The model catalog

Choose your model.
Keep your API.

Compare capabilities, context and cost for your next task. One request format. One wallet. A price before approval.

Growing lineup · 44 models

Available now

The current testnet lineup.

Live models and x402 prices from the gateway. New providers and models appear here as they become available.

Search models

Provider

Modality

Capability

Output price / 1M tokens

Sort by

44 of 44 models

Compare 2–3 models

0 selected

Select at least two below.

Anthropic / Chatupto + exact

Claude Haiku 5.5

Fastest, lowest-cost Claude model.

Input / 1M tokens: $0.103000
Output / 1M tokens: $0.515000

Plus 0.001000 USDC per call.

100,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Claude Haiku 5.5

Anthropic / Chatupto + exact

Claude Opus 5.5

Most capable Claude model in the Opus line.

Input / 1M tokens: $4.120000
Output / 1M tokens: $20.600000

Plus 0.001000 USDC per call.

1,000,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Claude Opus 5.5

Anthropic / Chatupto + exact

Claude Sonnet 5.5

Balanced Claude model for coding, agents and everyday work.

Input / 1M tokens: $2.060000
Output / 1M tokens: $10.300000

Plus 0.001000 USDC per call.

1,000,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Claude Sonnet 5.5

Black Forest Labs / Imageexact

FLUX.1 schnell

Very fast, cheap FLUX image model.

Per megapixel: $0.003090

Plus 0.001000 USDC per call.

image

View model ↗

Compare FLUX.1 schnell

Google / Chatupto + exact

Gemini 3.8 Flash

Fast Gemini model.

Input / 1M tokens: $0.772500
Output / 1M tokens: $3.862500

Plus 0.001000 USDC per call.

1,048,576 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Gemini 3.8 Flash

OpenAI / Chatupto + exact

GPT-6 Luna

Fast, low-cost GPT-6 model.

Input / 1M tokens: $0.103000
Output / 1M tokens: $0.515000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-6 Luna

OpenAI / Chatupto + exact

GPT-6.1 Sol

Balanced GPT-6 model.

Input / 1M tokens: $2.060000
Output / 1M tokens: $10.300000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-6.1 Sol

Anthropic / Chatupto + exact

Claude Fable 5.1

Anthropic's most capable model.

Input / 1M tokens: $10.300000
Output / 1M tokens: $51.500000

Plus 0.001000 USDC per call.

1,000,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Claude Fable 5.1

Black Forest Labs / Imageexact

FLUX.1 dev

Higher-quality FLUX image model.

Per megapixel: $0.025750

Plus 0.001000 USDC per call.

image

View model ↗

Compare FLUX.1 dev

Black Forest Labs / Imageexact

FLUX1.1 pro

FLUX pro image model.

Per megapixel: $0.041200

Plus 0.001000 USDC per call.

image

View model ↗

Compare FLUX1.1 pro

Google / Chatupto + exact

Gemini 3.1 Flash-Lite

Cheapest Gemini model.

Input / 1M tokens: $0.257500
Output / 1M tokens: $1.545000

Plus 0.001000 USDC per call.

1,048,576 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Gemini 3.1 Flash-Lite

Google / Chatupto + exact

Gemini 3.1 Pro (preview)

Gemini 3.1 Pro preview.

Input / 1M tokens: $2.060000
Output / 1M tokens: $12.360000

Plus 0.001000 USDC per call.

200,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Gemini 3.1 Pro (preview)

Google / Chatupto + exact

Gemini 3.5 Flash-Lite

Low-cost Gemini model.

Input / 1M tokens: $0.309000
Output / 1M tokens: $2.575000

Plus 0.001000 USDC per call.

1,048,576 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Gemini 3.5 Flash-Lite

Google / Chatupto + exact

Gemini 4 Argon

Google's flagship Gemini model.

Input / 1M tokens: $2.060000
Output / 1M tokens: $10.300000

Plus 0.001000 USDC per call.

1,048,576 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare Gemini 4 Argon

OpenAI / Imageexact

GPT Image 1

OpenAI image generation.

1024x1024 · low / image: $0.011330
1024x1536 · low / image: $0.016480
1536x1024 · low / image: $0.016480
1024x1024 · high / image: $0.172010
1024x1536 · high / image: $0.257500
1536x1024 · high / image: $0.257500
1024x1024 · medium / image: $0.043260
1024x1536 · medium / image: $0.064890
1536x1024 · medium / image: $0.064890

Plus 0.001000 USDC per call.

image

View model ↗

Compare GPT Image 1

OpenAI / Imageexact

GPT Image 1 mini

Low-cost OpenAI image generation.

1024x1024 · low / image: $0.005150
1024x1536 · low / image: $0.006180
1536x1024 · low / image: $0.006180
1024x1024 · high / image: $0.037080
1024x1536 · high / image: $0.053560
1536x1024 · high / image: $0.053560
1024x1024 · medium / image: $0.011330
1024x1536 · medium / image: $0.015450
1536x1024 · medium / image: $0.015450

Plus 0.001000 USDC per call.

image

View model ↗

Compare GPT Image 1 mini

OpenAI / Chatupto + exact

GPT-4.1 mini

Non-reasoning GPT-4.1 small model.

Input / 1M tokens: $0.412000
Output / 1M tokens: $1.648000

Plus 0.001000 USDC per call.

1,047,576 context · chat, vision, tools, streaming, json

View model ↗

Compare GPT-4.1 mini

OpenAI / Chatupto + exact

GPT-5 mini

Small GPT-5 model.

Input / 1M tokens: $0.257500
Output / 1M tokens: $2.060000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5 mini

OpenAI / Chatupto + exact

GPT-5 nano

Cheapest GPT-5 model.

Input / 1M tokens: $0.051500
Output / 1M tokens: $0.412000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5 nano

OpenAI / Chatupto + exact

GPT-5.4 mini

Small GPT-5.4 model.

Input / 1M tokens: $0.772500
Output / 1M tokens: $4.635000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5.4 mini

OpenAI / Chatupto + exact

GPT-5.4 nano

Smallest GPT-5.4 model.

Input / 1M tokens: $0.206000
Output / 1M tokens: $1.287500

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5.4 nano

OpenAI / Chatupto + exact

GPT-5.5

GPT-5.5 reasoning model.

Input / 1M tokens: $5.150000
Output / 1M tokens: $30.900000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5.5

OpenAI / Chatupto + exact

GPT-5.6 Luna

Low-cost GPT-5.6 model.

Input / 1M tokens: $0.206000
Output / 1M tokens: $1.236000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5.6 Luna

OpenAI / Chatupto + exact

GPT-5.6 Terra

GPT-5.6 general-purpose model.

Input / 1M tokens: $2.060000
Output / 1M tokens: $12.360000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-5.6 Terra

OpenAI / Chatupto + exact

GPT-6 Astra

OpenAI's flagship reasoning model.

Input / 1M tokens: $10.300000
Output / 1M tokens: $51.500000

Plus 0.001000 USDC per call.

272,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare GPT-6 Astra

Kuaishou / Videoexact

Kling O3 Pro (reference)

Keeps a character consistent across shots (character_image_urls, reference_image_urls).

1080p / second: $0.115360
1080p · audio / second: $0.144200

Plus 0.001000 USDC per call.

video, reference_images, image_to_video

View model ↗

Compare Kling O3 Pro (reference)

Kuaishou / Videoexact

Kling v3 Pro

Kling v3 Pro text to video.

1080p / second: $0.115360
1080p · audio / second: $0.173040

Plus 0.001000 USDC per call.

video

View model ↗

Compare Kling v3 Pro

Google / Imageexact

Nano Banana 2

Google's Gemini image model (1K output).

Per image: $0.082400

Plus 0.001000 USDC per call.

image

View model ↗

Compare Nano Banana 2

Google / Imageexact

Nano Banana 2 Edit

Edit or compose from up to 10 reference images (JSON image_urls).

Per image: $0.082400

Plus 0.001000 USDC per call.

image, image_edit

View model ↗

Compare Nano Banana 2 Edit

OpenAI / Chatupto + exact

o3

OpenAI o-series reasoning model.

Input / 1M tokens: $2.060000
Output / 1M tokens: $8.240000

Plus 0.001000 USDC per call.

200,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare o3

OpenAI / Chatupto + exact

o4-mini

Small o-series reasoning model.

Input / 1M tokens: $1.133000
Output / 1M tokens: $4.532000

Plus 0.001000 USDC per call.

200,000 context · chat, vision, tools, streaming, reasoning, json

View model ↗

Compare o4-mini

OpenAI / Moderationexact

Omni Moderation

OpenAI text and image moderation (free upstream; fixed per-call fee only).

Per 1M characters: $0.000000

Plus 0.001000 USDC per call.

moderation

View model ↗

Compare Omni Moderation

Recraft / Imageexact

Recraft V3

Design-oriented image model (raster styles).

Per image: $0.041200

Plus 0.001000 USDC per call.

image

View model ↗

Compare Recraft V3

ByteDance / Videoexact

Seedance 2.0 (reference)

Multi-shot video from up to 9 reference images.

720p / second: $0.312502
1080p / second: $0.702460
720p · audio / second: $0.312502
1080p · audio / second: $0.702460

Plus 0.001000 USDC per call.

video, reference_images, image_to_video

View model ↗

Compare Seedance 2.0 (reference)

ByteDance / Imageexact

Seedream 4

ByteDance image model.

Per image: $0.030900

Plus 0.001000 USDC per call.

image

View model ↗

Compare Seedream 4

OpenAI / Embeddingsexact

Text Embedding 3 Large

Most capable OpenAI embedding model (3072 dims).

Input / 1M tokens: $0.133900

Plus 0.001000 USDC per call.

embeddings

View model ↗

Compare Text Embedding 3 Large

OpenAI / Embeddingsexact

Text Embedding 3 Small

Small, cheap OpenAI embedding model (1536 dims).

Input / 1M tokens: $0.020600

Plus 0.001000 USDC per call.

embeddings

View model ↗

Compare Text Embedding 3 Small

OpenAI / Speechexact

TTS-1

OpenAI text to speech.

Per 1M characters: $15.450000

Plus 0.001000 USDC per call.

tts

View model ↗

Compare TTS-1

OpenAI / Speechexact

TTS-1 HD

Higher-quality OpenAI text to speech.

Per 1M characters: $30.900000

Plus 0.001000 USDC per call.

tts

View model ↗

Compare TTS-1 HD

Google / Videoexact

Veo 3.1

Google's flagship Veo video model with native audio.

720p / second: $0.206000
1080p / second: $0.206000
720p · audio / second: $0.412000
1080p · audio / second: $0.412000

Plus 0.001000 USDC per call.

video

View model ↗

Compare Veo 3.1

Google / Videoexact

Veo 3.1 (image to video)

Veo 3.1 starting from your image (image_url = first frame).

720p / second: $0.206000
1080p / second: $0.206000
720p · audio / second: $0.412000
1080p · audio / second: $0.412000

Plus 0.001000 USDC per call.

video, image_to_video

View model ↗

Compare Veo 3.1 (image to video)

Google / Videoexact

Veo 3.1 Fast

Google's fast Veo video model (with optional audio).

720p / second: $0.103000
1080p / second: $0.103000
720p · audio / second: $0.154500
1080p · audio / second: $0.154500

Plus 0.001000 USDC per call.

video

View model ↗

Compare Veo 3.1 Fast

Google / Videoexact

Veo 3.1 Fast (image to video)

Fast Veo 3.1 starting from your image (image_url = first frame).

720p / second: $0.103000
1080p / second: $0.103000
720p · audio / second: $0.154500
1080p · audio / second: $0.154500

Plus 0.001000 USDC per call.

video, image_to_video

View model ↗

Compare Veo 3.1 Fast (image to video)

OpenAI / Transcriptionexact

Whisper

OpenAI speech to text.

Per minute: $0.006180

Plus 0.001000 USDC per call.

stt

View model ↗

Compare Whisper

Token rates include the infrastructure fee. Per-unit prices use the unit shown. Each call adds the listed fixed fee; take the final amount from your request’s actual offer.

From model choice to your first call

Pick a model.
Put it to work.

Contact Synal ↗

The current testnet lineup.

Pick a model.Put it to work.

Pick a model.
Put it to work.