Pay for tokens. That's the whole bill.

The rate beside each model is the whole price — there is no gateway fee on top of it. Top up a balance and pay for what you send.

Get your API key Read the quickstart

Pay as you go

Every model in the catalogue, at the rate on this page, with nothing added on top.

Pay as you go

0%gateway fees

Pay the model rate, with nothing added on top.
No seats, no monthly minimum, no commitment.
Top up any amount and spend it on any model.

Spending a lot every month?Ask about volume discounts

Get your API key See every price

Volume discounts

Sending serious volume? Pay less per token.

0% gateway fees is where pay as you go starts, not where it ends. If your team spends steadily every month, tell us roughly how much and we will put together a discount on the models you use most.

Lower rates on the models you send the most traffic to
Applied to your workspace, so every project and key gets them
Still no seats, no fees, and no lock-in

Talk to us about volume pricing

Or email us at support@cloakray.com

Every model, every price

Text models are priced per 1M tokens. Image models are priced the way their provider bills them — per generated image, per request, or per token — so each row shows its own unit. What you see is what you pay, with no gateway fee on top.

Anthropic

16 models

Anthropic models, with the list price and the Cloakray price for each.
Model	Context	Input
Claude Fable 5.1claude-fable-5-1	1M	$10 / 1M input tokens · $50 / 1M output tokens · See all rates on the model page
Claude Opus 5.5claude-opus-5-5	1M	$4 / 1M input tokens · $20 / 1M output tokens · See all rates on the model page
Claude Fable 5claude-fable-5	1M	$10 / 1M input tokens · $50 / 1M output tokens · See all rates on the model page
Claude Opus 5claude-opus-5	1M	$5 / 1M input tokens · $25 / 1M output tokens · See all rates on the model page
Claude Opus 4.8claude-opus-4-8	1M	$5 / 1M input tokens · $25 / 1M output tokens · See all rates on the model page
Claude Opus 4.7claude-opus-4-7	1M	$5 / 1M input tokens · $25 / 1M output tokens · See all rates on the model page
Claude Opus 4.6claude-opus-4-6	1M	$5 / 1M input tokens · $25 / 1M output tokens · See all rates on the model page
Claude Sonnet 5.5claude-sonnet-5-5	1M	$2 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
Claude Sonnet 5claude-sonnet-5	1M	$2 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
Claude Sonnet 4.6claude-sonnet-4-6	1M	$3 / 1M input tokens · $15 / 1M output tokens · See all rates on the model page
Claude Haiku 5.5claude-haiku-5-5	1M	$0.1 / 1M input tokens · $0.5 / 1M output tokens · See all rates on the model page
Claude Haiku 4.5claude-haiku-4-5	200K	$1 / 1M input tokens · $5 / 1M output tokens · See all rates on the model page
Claude Haiku 4.5 (2025-10-01)claude-haiku-4-5-20251001	200K	$1 / 1M input tokens · $5 / 1M output tokens · See all rates on the model page
Claude Opus 4.5claude-opus-4-5-20251101	200K	$5 / 1M input tokens · $25 / 1M output tokens · See all rates on the model page
Claude Sonnet 4.5claude-sonnet-4-5	200K	$3 / 1M input tokens · $15 / 1M output tokens · See all rates on the model page
Claude Sonnet 4.5 (2025-09-29)claude-sonnet-4-5-20250929	200K	$3 / 1M input tokens · $15 / 1M output tokens · See all rates on the model page

OpenAI

43 models

OpenAI models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
GPT-6 Astragpt-6-astra	1.1M	$10 / 1M input tokens · $50 / 1M output tokens · See all rates on the model page
GPT-6.1 Solgpt-6.1-sol	1.1M	$2 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
GPT-6.1 Terragpt-6.1-terra	1.1M	$1 / 1M input tokens · $5 / 1M output tokens · See all rates on the model page
GPT-6 Solgpt-6-sol	1.1M	$2 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
GPT-6 Lunagpt-6-luna	1.1M	$0.1 / 1M input tokens · $0.5 / 1M output tokens · See all rates on the model page
GPT-5.6 Solgpt-5.6-sol	1.1M	$4 / 1M input tokens · $20 / 1M output tokens · See all rates on the model page
GPT-5.6 Terragpt-5.6-terra	1.1M	$2 / 1M input tokens · $12 / 1M output tokens · See all rates on the model page
GPT-5.6 Lunagpt-5.6-luna	1.1M	$0.2 / 1M input tokens · $1.2 / 1M output tokens · See all rates on the model page
GPT-5.5gpt-5.5	1.1M	$5 / 1M input tokens · $30 / 1M output tokens · See all rates on the model page
GPT-5.4gpt-5.4	1.1M	$2.5 / 1M input tokens · $15 / 1M output tokens · See all rates on the model page
GPT-5.2gpt-5.2	400K	$1.75 / 1M input tokens · $14 / 1M output tokens · See all rates on the model page
GPT Image 2.5 Sunburstgpt-image-2.5-sunburst	—	$30 / 1M image tokens Temporarily unavailable
GPT Image 2.5 Flaregpt-image-2.5-flare	—	$30 / 1M image tokens Temporarily unavailable
GPT Image 2gpt-image-2	—	$30 / 1M image tokens
GPT-4.1gpt-4.1	1M	$2	$0.5	$8
GPT-4.1 Minigpt-4.1-mini	1M	$0.4	$0.1	$1.6
GPT-4ogpt-4o	128K	$2.5 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
GPT-4o Minigpt-4o-mini	128K	$0.15	$0.075	$0.6
GPT-4o Mini TTSgpt-4o-mini-tts	2K	$0.6 / 1M input tokens · $12 / 1M output tokens · See all rates on the model page Temporarily unavailable
GPT-5gpt-5	400K	$1.25 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
GPT-5 Minigpt-5-mini	400K	$0.25 / 1M input tokens · $2 / 1M output tokens · See all rates on the model page
GPT-5 Nanogpt-5-nano	400K	$0.05 / 1M input tokens · $0.4 / 1M output tokens · See all rates on the model page
GPT-5 Progpt-5-pro	400K	$15 / 1M input tokens · $120 / 1M output tokens · See all rates on the model page
GPT-5.1gpt-5.1	400K	$1.25 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
GPT-5.1 Codexgpt-5.1-codex	400K	$1.25 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
GPT-5.1 Codex minigpt-5.1-codex-mini	400K	$0.25 / 1M input tokens · $2 / 1M output tokens · See all rates on the model page
GPT-5.2 Codexgpt-5.2-codex	400K	$1.75 / 1M input tokens · $14 / 1M output tokens · See all rates on the model page
GPT-5.2 Progpt-5.2-pro	400K	$21 / 1M input tokens · $168 / 1M output tokens · See all rates on the model page
GPT-5.3 Codexgpt-5.3-codex	400K	$1.75 / 1M input tokens · $14 / 1M output tokens · See all rates on the model page
GPT-5.4 Minigpt-5.4-mini	400K	$0.75 / 1M input tokens · $4.5 / 1M output tokens · See all rates on the model page
GPT-5.4 Nanogpt-5.4-nano	400K	$0.2 / 1M input tokens · $1.25 / 1M output tokens · See all rates on the model page
GPT-5.4 Progpt-5.4-pro	1.1M	$30 / 1M input tokens · $180 / 1M output tokens · See all rates on the model page
GPT-5.5 Progpt-5.5-pro	1.1M	$30 / 1M input tokens · $180 / 1M output tokens · See all rates on the model page
GPT-6 Luna Decisionsgpt-6-luna-decisions	1.1M	$0.1 / 1M input tokens · $0.1 / 1M input tokens · Up to 272K input tokens · See all rates on the model page
GPT OSS 120Bgpt-oss-120b	131K	$0.15	Price not published	$0.75
GPT OSS 20Bgpt-oss-20b	131K	$0.1	Price not published	$0.5
o3o3	200K	$2	$0.5	$8
Text Embedding 3 Largetext-embedding-3-large	8K	$0.13 / 1M input tokens
Text Embedding 3 Smalltext-embedding-3-small	8K	$0.02 / 1M input tokens
Text Embedding Ada 002text-embedding-ada-002	8K	$0.1 / 1M input tokens
TTS-1tts-1	4K	$15 / 1M characters
TTS-1 HDtts-1-hd	4K	$30 / 1M characters
Moderationopenai-moderation	—	$0.00001 / request

Google

30 models

Google models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Gemini 3 Pro Image (Preview)gemini-3-pro-image-preview	—	$0.1344–$0.24 / image
Gemini 3 Pro Imagegemini-3-pro-image	—	$0.1344–$0.24 / image
Gemini 3.1 Flash Imagegemini-3.1-flash-image	—	$0.04482–$0.1512 / image
Gemini 3.1 Flash Lite Imagegemini-3.1-flash-lite-image	—	$0.0336 / image
Gemini Nano Banana 2.1gemini-nano-banana-2.1	—	$0.0336–$0.0756 / image
Gemini 2.5 Flash Imagegemini-2.5-flash-image	—	$0.0387 / image
Gemini 4 Argongemini-4-argon	1.0M	$4 / 1M input tokens · $20 / 1M output tokens · See all rates on the model page
Gemini 3.8 Flashgemini-3.8-flash	1.0M	$0.75 / 1M input tokens · $3.75 / 1M output tokens · See all rates on the model page
Gemini 3.5 Flashgemini-3.5-flash	1.0M	$1.5 / 1M input tokens · $9 / 1M output tokens · See all rates on the model page
Gemini 3.5 Flash Litegemini-3.5-flash-lite	1.0M	$0.3 / 1M input tokens · $2.5 / 1M output tokens · See all rates on the model page
Gemini 3.1 Flash Litegemini-3.1-flash-lite	1.0M	$0.25 / 1M input tokens · $1.5 / 1M output tokens · See all rates on the model page
Gemini 3.1 Pro (Preview)gemini-3.1-pro-preview	1.0M	$2 / 1M input tokens · $12 / 1M output tokens · See all rates on the model page
Gemini 2.5 Flash Preview TTSgemini-2.5-flash-preview-tts	8K	$0.5 / 1M input tokens · $10 / 1M output tokens · See all rates on the model page
Gemini 2.5 Pro Preview TTSgemini-2.5-pro-preview-tts	8K	$1 / 1M input tokens · $20 / 1M output tokens · See all rates on the model page
Gemini 3 Flash (Preview)gemini-3-flash-preview	1.0M	$0.5 / 1M input tokens · $3 / 1M output tokens · See all rates on the model page
Gemini 3.1 Flash Image (Preview)gemini-3.1-flash-image-preview	—	$0.04482–$0.1512 / image
Gemini 3.1 Flash TTS Previewgemini-3.1-flash-tts-preview	8K	$1 / 1M input tokens · $20 / 1M output tokens · See all rates on the model page
Gemini 3.6 Flashgemini-3.6-flash	1.0M	$0.75 / 1M input tokens · $3.75 / 1M output tokens · See all rates on the model page
Gemini 3.7 Flashgemini-3.7-flash	1.0M	$0.75 / 1M input tokens · $3.75 / 1M output tokens · See all rates on the model page
Gemini Embedding 001gemini-embedding-001	2K	$0.15 / 1M input tokens
Gemini Embedding 2gemini-embedding-2	8K	$0.2 / 1M input tokens
Gemini Omni 1.1 Flashgemini-omni-1.1-flash	131K	$0.0338–$0.3041 / second Temporarily unavailable
Gemini Pro Latestgemini-pro-latest	1.0M	$2 / 1M input tokens · $12 / 1M output tokens · See all rates on the model page
Gemma 4 26B A4B ITgemma-4-26b-a4b-it	262K	$0.07	Price not published	$0.34
Gemma 4 31B ITgemma-4-31b-it	262K	$0.2	Price not published	$0.4
Text Embedding 004text-embedding-004	2K	$0.025 / 1M input tokens
Text Embedding 005text-embedding-005	2K	$0.025 / 1M input tokens
Text Multilingual Embedding 002text-multilingual-embedding-002	2K	$0.025 / 1M input tokens
Veo 3.1 Fastveo-3.1-fast-generate-preview	33K	$0.10–$0.35 / second
Veo 3.1veo-3.1-generate-preview	33K	$0.20–$0.60 / second

DeepSeek

6 models

DeepSeek models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
DeepSeek V4.1 Flashdeepseek-v4.1-flash	1M	$0.15 / 1M input tokens · $0.6 / 1M output tokens · See all rates on the model page
DeepSeek V3.2deepseek-v3.2	131K	$0.28	$0.028	$0.42
DeepSeek V4 Flashdeepseek-v4-flash	1.1M	$0.14 / 1M input tokens · $0.28 / 1M output tokens · See all rates on the model page
DeepSeek V4 Prodeepseek-v4-pro	1.1M	$0.66 / 1M input tokens · $1.98 / 1M output tokens · See all rates on the model page
DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017	1M	$0.15 / 1M input tokens · $0.6 / 1M output tokens · See all rates on the model page
DeepSeek V4.1 Flash Cyberdeepseek-v4.1-flash-cyber	1.0M	$0.3 Availability not yet verified	$0.007	$1

Z.ai

23 models

Z.ai models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
GLM-5.3glm-5.3	262K	$0.77	$0.143	$2.42
GLM-5.2glm-5.2	1M	$1.4 / 1M input tokens · $4.4 / 1M output tokens · See all rates on the model page
CogView-4cogview-4	—	$0.01 / request
GLM-4 32B (0414-128k)glm-4-32b-0414-128k	128K	$0.1	Price not published	$0.1
GLM-4.5glm-4.5	128K	$0.6 / 1M input tokens · $2.2 / 1M output tokens · See all rates on the model page
GLM-4.5 Airglm-4.5-air	128K	$0.2	$0.03	$1.1
GLM-4.5 AirXglm-4.5-airx	128K	$1.1	$0.22	$4.5
GLM-4.5 Xglm-4.5-x	128K	$2.2	$0.45	$8.9
GLM-4.5Vglm-4.5v	128K	$0.6	$0.11	$1.8
GLM-4.6glm-4.6	200K	$0.6 / 1M input tokens · $2.2 / 1M output tokens · See all rates on the model page
GLM-4.6Vglm-4.6v	128K	$0.3	$0.05	$0.9
GLM-4.6V FlashXglm-4.6v-flashx	128K	$0.04	$0.004	$0.4
GLM-4.7glm-4.7	200K	$0.6 / 1M input tokens · $2.2 / 1M output tokens · See all rates on the model page
GLM-4.7 FlashXglm-4.7-flashx	200K	$0.07	$0.01	$0.4
GLM-5glm-5	203K	$1 / 1M input tokens · $3.2 / 1M output tokens · See all rates on the model page
GLM-5 Turboglm-5-turbo	200K	$1.2	$0.24	$4
GLM-5.1glm-5.1	200K	$1.4 / 1M input tokens · $4.4 / 1M output tokens · See all rates on the model page
GLM-5.2 Turboglm-5.2-fast	1M	Price not published Availability not yet verified
GLM 5.3 Fastglm-5.3-fast	1M	Price not published Availability not yet verified
GLM-5.3 Flashglm-5.3-flash	1M	$0.15	$0.03	$0.5
GLM-5.3 FlashXglm-5.3-flashx	1M	$0.37 Availability not yet verified	$0.075	$1.25
GLM-5V Turboglm-5v-turbo	200K	$1.2	$0.24	$4
GLM-Imageglm-image	—	$0.015 / request

Moonshot AI

10 models

Moonshot AI models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Kimi K3kimi-k3	1.0M	$3	$0.3	$15
Kimi K2.6kimi-k2.6	262K	$0.95	$0.16	$4
Kimi K2kimi-k2	131K	$1	$0.5	$3
Kimi K2.5kimi-k2.5	262K	$0.6	$0.1	$3
Kimi K2.7 Codekimi-k2.7-code	262K	$0.95	$0.19	$4
Kimi K2.7 Code Highspeedkimi-k2.7-code-highspeed	262K	$1.9	$0.38	$8
Kimi K2.8 Previewkimi-k2.8-preview	1M	$1 Availability not yet verified	$0.25	$4
Kimi K3 Fastkimi-k3-fast	1.0M	$4.5	$0.45	$22.5
Kimi K3.1 Prokimi-k3.1-pro	1.0M	$2	$0.2	$10
Kimi K3.1 Pro Highspeedkimi-k3.1-pro-highspeed	1.0M	$4	$0.2	$20

Alibaba

40 models

Alibaba models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Qwen3.8 Maxqwen3.8-max	984K	$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model page
Qwen-Audio-3.0-TTS Flashqwen-audio-3.0-tts-flash	20K	$15 / 1M characters
Qwen-Audio-3.0-TTS Plusqwen-audio-3.0-tts-plus	20K	$20 / 1M characters
Qwen Flashqwen-flash	1M	$0.05 / 1M input tokens · $0.4 / 1M output tokens · See all rates on the model page
Qwen Image 2.1 Proqwen-image-2.1-pro	—	$0.04 / image · Default
Qwen Image 2.1 Turboqwen-image-2.1-turbo	—	$0.016 / image · Default
Qwen Image 3.0qwen-image-3.0	—	$0.03 / image · Default
Qwen Image 3.0 Proqwen-image-3.0-pro	—	$0.04 / image · Rate tier: 1K · $0.075 / image · Rate tier: 2K · See all rates on the model page
Qwen Maxqwen-max	33K	$1.6	Price not published	$6.4
Qwen Plusqwen-plus	131K	$0.4 / 1M input tokens · $1.2 / 1M output tokens · See all rates on the model page
Qwen Plus Latestqwen-plus-latest	1M	$0.4 / 1M input tokens · $1.2 / 1M output tokens · See all rates on the model page
Qwen3 14Bqwen3-14b	33K	$0.08 Availability not yet verified	Price not published	$0.24
Qwen3 30B A3Bqwen3-30b-a3b	33K	$0.1 Availability not yet verified	Price not published	$0.3
Qwen3 32Bqwen3-32b	41K	$0.1 Availability not yet verified	Price not published	$0.3
Qwen3 Coder Flashqwen3-coder-flash	998K	$0.3 / 1M input tokens · $1.5 / 1M output tokens · See all rates on the model page
Qwen3 Embedding 0.6Bqwen3-embedding-0.6b	33K	$0.01 / 1M input tokens
Qwen3 Embedding 8Bqwen3-embedding-8b	33K	$0.01 / 1M input tokens
Qwen3 Reranker 0.6Bqwen3-reranker-0.6b	33K	$0.01 / 1M input tokens
Qwen3 Reranker 4Bqwen3-reranker-4b	33K	$0.025 / 1M input tokens
Qwen3 Reranker 8Bqwen3-reranker-8b	33K	$0.05 / 1M input tokens
Qwen3 VL 235B A22B Instructqwen3-vl-235b-a22b-instruct	262K	$0.5	Price not published	$2
Qwen3 VL 30B A3B Instructqwen3-vl-30b-a3b-instruct	131K	$0.2	Price not published	$0.7
Qwen3 VL Plusqwen3-vl-plus	262K	$0.2 / 1M input tokens · $1.6 / 1M output tokens · See all rates on the model page
Qwen3.5 122B A10Bqwen3.5-122b-a10b	262K	$0.4	Price not published	$3.2
Qwen3.5 27Bqwen3.5-27b	262K	$0.3	Price not published	$2.4
Qwen3.5 35B A3Bqwen3.5-35b-a3b	262K	$0.25	Price not published	$2
Qwen3.5 9Bqwen3.5-9b	262K	$0.1	Price not published	$0.15
Qwen3.6 27Bqwen3.6-27b	16K	Price not published Availability not yet verified
Qwen3.6 35B A3Bqwen3.6-35b-a3b	262K	$0.375 / 1M input tokens · $2.25 / 1M output tokens · See all rates on the model page
Qwen3.6 Flashqwen3.6-flash	984K	$0.25 / 1M input tokens · $1.5 / 1M output tokens · See all rates on the model page
Qwen3.6 Plusqwen3.6-plus	984K	$0.5 / 1M input tokens · $3 / 1M output tokens · See all rates on the model page
Qwen3.7 Flashqwen3.7-flash	984K	$0.03 / 1M input tokens · $0.13 / 1M output tokens · See all rates on the model page
Qwen3.7 Maxqwen3.7-max	984K	$2.5 / 1M input tokens · $7.5 / 1M output tokens · See all rates on the model page
Qwen3.7 Plusqwen3.7-plus	984K	$0.4 / 1M input tokens · $1.6 / 1M output tokens · See all rates on the model page
Qwen3.8 2.4T A95Bqwen3.8-2.4t-a95b	1M	$2	$0.25	$6
Qwen3.8 27Bqwen3.8-27b	1M	$0.42	$0.085	$3
Qwen3.8 Flashqwen3.8-flash	984K	$0.15 / 1M input tokens · $0.47 / 1M output tokens · See all rates on the model page
Qwen3.8 Omni Flashqwen3.8-omni-flash	984K	$0.15	$0.016	$0.47
Qwen3.5 397B A17Bqwen35-397b-a17b	262K	$0.6 / 1M input tokens · $3.6 / 1M output tokens · See all rates on the model page
Wan 2.6 Text-to-Videowan-2-6-t2v	2K	$0.08–$0.12 / second

MiniMax

12 models

MiniMax models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
MiniMax M3minimax-m3	512K	$0.6	$0.12	$2.4
MiniMax H3 Maxminimax-h3-max	7K	$0.05–$0.08 / second
MiniMax Hailuo 2.3minimax-hailuo-2-3	2K	$0.0467–$0.0817 / second
MiniMax M2minimax-m2	197K	$0.2	$0.03	$1
MiniMax M2.1minimax-m2.1	197K	$0.27	Price not published	$1.1
MiniMax M2.1 Lightningminimax-m2.1-lightning	197K	$0.12	Price not published	$0.48
MiniMax M2.5minimax-m2.5	205K	$0.3	$0.03	$1.2
MiniMax M2.5 Highspeedminimax-m2.5-highspeed	205K	$0.6	$0.03	$2.4
MiniMax M2.7minimax-m2.7	205K	$0.3	$0.06	$1.2
MiniMax M2.7 Highspeedminimax-m2.7-highspeed	205K	$0.6	$0.06	$2.4
MiniMax M3.1 Flashminimax-m3.1-flash	1.0M	$0.15	$0.015	$0.6
MiniMax Text 01minimax-text-01	1M	$0.2	Price not published	$1.1

ByteDance

18 models

ByteDance models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Seedance 2.0 Miniseedance-2-0-mini	2K	$0.0378–$0.0756 / second
Seed 1.6 (250615)seed-1-6-250615	256K	$0.25	$0.05	$2
Seed 1.6 (250915)seed-1-6-250915	256K	$0.25	$0.05	$2
Seed 1.6 Flash (250715)seed-1-6-flash-250715	256K	$0.07	$0.015	$0.3
Seed 1.8 (251228)seed-1-8-251228	256K	$0.25	$0.05	$2
Seed 2.0 Code Preview (260328)seed-2-0-code-preview-260328	262K	$0.5 / 1M input tokens · $3 / 1M output tokens · See all rates on the model page
Seed 2.0 Lite (260428)seed-2-0-lite-260428	262K	$0.25 / 1M input tokens · $2 / 1M output tokens · See all rates on the model page
Seed 2.0 Mini (260428)seed-2-0-mini-260428	262K	$0.1 / 1M input tokens · $0.4 / 1M output tokens · See all rates on the model page
Seed 2.0 Pro (260328)seed-2-0-pro-260328	262K	$0.5 / 1M input tokens · $3 / 1M output tokens · See all rates on the model page
Seedance 1.5 Proseedance-1-5-pro	2K	$0.0259–$0.1166 / second
Seedance 2.0seedance-2-0	2K	$0.1512–$0.3402 / second
Seedance 2.0 Fastseedance-2-0-fast	2K	$0.121–$0.2722 / second
Seedance 2.5seedance-2-5	2K	$0.1028–$0.52 / second
Seedream 4.0seedream-4-0	—	$0.035 / request
Seedream 4.5seedream-4-5	—	$0.045 / request
Seedream 5.0 Flashseedream-5-0-flash	—	$0.018 / request
Seedream 5.0 Liteseedream-5-0-lite	—	$0.035 / request
Seedream 5.0 Proseedream-5-0-pro	—	$0.09 / request

Baai

1 model

Baai models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
BGE-M3bge-m3	8K	$0.01 / 1M input tokens

Mistral

12 models

Mistral models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Codestralcodestral-2508	256K	$0.3	Price not published	$0.9
Devstral 2devstral-2512	262K	$0.4	Price not published	$2
Ministral 14Bministral-14b-2512	262K	$0.2	Price not published	$0.2
Ministral 3Bministral-3b-2512	131K	$0.1	Price not published	$0.1
Ministral 8Bministral-8b-2512	262K	$0.15	Price not published	$0.15
Mistral Large 3mistral-large-2512	262K	$0.5	Price not published	$1.5
Mistral Large 4mistral-large-4	1M	$1.36	$0.14	$4.18
Mistral Large Latestmistral-large-latest	128K	$4	Price not published	$12
Mistral Medium 3.5mistral-medium-3-5	262K	$1.5	Price not published	$7.5
Mistral OCRmistral-ocr-latest	—	$0.004 / page
Mistral Small 3.2mistral-small-2506	128K	$0.1	Price not published	$0.3
Mistral Small 4mistral-small-2603	262K	$0.15	Price not published	$0.6

ElevenLabs

4 models

ElevenLabs models, with the list price and the Cloakray price for each.
Model	Context	Input
Eleven Flash v2.5eleven-flash-v2-5	40K	$55 / 1M characters
Eleven Multilingual v2eleven-multilingual-v2	10K	$110 / 1M characters
Eleven Turbo v2.5eleven-turbo-v2-5	40K	$55 / 1M characters
Eleven v3eleven-v3	5K	$110 / 1M characters

Black Forest Labs

1 model

Black Forest Labs models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
FLUX 3 Maxflux-3-max	—	$0.17–$0.29 / second Availability not yet verified

Sakana AI

3 models

Sakana AI models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Fugu Maxfugu-max	1M	$2	$0.25	$6
Fugu Ultrafugu-ultra	1M	$5 / 1M input tokens · $30 / 1M output tokens · See all rates on the model page
Fugu Ultra v2.0fugu-ultra-v2.0	1M	$5 / 1M input tokens · $30 / 1M output tokens · See all rates on the model page

Ibm

1 model

Ibm models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Granite 4.2 8Bgranite-4.2-8b	131K	$0.06	$0.015	$0.25

xAI

17 models

xAI models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Grok 4grok-4	256K	$3 / 1M input tokens · $15 / 1M output tokens · See all rates on the model page
Grok 4.1 Fast Reasoninggrok-4-1-fast-reasoning	128K	$0.2 / 1M input tokens · $0.5 / 1M output tokens · See all rates on the model page
Grok 4.20 Beta Non-Reasoning (0309)grok-4-20-beta-0309-non-reasoning	2M	$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model page
Grok 4.20 Beta Reasoning (0309)grok-4-20-beta-0309-reasoning	2M	$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model page
Grok 4.20 Non-Reasoninggrok-4-20-non-reasoning	2M	$1.25	$0.2	$2.5
Grok 4.20 Reasoninggrok-4-20-reasoning	2M	$1.25	$0.2	$2.5
Grok 4.3grok-4-3	1M	$1.25 / 1M input tokens · $2.5 / 1M output tokens · See all rates on the model page
Grok 4.5grok-4-5	500K	$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model page
Grok 4.6grok-4-6	500K	$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model page
Grok 4.7grok-4-7	500K	$2 / 1M input tokens · $6 / 1M output tokens · See all rates on the model page
Grok Build 0.1grok-build-0-1	256K	$1 / 1M input tokens · $2 / 1M output tokens · See all rates on the model page
Grok Imagine Imagegrok-imagine-image	—	$0.02 / request
Grok Imagine Image 2.0grok-imagine-image-2-0	—	$0.04 / image · Rate tier: low/1k · $0.06 / image · Rate tier: low/2k · See all rates on the model page
Grok Imagine Video 1.5grok-imagine-video-1-5	2K	$0.08–$0.14 / second
Grok Imagine Video 1.5 Litegrok-imagine-video-1-5-lite	2K	$0.02–$0.03 / second
Grok Imagine Video 1.5 Previewgrok-imagine-video-1-5-preview	2K	$0.08–$0.14 / second
Grok STT 1.0grok-stt-1-0	—	$0.1 / audio hour

Tencent Cloud

4 models

Tencent Cloud models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Hy Image 3.5 Previewhy-image-v3.5-preview	—	$0.032 / image
Hy-MT2 Plushy-mt2-plus	8K	$0.074	Price not published	$0.295
Hy3hy3	262K	$0.14	$0.035	$0.58
Hy4 Previewhy4-preview	1M	$0.834	$0.042	$2.501

TypeSafe AI

2 models

TypeSafe AI models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Jev 1.13jev-1.13.0	262K	$0.042 / 1M input tokens
Jev 1.14jev-1.14.0	262K	$0.042 / 1M input tokens

Kinfra

2 models

Kinfra models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Kinfra Text Embedding 0.6Bkinfra-text-embedding-0.6b	33K	$0.07 / 1M input tokens
Kinfra Text Embedding 4Bkinfra-text-embedding-4b	33K	$0.084 / 1M input tokens

AtlasCloud

5 models

AtlasCloud models, with the list price and the Cloakray price for each.
Model	Context	Input
KLING v3.0kling-v3-0	2K	$0.084–$0.42 / second
KLING v3.0 Prokling-v3-0-pro	2K	$0.112–$0.168 / second
KLING v3.0 Turbokling-v3-0-turbo	2K	$0.168–$0.21 / second
VEED Fabric 1.0veed-fabric-1-0	2K	$0.088–$0.165 / second
VEED Fabric 1.0 Fastveed-fabric-1-0-fast	2K	$0.11–$0.22 / second

Inclusionai

2 models

Inclusionai models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Ling 3.0 Flashling-3.0-flash	262K	$0.06	$0.012	$0.18
Ling 3.0 Flash VLling-3.0-flash-vl	131K	$0.06	$0.012	$0.18

Meta models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Llama 3.1 70B Instructllama-3.1-70b-instruct	128K	$0.792	Price not published	$0.792
Llama 3.2 11B Instructllama-3.2-11b-instruct	128K	$0.07	Price not published	$0.33
Llama 3.3 70B Instructllama-3.3-70b-instruct	131K	$0.13	Price not published	$0.4
Llama 4 Maverick 17B Instructllama-4-maverick-17b-instruct	8K	$0.264	Price not published	$1.067
Llama 4 Scout 17B Instructllama-4-scout-17b-instruct	8K	$0.187	Price not published	$0.726
Muse Glimmer 30Bmuse-glimmer-30b	131K	$0.3	$0.04	$1.2
Muse Image 1.0muse-image-1.0	—	$0.01 / image · Default
Muse Spark 1.1muse-spark-1.1	1.0M	$1.25	$0.15	$4.25
Muse Spark 1.2muse-spark-1.2	1.0M	$1.25	$0.15	$4.25
Muse Spark 1.2 Contributormuse-spark-1.2-contributor	1.0M	$0.1	$0.002	$0.2
Muse Spark 1.3muse-spark-1.3	1.0M	$1.25	$0.15	$4.25
Muse Spark 1.3 Contributormuse-spark-1.3-contributor	1.0M	$0.1	$0.002	$0.2
Muse Wonder 1.0muse-wonder-1.0	1.0M	$4	$0.2	$20

Microsoft

1 model

Microsoft models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Microsoft-Decision-1microsoft-decision-1	33K	$0.042 / 1M input tokens

Xiaomi

2 models

Xiaomi models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
MiMo V2.6 Flashmimo-v2.6-flash	1M	$0.14	$0.0028	$0.28
MiMo V2.6 Promimo-v2.6-pro	1M	$0.435	$0.0036	$0.87

NVIDIA

1 model

NVIDIA models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Nemotron 3 Ultra 550Bnemotron-3-ultra-550b	262K	$0.5	$0.1	$2.2

Perplexity

3 models

Perplexity models, with the list price and the Cloakray price for each.
Model	Context	Input
Perplexity Searchperplexity-search	—	$0.005 / request
Perplexity Search Fastperplexity-search-fast	—	$0.001 / request
Sonarsonar	130K	$0.25 / 1M input tokens · $2.5 / 1M output tokens · See all rates on the model page Temporarily unavailable

Qwen3.8 27B

1 model

Qwen3.8 27B models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Qwen3.8 27BQwen3.8-27B	262K	Price not published Availability not yet verified

Reka

1 model

Reka models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Reka Edge 2603reka-edge-2603	16K	Price not published Availability not yet verified

Stepfun

2 models

Stepfun models, with the list price and the Cloakray price for each.
Model	Context	Input	Cached input	Output
Step 3.7 Flashstep-3.7-flash	262K	$0.2	$0.04	$1.15
Step 5 Previewstep-5-preview	1M	$1 Availability not yet verified	$0.1	$2.7

Four things you never get charged for

No seats: Invite the whole team. You pay for tokens, not headcount.
No commitment: Nothing renews. Top up when you want to, as much as you want to.
No minimum: Spend $5 this month and $5,000 the next. There is no minimum to meet before the rates apply.
No gateway fee: Nothing is added on top of the model rate, whether you send one request or a million.

Questions worth answering

Is it the same model I'd get direct?: Yes. Same model, same version, same answers. The only thing that changes is what it costs you.
Do you charge gateway fees?: No. You pay the rate shown for the model you called, and nothing is added on top of it. Seats, projects, and API keys are free, and there's no tier to reach before that applies.
Do you offer volume discounts?: Yes. If you spend steadily every month, contact us with your expected usage and the models you rely on, and we will offer a discount that applies to your whole workspace on top of 0% gateway fees.
Are failed requests charged?: Requests rejected before generation are not charged. If generation starts, any billable usage is charged even if the request later fails or is interrupted. No gateway fees are added.
Why is cached input cheaper?: Providers price input they have already seen well below fresh input, and that price is passed straight through. Workloads that reuse a long system prompt or a big document pay noticeably less than the input column suggests.
What happens when my balance runs out?: Requests stop rather than silently overspending. Turn on auto top-up in the console and your balance refills before that happens.
Do I get an invoice?: Every top-up produces a receipt, and the console breaks spend down by project, key, and model so you can see where it went.

Start with no gateway fees

Create a key, top up, and your very next request is billed at the rate on this page.

Get your API key Browse the models

Pay for tokens. That's the whole bill.

Pay as you go

0%gateway fees

Sending serious volume? Pay less per token.

Every model, every price

Anthropic

OpenAI

Google

DeepSeek

Z.ai

Moonshot AI

Alibaba

MiniMax

ByteDance

Baai

Mistral

ElevenLabs

Black Forest Labs

Sakana AI

Ibm

xAI

Tencent Cloud

TypeSafe AI

Kinfra

AtlasCloud

Inclusionai

Meta

Microsoft

Xiaomi

NVIDIA

Perplexity

Qwen3.8 27B

Reka

Stepfun

Four things you never get charged for

Questions worth answering

Start with no gateway fees