Scale plan

Price: from $99 a month (sizes)
Usage: Up to $400 of usage a month on the $99 size*
5-hour limit: 30% of the month’s usage
Weekly limit: 60% of the month’s usage
Models: 127, listed below

* Based on DeepSeek V4.1 Flash 1017, with cached input counted at its normal input price. Real usage depends on the model, context and caching. The month’s usage renews with each billing cycle and doesn’t carry over. At 100% of a limit, requests pause until it resets; with extra usage on, they carry on using purchased credit. See Usage limits. Subscribe or upgrade on the pricing page. An upgrade applies at once, for the prorated difference; a downgrade at your next renewal. See Payment methods.

Sizes

Scale comes in 4 sizes. Every size has the same models and the same 5-hour and weekly shares of its month.

Price a month	Usage a month*
$99	Up to $400
$199	Up to $800
$499	Up to $2,000
$999	Up to $4,000

Models included

Scale has the same 127 models as Max, with more usage a month. Prices are list prices in US dollars per 1M tokens. A dash under Cached input means the model has no cached-input discount: cached input costs the input price.

Anthropic

Model	Context	Input	Cached input	Output
Claude Opus 5.5 `opus-5.5`	1M	$4	$0.2	$20
Claude Sonnet 5.5 `sonnet-5.5`	1M	$2	$0.2	$10
Claude Haiku 5.5 `haiku-5.5`	100K	$0.1	$0.01	$0.5

OpenAI

Model	Context	Input	Cached input	Output
GPT-6 Astra `gpt-6-astra`	272K	$10	$1	$50
GPT-6.1 Sol `gpt-6.1-sol`	272K	$2	$0.1	$10
GPT-6 Sol `gpt-6-sol`	272K	$2	$0.2	$10
GPT-5.6 Sol `gpt-5.6-sol`	272K	$5	$0.5	$30
GPT-5.5 `gpt-5.5`	272K	$5	$0.5	$30
GPT-6.1 Terra `gpt-6.1-terra`	272K	$1	$0.05	$5
GPT-5 Codex `gpt-5-codex`	400K	$1.25	$0.125	$10
GPT-5.6 Terra `gpt-5.6-terra`	272K	$2	$0.2	$12
GPT-5.4 `gpt-5.4`	272K	$2.5	$0.25	$15
GPT-5.3 Codex `gpt-5.3-codex`	400K	$1.75	$0.175	$14
GPT-5.2 `gpt-5.2`	400K	$1.75	$0.175	$14
GPT-5.2 Codex `gpt-5.2-codex`	400K	$1.75	$0.175	$14
GPT-5.1 `gpt-5.1`	400K	$1.25	$0.125	$10
GPT-5.1 Codex Max `gpt-5.1-codex-max`	400K	$1.25	$0.125	$10
GPT-5.1 Codex `gpt-5.1-codex`	400K	$1.25	$0.125	$10
GPT-5 `gpt-5`	400K	$1.25	$0.125	$10
GPT-5.4 mini `gpt-5.4-mini`	400K	$0.75	$0.075	$4.5
GPT-6 Luna `gpt-6-luna`	272K	$0.1	$0.01	$0.5
GPT-5.6 Luna `gpt-5.6-luna`	272K	$0.2	$0.02	$1.2
GPT-5.1 Codex mini `gpt-5.1-codex-mini`	400K	$0.25	$0.025	$2
GPT Chat (latest) `gpt-chat-latest`	200K	$5	$0.5	$30
GPT-5 mini `gpt-5-mini`	400K	$0.25	$0.025	$2
GPT-5.4 nano `gpt-5.4-nano`	400K	$0.2	$0.02	$1.25
GPT-4.1 `gpt-4.1`	1.05M	$2	$0.5	$8
GPT-5 nano `gpt-5-nano`	400K	$0.05	$0.005	$0.4
GPT-OSS 120B `@sdn/gpt-oss-120b`	128K	$0.35	—	$0.75
GPT-4.1 mini `gpt-4.1-mini`	1.05M	$0.4	$0.1	$1.6
GPT-OSS Safeguard 120B `@sdn/gpt-oss-safeguard-120b`	128K	$0.15	—	$0.6
GPT-4.1 nano `gpt-4.1-nano`	1.05M	$0.1	$0.025	$0.4
GPT-OSS Safeguard 20B `@sdn/gpt-oss-safeguard-20b`	128K	$0.07	—	$0.2
GPT-OSS 20B `@sdn/gpt-oss-20b`	128K	$0.2	—	$0.3

gpt-chat-latest retires on Dec 2, 2026.

Moonshot AI

Model	Context	Input	Cached input	Output
Kimi K3.1 Pro `@sdn/kimi-k3.1-pro`	1.05M	$2	$0.2	$10
Kimi K3 `@sdn/kimi-k3`	1M	$3	$0.3	$15
Kimi K2.7 Code `@sdn/kimi-k2.7-code`	131K	$0.95	$0.19	$4
Kimi K2.6 `@sdn/kimi-k2.6`	262K	$0.95	$0.16	$4
Kimi K2.5 `@sdn/kimi-k2.5`	262K	$0.6	—	$3
Kimi K2 Thinking `@sdn/kimi-k2-thinking`	262K	$0.6	—	$2.5

Z.ai

Model	Context	Input	Cached input	Output
GLM 5.3 `@sdn/glm-5.3`	1M	$1.4	$0.26	$4.4
GLM 5.2 `@sdn/glm-5.2`	131K	$1.4	$0.26	$4.4
GLM 5.3 Flash `@sdn/glm-5.3-flash`	1M	$0.15	$0.03	$0.5
GLM 5.3 Flash Ultra Fast `@sdn/glm-5.3-flash-ultra-fast`	1M	$0.3	$0.06	$1
GLM 5 `@sdn/glm-5`	200K	$1	—	$3.2
GLM 4.7 `@sdn/glm-4.7`	200K	$0.6	—	$2.2
GLM 4.6 `@sdn/glm-4.6`	200K	$0.6	—	$2.2
GLM 4.7 Flash `@sdn/glm-4.7-flash`	131K	$0.0605	—	$0.4

@sdn/glm-5.3-flash-ultra-fast is 50% off at launch, from Nov 8, 2026, 17:00 UTC until Nov 15, 2026, 17:00 UTC. The table shows its list price, which applies after.

DeepSeek

Model	Context	Input	Cached input	Output
DeepSeek V4 Pro `@sdn/deepseek-v4-pro`	1M	$1.32	$0.044	$3.96
DeepSeek V4 Flash `@sdn/deepseek-v4-flash`	1M	$0.44	$0.014	$1.32
DeepSeek V4.1 Flash 1017 `@sdn/deepseek-v4.1-flash-1017`	1M	$0.3	$0.006	$1.2
DeepSeek V4.1 Flash Ultra Fast `@sdn/deepseek-v4.1-flash-ultra-fast`	1M	$0.6	$0.012	$2.4
DeepSeek V3.2 `@sdn/deepseek-v3.2`	131K	$0.57	$0.114	$1.71
DeepSeek V3.1 `@sdn/deepseek-v3.1`	164K	$0.58	—	$1.68
DeepSeek R1 `@sdn/deepseek-r1`	128K	$1.35	—	$5.4

@sdn/deepseek-v4.1-flash-ultra-fast is 50% off at launch, from Nov 8, 2026, 17:00 UTC until Nov 15, 2026, 17:00 UTC. The table shows its list price, which applies after.

xAI

Model	Context	Input	Cached input	Output
Grok 4.7 `grok-4.7`	200K	$2	$0.5	$6
Grok 4.6 `grok-4.6`	500K	$2	$0.5	$6
Grok 4.3 `grok-4.3`	1M	$1.25	$0.2	$2.5
Grok 4 `grok-4`	256K	$3	—	$15
Grok 4.20 `grok-4.20`	2M	$1.25	—	$2.5
Grok 4.20 (non-reasoning) `grok-4.20-non-reasoning`	2M	$1.25	—	$2.5
Grok 4.1 Fast `grok-4.1-fast`	2M	$0.2	—	$0.5

Model	Context	Input	Cached input	Output
Muse Spark 1.3 `muse-spark-1.3`	1.05M	$1.25	$0.15	$4.25
Muse Spark 1.3 Contributor `muse-spark-1.3-contributor`	1.05M	$0.1	$0.002	$0.2
Llama 4 Maverick `@sdn/llama-4-maverick`	1M	$0.24	—	$0.97
Llama 3.3 70B `@sdn/llama-3.3-70b`	128K	$0.72	—	$0.72
Llama 3.1 70B `@sdn/llama-3.1-70b`	128K	$0.72	—	$0.72
Llama 3.2 11B Vision `@sdn/llama-3.2-11b-vision`	128K	$0.049	—	$0.676
Llama 4 Scout `@sdn/llama-4-scout`	3.5M	$0.17	—	$0.66
Llama 3.2 3B `@sdn/llama-3.2-3b`	80K	$0.051	—	$0.335
Llama 3 70B `@sdn/llama-3-70b`	8K	$2.65	—	$3.5
Llama 3.1 8B `@sdn/llama-3.1-8b`	128K	$0.22	—	$0.22
Llama 3.2 1B `@sdn/llama-3.2-1b`	60K	$0.027	—	$0.201
Llama 3 8B `@sdn/llama-3-8b`	8K	$0.3	—	$0.6

Alibaba Qwen

Model	Context	Input	Cached input	Output
Qwen3 Coder 480B `@sdn/qwen3-coder-480b`	131K	$0.45	$0.045	$1.8
Qwen3 235B `@sdn/qwen3-235b`	262K	$0.22	$0.022	$0.88
Qwen 3.8 27B `@sdn/qwen3.8-27b`	262K	$0.45	—	$3.2
Qwen3 Coder Next `@sdn/qwen3-coder-next`	262K	$0.5	—	$1.2
Qwen3 VL 235B `@sdn/qwen3-vl-235b`	262K	$0.3	—	$1.5
Qwen3 Next 80B `@sdn/qwen3-next-80b`	262K	$0.14	—	$1.2
Qwen3 Coder 30B `@sdn/qwen3-coder-30b`	262K	$0.15	—	$0.6
Qwen3 30B A3B `@sdn/qwen3-30b-a3b`	33K	$0.051	—	$0.335
Qwen3 32B `@sdn/qwen3-32b`	16K	$0.15	—	$0.6
Qwen2.5 Coder 32B `@sdn/qwen2.5-coder-32b`	33K	$0.66	—	$1

Cohere

Model	Context	Input	Cached input	Output
Command A `@sdn/command-a`	256K	$2.5	—	$10

MiniMax

Model	Context	Input	Cached input	Output
MiniMax M3.1 Flash `@sdn/minimax-m3.1-flash`	300K	$0.15	$0.015	$0.6
MiniMax M2.5 `@sdn/minimax-m2.5`	197K	$0.3	—	$1.2
MiniMax M2.1 `@sdn/minimax-m2.1`	205K	$0.3	—	$1.2
MiniMax M2 `@sdn/minimax-m2`	205K	$0.3	—	$1.2

Sarvam

Model	Context	Input	Cached input	Output
Sarvam 105B `@sdn/sarvam-105b`	128K	$0.18	$0.06	$0.7
Sarvam 105B Conversations `sarvam-105b-conversations`	32K	$0.18	$0.06	$0.7

Mistral AI

Model	Context	Input	Cached input	Output
Mistral Medium 3.5 `mistral-medium-3.5`	256K	$1.5	—	$7.5
Devstral 2 123B `@sdn/devstral-2-123b`	262K	$0.4	—	$2
Mistral Large 3 675B `@sdn/mistral-large-3-675b`	262K	$0.5	—	$1.5
Magistral Small `@sdn/magistral-small`	128K	$0.5	—	$1.5
Mistral Small 3.1 `@sdn/mistral-small-3.1`	131K	$0.351	—	$0.555
Pixtral Large `@sdn/pixtral-large`	128K	$2	—	$6
Mistral Large 24.02 `@sdn/mistral-large-2402`	33K	$4	—	$12
Ministral 14B `@sdn/ministral-14b`	128K	$0.2	—	$0.2
Mistral Small `@sdn/mistral-small`	33K	$1	—	$3
Ministral 8B `@sdn/ministral-8b`	128K	$0.15	—	$0.15
Ministral 3B `@sdn/ministral-3b`	256K	$0.1	—	$0.1

NVIDIA

Model	Context	Input	Cached input	Output
Nemotron 3 120B `@sdn/nemotron-3-120b`	256K	$0.5	—	$1.5
Nemotron Super 3 120B `@sdn/nemotron-super-3-120b`	262K	$0.15	—	$0.65
Nemotron Nano 3 30B `@sdn/nemotron-nano-3-30b`	262K	$0.06	—	$0.24
Nemotron Nano 12B `@sdn/nemotron-nano-12b`	128K	$0.2	—	$0.6

Microsoft

Model	Context	Input	Cached input	Output
Phi-4 `@sdn/phi-4`	16K	$0.125	—	$0.5
Phi-4 mini `@sdn/phi-4-mini`	131K	$0.075	—	$0.3

Google

Model	Context	Input	Cached input	Output
Gemma 4 26B `@sdn/gemma-4-26b`	256K	$0.1	—	$0.3
Gemma 3 27B `@sdn/gemma-3-27b`	203K	$0.12	—	$0.2
Gemma 3 12B `@sdn/gemma-3-12b`	131K	$0.05	—	$0.1
Gemma 3 4B `@sdn/gemma-3-4b`	128K	$0.04	—	$0.08

Amazon

Model	Context	Input	Cached input	Output
Nova Pro `nova-pro`	300K	$0.8	$0.2	$3.2
Nova 2 Lite `nova-2-lite`	128K	$0.33	—	$2.75
Nova Lite `nova-lite`	300K	$0.06	$0.015	$0.24
Nova Micro `nova-micro`	128K	$0.035	$0.0088	$0.14

Writer

Model	Context	Input	Cached input	Output
Palmyra X5 `palmyra-x5`	1M	$0.6	—	$6
Palmyra X4 `palmyra-x4`	123K	$2.5	—	$10

AI Singapore

Model	Context	Input	Cached input	Output
Gemma Sea Lion v4 27B `@sdn/gemma-sea-lion-v4-27b`	128K	$0.351	—	$0.555

IBM

Model	Context	Input	Cached input	Output
Granite 4.0 H Micro `@sdn/granite-4.0-h-micro`	131K	$0.017	—	$0.112

Embedding models

Text in, vectors out (Embeddings). They have no output price.

Model	Max input	Dimensions	Input
Qwen3 Embedding 0.6B `@sdn/qwen3-embed-0.6b`	8K	1,024	$0.02
BGE-M3 `@sdn/bge-m3`	8K	1,024	$0.02
BGE Large EN v1.5 `@sdn/bge-large-en`	1K	1,024	$0.21
EmbeddingGemma 300M `@sdn/embed-gemma-300m`	2K	768	$0.02
BGE Base EN v1.5 `@sdn/bge-base-en`	1K	768	$0.07
PLaMo Embedding 1B `@sdn/plamo-embed-1b`	4K	2,048	$0.02
BGE Small EN v1.5 `@sdn/bge-small-en`	1K	384	$0.03

Get started

Plans & pricing

Agents

API reference

Guides

Reference