etc.).

Input-

Image generation

9

Gemini 3.1 Flash Image

preview
Googlegemini-3-1-flash-image-preview

Designed for speed and efficiency. High-throughput image generation.

intext, imageouttext, image
InputText / image$0.5 / 1M tok
Image output0.5K (512px)$0.045 / image
1K (1024×1024)$0.067 / image
2K (2048×2048)$0.101 / image
4K (4096×4096)$0.151 / image
Grounding (Search)after 5,000 free/month$14 / 1k searches
0.5K image consumes 747 tokens; 1K = 1120; 2K = 1680; 4K = 2520. Per-image price is the token rate × token count.

Gemini 3 Pro Image

preview
Googlegemini-3-pro-image

Native image generation model, optimized for speed, flexibility, and contextual understanding. Text in/out priced like Gemini 3.1 Pro.

intext, imageouttext, image
InputImage (per image)$0.0011 / image
Image output1K–2K (1024–2048px)$0.134 / image
4K (4096×4096)$0.24 / image
Grounding (Search)after 5,000 free/month$14 / 1k searches
Image input is 560 tokens (~$0.0011 per image).
1K/2K output images consume 1,120 tokens; 4K consume 2,000 tokens.

Gemini 2.5 Flash Image

preview
Googlegemini-2-5-flash-image

Native image generation model, optimized for speed and contextual understanding. Text in/out priced like Gemini 2.5 Flash.

intext, imageouttext, image
Image output1K (1024×1024)$0.039 / image
Image output priced at $30 per 1M tokens; 1K image = 1,290 tokens.

Flux Schnell

Replicateflux-schnell
Image output$0.003 / image

Flux Pro

Replicateflux-pro
Image output$0.055 / image

Flux Dev

Replicateflux-dev
Image output$0.025 / image

Stable Diffusion XL

Replicatesdxl
Image output$0.0095 / image

DALL·E 3

OpenAIdalle-3
Image outputStandard 1024×1024$0.04 / image
Standard 1024×1792$0.08 / image
HD 1024×1024$0.08 / image
HD 1024×1792$0.12 / image

Ideogram v2

Ideogramideogram-v2
Image output$0.08 / image

Video generation

9

Runway Gen-3

Runwayrunway-gen3
Video output$0.05 / second

Kling 1.5

Klingkling-1-5
Video output$0.42 / second

Sora

OpenAIsora
Video output-

Veo 3.1 Standard

preview
Googleveo-3-1-generate-preview

Latest video generation model with audio. 4K supported.

intext, imageoutvideo, audio
Video output720p / 1080p with audio$0.4 / second
4K with audio$0.6 / second

Veo 3.1 Fast

preview
Googleveo-3-1-fast-generate-preview

Faster, cheaper variant of Veo 3.1 with audio.

Video output720p with audio$0.1 / second
1080p with audio$0.12 / second
4K with audio$0.3 / second

Veo 3.1 Lite

preview
Googleveo-3-1-lite-generate-preview

Lightest Veo 3.1 tier. 4K not supported.

Video output720p with audio$0.05 / second
1080p with audio$0.08 / second

Veo 3 Standard

Googleveo-3-0-generate-001

Stable video generation model with audio.

Video outputwith audio$0.4 / second

Veo 3 Fast

Googleveo-3-0-fast-generate-001

Faster, cheaper Veo 3 variant.

Video output720p with audio$0.1 / second
1080p with audio$0.12 / second
4K with audio$0.3 / second

Veo 2

Googleveo-2-0-generate-001

Previous-generation Veo video model.

Video output$0.35 / second

Audio generation

1

Suno v4

Sunosuno-v4
Audio output-

Text-to-speech

2

Gemini 3.1 Flash TTS

preview
Googlegemini-3-1-flash-tts

Text-to-speech model optimized for price-performant, low-latency, controllable speech generation.

intextoutaudio
InputText$1 / 1M tok
OutputAudio$20 / 1M tok
Audio tokens correspond to 25 tokens per second of audio.

ElevenLabs v2

ElevenLabselevenlabs-v2
TTS outputPer character$0.0003 / call

Realtime / live

1

Gemini 3.1 Flash Live

preview
Googlegemini-3-1-flash-live

Low-latency, audio-to-audio model optimized for real-time dialogue with acoustic nuance detection, numeric precision, and multimodal awareness.

intext, image, audio, videoouttext, audio
InputText$0.75 / 1M tok
Audio$3 / 1M tok
Audio (per minute)$0.005 / minute
Image / video$1 / 1M tok
Image / video (per minute)$0.002 / minute
OutputText$4.5 / 1M tok
Audio$12 / 1M tok
Audio (per minute)$0.018 / minute
Grounding (Search)after 5,000 free/month$14 / 1k searches

Embeddings

3

text-embedding-3-small

OpenAItext-embedding-3-small
Input$0.02 / 1M tok

text-embedding-3-large

OpenAItext-embedding-3-large
Input$0.13 / 1M tok

text-embedding-ada-002

OpenAItext-embedding-ada-002
Input$0.1 / 1M tok

Moderation

2

omni-moderation-latest

OpenAIomni-moderation-latest
InputFree

text-moderation-latest

deprecated
OpenAItext-moderation-latest
InputFree

All models (text fallback)

Language models

  • GPT-5.5 - OpenAI · Input (≤272K context): 5 · Cached input (≤272K context): 0.5 · Output (≤272K context): 30
  • GPT-5.5 Pro - OpenAI · Input (≤272K context): 30 · Output (≤272K context): 180
  • GPT-5.4 - OpenAI · Input (≤272K context): 2.5 · Cached input (≤272K context): 0.25 · Output (≤272K context): 15
  • GPT-5.4 mini - OpenAI · Input: 0.75 · Cached input: 0.075 · Output: 4.5
  • GPT-5.4 nano - OpenAI · Input: 0.2 · Cached input: 0.02 · Output: 1.25
  • GPT-5.4 Pro - OpenAI · Input (≤272K context): 30 · Output (≤272K context): 180
  • GPT-5.2 - OpenAI · Input: 1.75 · Cached input: 0.175 · Output: 14
  • GPT-5.2 Pro - OpenAI · Input: 21 · Output: 168
  • GPT-5.1 - OpenAI · Input: 1.25 · Cached input: 0.125 · Output: 10
  • GPT-5 - OpenAI · Input: 1.25 · Cached input: 0.125 · Output: 10
  • GPT-5 mini - OpenAI · Input: 0.25 · Cached input: 0.025 · Output: 2
  • GPT-5 nano - OpenAI · Input: 0.05 · Cached input: 0.005 · Output: 0.4
  • GPT-5 Pro - OpenAI · Input: 15 · Output: 120
  • GPT-4.1 - OpenAI · Input: 2 · Cached input: 0.5 · Output: 8
  • GPT-4.1 mini - OpenAI · Input: 0.4 · Cached input: 0.1 · Output: 1.6
  • GPT-4.1 nano - OpenAI · Input: 0.1 · Cached input: 0.025 · Output: 0.4
  • GPT-4o - OpenAI · Input: 2.5 · Cached input: 1.25 · Output: 10
  • GPT-4o mini - OpenAI · Input: 0.15 · Cached input: 0.075 · Output: 0.6
  • o1 - OpenAI · Input: 15 · Cached input: 7.5 · Output: 60
  • o1-pro - OpenAI · Input: 150 · Output: 600
  • o3 - OpenAI · Input: 2 · Cached input: 0.5 · Output: 8
  • o3-pro - OpenAI · Input: 20 · Output: 80
  • o3-mini - OpenAI · Input: 1.1 · Cached input: 0.55 · Output: 4.4
  • o4-mini - OpenAI · Input: 1.1 · Cached input: 0.275 · Output: 4.4
  • GPT-4o (2024-05-13) - OpenAI · Input: 5 · Output: 15
  • o1-mini - OpenAI · Input: 1.1 · Cached input: 0.55 · Output: 4.4
  • o3-deep-research - OpenAI · Input: 10 · Cached input: 2.5 · Output: 40
  • o4-mini-deep-research - OpenAI · Input: 2 · Cached input: 0.5 · Output: 8
  • computer-use-preview - OpenAI · Input: 3 · Output: 12
  • GPT-4 Turbo (2024-04-09) - OpenAI · Input: 10 · Output: 30
  • GPT-4 0125 Preview - OpenAI · Input: 10 · Output: 30
  • GPT-4 1106 Preview - OpenAI · Input: 10 · Output: 30
  • GPT-4 1106 Vision Preview - OpenAI · Input: 10 · Output: 30
  • GPT-4 0613 - OpenAI · Input: 30 · Output: 60
  • GPT-4 0314 - OpenAI · Input: 30 · Output: 60
  • GPT-4 32k - OpenAI · Input: 60 · Output: 120
  • GPT-3.5 Turbo - OpenAI · Input: 0.5 · Output: 1.5
  • GPT-3.5 Turbo 0125 - OpenAI · Input: 0.5 · Output: 1.5
  • GPT-3.5 Turbo 1106 - OpenAI · Input: 1 · Output: 2
  • GPT-3.5 Turbo 0613 - OpenAI · Input: 1.5 · Output: 2
  • GPT-3.5 0301 - OpenAI · Input: 1.5 · Output: 2
  • GPT-3.5 Turbo Instruct - OpenAI · Input: 1.5 · Output: 2
  • GPT-3.5 Turbo 16k 0613 - OpenAI · Input: 3 · Output: 4
  • davinci-002 - OpenAI · Input: 2 · Output: 2
  • babbage-002 - OpenAI · Input: 0.4 · Output: 0.4
  • Claude Opus 4.7 - Anthropic · Input: 5 · Cache write (5 min): 6.25 · Cache write (1 hour): 10 · Cache hit / refresh: 0.5 · Output: 25
  • Claude Opus 4.6 - Anthropic · Input: 5 · Cache write (5 min): 6.25 · Cache write (1 hour): 10 · Cache hit / refresh: 0.5 · Output: 25
  • Claude Opus 4.5 - Anthropic · Input: 5 · Cache write (5 min): 6.25 · Cache write (1 hour): 10 · Cache hit / refresh: 0.5 · Output: 25
  • Claude Opus 4.1 - Anthropic · Input: 15 · Cache write (5 min): 18.75 · Cache write (1 hour): 30 · Cache hit / refresh: 1.5 · Output: 75
  • Claude Opus 4 - Anthropic · Input: 15 · Cache write (5 min): 18.75 · Cache write (1 hour): 30 · Cache hit / refresh: 1.5 · Output: 75
  • Claude Sonnet 4.6 - Anthropic · Input: 3 · Cache write (5 min): 3.75 · Cache write (1 hour): 6 · Cache hit / refresh: 0.3 · Output: 15
  • Claude Sonnet 4.5 - Anthropic · Input: 3 · Cache write (5 min): 3.75 · Cache write (1 hour): 6 · Cache hit / refresh: 0.3 · Output: 15
  • Claude Sonnet 4 - Anthropic · Input: 3 · Cache write (5 min): 3.75 · Cache write (1 hour): 6 · Cache hit / refresh: 0.3 · Output: 15
  • Claude Sonnet 3.7 - Anthropic · Input: 3 · Cache write (5 min): 3.75 · Cache write (1 hour): 6 · Cache hit / refresh: 0.3 · Output: 15
  • Claude Haiku 4.5 - Anthropic · Input: 1 · Cache write (5 min): 1.25 · Cache write (1 hour): 2 · Cache hit / refresh: 0.1 · Output: 5
  • Claude Haiku 3.5 - Anthropic · Input: 0.8 · Cache write (5 min): 1 · Cache write (1 hour): 1.6 · Cache hit / refresh: 0.08 · Output: 4
  • Claude Opus 3 - Anthropic · Input: 15 · Cache write (5 min): 18.75 · Cache write (1 hour): 30 · Cache hit / refresh: 1.5 · Output: 75
  • Claude Haiku 3 - Anthropic · Input: 0.25 · Cache write (5 min): 0.3 · Cache write (1 hour): 0.5 · Cache hit / refresh: 0.03 · Output: 1.25
  • Gemini 3.1 Pro - Google · Input (≤200k tokens): 2 · Input (>200k tokens): 4 · Output (≤200k tokens): 12 · Output (>200k tokens): 18 · Context cache (≤200k tokens): 0.2 · Context cache (>200k tokens): 0.4 · Cache storage (per hour): 4.5 · Grounding (Search) (after 5,000 free/month): 14
  • Gemini 3.1 Flash-Lite - Google · Input (Text / image / video): 0.25 · Input (Audio): 0.5 · Output: 1.5 · Context cache (Text / image / video): 0.025 · Context cache (Audio): 0.05 · Cache storage (per hour): 1 · Grounding (Search) (after 5,000 free/month): 14
  • Gemini 2.5 Pro - Google · Input (Text / image / video): 1.25 · Output: 10
  • Gemini 3 Flash - Google · Input (Text / image / video): 0.5 · Input (Audio): 1 · Output: 3 · Context cache (Text / image / video): 0.05 · Context cache (Audio): 0.1 · Cache storage (per hour): 1 · Grounding (Search) (after 5,000 free/month): 14
  • Llama 3.3 70B - Meta · Input: N/A

Image generation

  • Gemini 3.1 Flash Image - Google · Input (Text / image): 0.5 · Image output (0.5K (512px)): 0.045 · Image output (1K (1024×1024)): 0.067 · Image output (2K (2048×2048)): 0.101 · Image output (4K (4096×4096)): 0.151 · Grounding (Search) (after 5,000 free/month): 14
  • Gemini 3 Pro Image - Google · Input (Image (per image)): 0.0011 · Image output (1K–2K (1024–2048px)): 0.134 · Image output (4K (4096×4096)): 0.24 · Grounding (Search) (after 5,000 free/month): 14
  • Gemini 2.5 Flash Image - Google · Image output (1K (1024×1024)): 0.039
  • Flux Schnell - Replicate · Image output: 0.003
  • Flux Pro - Replicate · Image output: 0.055
  • Flux Dev - Replicate · Image output: 0.025
  • Stable Diffusion XL - Replicate · Image output: 0.0095
  • DALL·E 3 - OpenAI · Image output (Standard 1024×1024): 0.04 · Image output (Standard 1024×1792): 0.08 · Image output (HD 1024×1024): 0.08 · Image output (HD 1024×1792): 0.12
  • Ideogram v2 - Ideogram · Image output: 0.08

Video generation

  • Runway Gen-3 - Runway · Video output: 0.05
  • Kling 1.5 - Kling · Video output: 0.42
  • Sora - OpenAI · Video output: N/A
  • Veo 3.1 Standard - Google · Video output (720p / 1080p with audio): 0.4 · Video output (4K with audio): 0.6
  • Veo 3.1 Fast - Google · Video output (720p with audio): 0.1 · Video output (1080p with audio): 0.12 · Video output (4K with audio): 0.3
  • Veo 3.1 Lite - Google · Video output (720p with audio): 0.05 · Video output (1080p with audio): 0.08
  • Veo 3 Standard - Google · Video output (with audio): 0.4
  • Veo 3 Fast - Google · Video output (720p with audio): 0.1 · Video output (1080p with audio): 0.12 · Video output (4K with audio): 0.3
  • Veo 2 - Google · Video output: 0.35

Audio generation

  • Suno v4 - Suno · Audio output: N/A

Text-to-speech

  • Gemini 3.1 Flash TTS - Google · Input (Text): 1 · Output (Audio): 20
  • ElevenLabs v2 - ElevenLabs · TTS output (Per character): 0.0003

Realtime / live

  • Gemini 3.1 Flash Live - Google · Input (Text): 0.75 · Input (Audio): 3 · Input (Audio (per minute)): 0.005 · Input (Image / video): 1 · Input (Image / video (per minute)): 0.002 · Output (Text): 4.5 · Output (Audio): 12 · Output (Audio (per minute)): 0.018 · Grounding (Search) (after 5,000 free/month): 14

Embeddings

  • text-embedding-3-small - OpenAI · Input: 0.02
  • text-embedding-3-large - OpenAI · Input: 0.13
  • text-embedding-ada-002 - OpenAI · Input: 0.1

Moderation

  • omni-moderation-latest - OpenAI · Input: N/A
  • text-moderation-latest - OpenAI · Input: N/A

Provider order: openai, anthropic, google, meta, replicate, runway, kling, ideogram, elevenlabs, suno.