Live model catalog

Loading models…

Fetching current ScaleMax availability and prices.

Live model catalog

Models and pricing

Browse every model by maker. Click an API ID to copy it. Rates are what ScaleMax charges per 1M tokens today.

Public catalog · no sign-in required

All models

Grouped by who makes the model. Other versions of a model (ids ending in -v2, -v3, -new or -preview) are folded under it. Claude ids ending in [1m] are the same model with the full 1M-token context — use either id. A limited-access label means the model is listed for comparison but cannot be bought through checkout.

Jump to a model

Show index

Anthropic

Claude Haiku 4.5 20251001
Claude Haiku 5.5
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.8
Claude Opus 5
Claude Opus 5.5
Claude Sonnet 5
Claude Sonnet 5.5
Sonnet 4.6
Fable 5
Fable 5.1

OpenAI

GPT-5.6 Luna
GPT-5.6 Sol
GPT-5.6 Terra
GPT-6.1 Sol
GPT-6.1 Terra
GPT-6 astra
GPT-6 Luna
GPT-6 Sol

GLM

GLM 5.3 (v2)
GLM 5.2 v2
GLM 5.3 Flash
GLM 5
GLM 5.1

Gemini

Gemini 3.1 Flash Lite (Preview)
Gemini 3.5 Flash Lite
Gemini 3.8 Flash
Gemini 3 Flash (Preview)

Grok

Grok 4.5
Grok 4.6
Grok 4.7

DeepSeek

DeepSeek V4 Flash
DeepSeek V4 Pro
DeepSeek V3.2
DeepSeek V4.1 Flash

Qwen

Qwen 3.7 Flash
Qwen 3.8 27B
Qwen 3.8 Flash
Qwen 3.7 Max
Qwen 3.8 Max

Kimi

Kimi K2.7 Code
Kimi K2.6
Kimi K3

MiniMax

MiniMax M3
MiniMax M2.5
MiniMax M2.7

More models

Muse Spark 1.2
Hunyuan 3
Hunyuan 4
MiMo V2.5 Pro
Jev 1.13 (Free)

Embeddings

Text Embedding 3 Small
Text Embedding 3 Large
Text Embedding Ada 002

Image generation

Grok Imagine Image
Grok Imagine Image Quality
ScaleMax Image 1.5
ScaleMax Image 2
ScaleMax Image 2.5 Flare
ScaleMax Image 2.5 Sunburst
Gemini 3.1 Flash Image

Video generation

Grok Imagine Video
Grok Imagine Video 1.5

Browse by family

Grouped by who makes the model. A family with no match for your search or task is dimmed.

Choose by task

Guidance comes from the live catalog, published rates, and model names—not hidden benchmarks.

“Lower published rate” compares the current input and output rates. “Fast responses” is based on model naming and should be tested for your workload. Task filters apply to text models; embedding, image and video models are hidden while one is active.

Showing every active model. Limits and capabilities come from the current catalog record.

Anthropic

Claude and Fable models for coding, agents and long-form reasoning.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Claude Haiku 4.5 20251001 API ID · click to copy Build & codeFast responseLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $1.00 Output $5.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 8 2026, 13:01 UTC
Display name Claude Haiku 5.5 API ID · click to copy Build & codeFast responseLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $0.20 Output $1.00	Context 1,000,000 Max output 128,000 Input Text Output Text	Chat Tools Vision Reasoning Streaming Prompt caching	At or above 100000 input tokens Input $1.00 Output $5.00	RefreshedOct 17 2026, 19:02 UTC
Display name Claude Opus 4.6 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $5.00 Output $25.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 8 2026, 13:01 UTC
Display name Claude Opus 4.7 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $5.00 Output $25.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 8 2026, 13:01 UTC
Display name Claude Opus 4.8 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $5.00 Output $25.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 8 2026, 13:01 UTC
Display name Claude Opus 5 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $5.00 Output $25.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Reasoning Streaming Prompt caching Image input	No separate long-context rate published	RefreshedJul 30 2026, 11:23 UTC
Display name Claude Opus 5.5 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $5.00 Output $25.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Reasoning Streaming Prompt caching Image input	No separate long-context rate published	RefreshedJul 30 2026, 11:23 UTC
Display name Claude Sonnet 5 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $2.00 Output $10.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 8 2026, 13:01 UTC
Display name Claude Sonnet 5.5 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $2.00 Output $10.00	Context 1,000,000 Max output 128,000 Input Text Output Text	Chat Tools Vision Reasoning Streaming Prompt caching	No separate long-context rate published	RefreshedOct 1 2026, 06:12 UTC
Display name Sonnet 4.6 API ID · click to copy Build & codeLong context	Anthropic	Chat CompletionsOpenAI-compatible	Input $0.44 Output $1.32	Context 1,000,000 Max output 384,000 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedSep 2 2026, 03:00 UTC
Display name Fable 5 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $10.00 Output $50.00	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Tools Vision Streaming Prompt caching Image input	No separate long-context rate published	RefreshedJul 30 2026, 11:23 UTC
Display name Fable 5.1 API ID · click to copy Build & codeLong context	Anthropic	Chat Completions + MessagesOpenAI & Anthropic-compatible	Input $10.00 Output $50.00	Context 1,000,000 Max output 128,000 Input Text, Image Output Text	Tools Vision Streaming Prompt caching Image input	No separate long-context rate published	RefreshedSep 12 2026, 03:20 UTC

Claude Haiku 4.5 20251001

$1.00 in · $5.00 out per 1M · 1,000,000 context

Build & codeFast responseLong context

Details

Family: Anthropic
API surface: Chat Completions + Messages
Input: Text, Image
Output: Text
Context: 1,000,000
Max output: 128,000
Catalog refreshed: Aug 8 2026, 13:01 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Claude Haiku 5.5

$0.20 in · $1.00 out per 1M · 1,000,000 context

Build & codeFast responseLong context

Details

Family: Anthropic
API surface: Chat Completions + Messages
Input: Text
Output: Text
Context: 1,000,000
Max output: 128,000
Catalog refreshed: Oct 17 2026, 19:02 UTC

Catalog-declared features

Chat
Tools
Vision
Reasoning
Streaming
Prompt caching

Long-context pricing

At or above 100000 input tokens

Input: $1.00
Output: $5.00

Claude Opus 4.6

$5.00 in · $25.00 out per 1M · 1,000,000 context

Build & codeLong context

Details

Family: Anthropic
API surface: Chat Completions + Messages
Input: Text, Image
Output: Text
Context: 1,000,000
Max output: 128,000
Catalog refreshed: Aug 8 2026, 13:01 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

OpenAI

GPT and Codex models, plus the open-weight GPT OSS.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name GPT-5.6 Luna API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $0.522 Output $3.132	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Tools Vision Responses API Streaming Prompt caching Image input	No separate long-context rate published	RefreshedJul 9 2026, 23:26 UTC
Display name GPT-5.6 Sol API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $5.00 Output $30.00	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Tools Vision Streaming Prompt caching Image input	At or above 272000 input tokens Input $10.00 Output $45.00	RefreshedJul 29 2026, 08:03 UTC
Display name GPT-5.6 Terra API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $2.00 Output $12.00	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Tools Vision Responses API Streaming Prompt caching Image input	At or above 272000 input tokens Input $4.00 Output $18.00	RefreshedJul 9 2026, 23:26 UTC
Display name GPT-6.1 Sol API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $2.00 Output $10.00	Context 1,050,000 Max output 128,000 Input Text Output Text	Chat Tools Vision Streaming Prompt caching	No separate long-context rate published	RefreshedOct 1 2026, 06:12 UTC
Display name GPT-6.1 Terra API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $1.00 Output $5.00	Context 1,050,000 Max output 128,000 Input Text Output Text	Chat Tools Vision Streaming Prompt caching	No separate long-context rate published	RefreshedOct 27 2026, 05:04 UTC
Display name GPT-6 astra API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $15.00 Output $60.00	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedSep 5 2026, 10:38 UTC
Display name GPT-6 Luna API ID · click to copy Build & codeLower published rateLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $0.10 Output $0.50	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Responses API Streaming Prompt caching Image input	No separate long-context rate published	RefreshedSep 23 2026, 15:25 UTC
Display name GPT-6 Sol API ID · click to copy Build & codeLong context	OpenAI	Chat CompletionsOpenAI-compatible	Input $2.00 Output $10.00	Context 1,050,000 Max output 128,000 Input Text, Image Output Text	Chat Tools Vision Streaming Prompt caching Image input	No separate long-context rate published	RefreshedSep 23 2026, 15:25 UTC

GPT-5.6 Luna

$0.522 in · $3.132 out per 1M · 1,050,000 context

Build & codeLong context

Details

Family: OpenAI
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Jul 9 2026, 23:26 UTC

Catalog-declared features

Tools
Vision
Responses API
Streaming
Prompt caching
Image input

Long-context pricing

No separate long-context rate published

GPT-5.6 Sol

$5.00 in · $30.00 out per 1M · 1,050,000 context

Build & codeLong context

Details

Family: OpenAI
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Jul 29 2026, 08:03 UTC

Catalog-declared features

Tools
Vision
Streaming
Prompt caching
Image input

Long-context pricing

At or above 272000 input tokens

Input: $10.00
Output: $45.00

GPT-5.6 Terra

$2.00 in · $12.00 out per 1M · 1,050,000 context

Build & codeLong context

Details

Family: OpenAI
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,050,000
Max output: 128,000
Catalog refreshed: Jul 9 2026, 23:26 UTC

Catalog-declared features

Tools
Vision
Responses API
Streaming
Prompt caching
Image input

Long-context pricing

At or above 272000 input tokens

Input: $4.00
Output: $18.00

GLM

Zhipu GLM models for coding and general chat.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name GLM 5.3 Flash API ID · click to copy Build & codeFast responseLong context 2 other versions GLM 5.3 Flash (v2) $0.1875 in · $0.625 out GLM 5.3 Flash v3 $0.1875 in · $0.625 out	GLM	Chat CompletionsOpenAI-compatible	Input $0.1875 Output $0.625	Context 1,048,576 Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 26 2026, 21:29 UTC
Display name GLM 5.3 (v2) API ID · click to copy Build & code	GLM	Chat CompletionsOpenAI-compatible	Input $1.75 Output $5.50	Context Limit unavailable Max output Limit unavailable Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedSep 4 2026, 04:15 UTC
Display name GLM 5.2 v2 API ID · click to copy Build & code	GLM	Chat CompletionsOpenAI-compatible	Input $1.75 Output $5.50	Context Limit unavailable Max output Limit unavailable Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedAug 22 2026, 11:47 UTC
Display name GLM 5 API ID · click to copy Build & codeLong context	GLM	Chat CompletionsOpenAI-compatible	Input $1.925 Output $3.828	Context 200,000 Max output 128,000 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedAug 23 2026, 08:06 UTC
Display name GLM 5.1 API ID · click to copy Build & codeLong context	GLM	Chat CompletionsOpenAI-compatible	Input $1.925 Output $3.828	Context 200,000 Max output 128,000 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedSep 25 2026, 05:13 UTC

GLM 5.3 Flash

$0.1875 in · $0.625 out per 1M · 1,048,576 context

Build & codeFast responseLong context

2 other versions

GLM 5.3 Flash (v2)
$0.1875 in · $0.625 out
GLM 5.3 Flash v3
$0.1875 in · $0.625 out

Details

Family: GLM
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,048,576
Max output: Limit unavailable
Catalog refreshed: Aug 26 2026, 21:29 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

GLM 5.3 (v2)

$1.75 in · $5.50 out per 1M

Build & code

Details

Family: GLM
API surface: Chat Completions
Input: Text
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Sep 4 2026, 04:15 UTC

Catalog-declared features

Chat
Tools
Streaming

Long-context pricing

No separate long-context rate published

GLM 5.2 v2

$1.75 in · $5.50 out per 1M

Build & code

Details

Family: GLM
API surface: Chat Completions
Input: Text
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 22 2026, 11:47 UTC

Catalog-declared features

Chat
Tools
Streaming

Long-context pricing

No separate long-context rate published

Gemini

Google Gemini Flash and Flash Lite models.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Gemini 3.1 Flash Lite (Preview) API ID · click to copy Build & codeFast responseLong context	Gemini	Chat CompletionsOpenAI-compatible	Input $0.25 Output $1.50	Context 1,050,000 Max output 65,500 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 3 2026, 07:34 UTC
Display name Gemini 3.5 Flash Lite API ID · click to copy Build & codeFast responseLong context	Gemini	Chat CompletionsOpenAI-compatible	Input $0.25 Output $1.50	Context 1,050,000 Max output 65,500 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 3 2026, 07:34 UTC
Display name Gemini 3.8 Flash API ID · click to copy Build & codeFast responseLong context	Gemini	Chat CompletionsOpenAI-compatible	Input $0.75 Output $3.75	Context 1,050,000 Max output 65,500 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedSep 27 2026, 14:03 UTC
Display name Gemini 3 Flash (Preview) API ID · click to copy Build & codeFast responseLong context	Gemini	Chat CompletionsOpenAI-compatible	Input $0.50 Output $3.00	Context 1,050,000 Max output 65,500 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 3 2026, 07:34 UTC

Gemini 3.1 Flash Lite (Preview)

$0.25 in · $1.50 out per 1M · 1,050,000 context

Build & codeFast responseLong context

Details

Family: Gemini
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,050,000
Max output: 65,500
Catalog refreshed: Aug 3 2026, 07:34 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Gemini 3.5 Flash Lite

$0.25 in · $1.50 out per 1M · 1,050,000 context

Build & codeFast responseLong context

Details

Family: Gemini
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,050,000
Max output: 65,500
Catalog refreshed: Aug 3 2026, 07:34 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Gemini 3.8 Flash

$0.75 in · $3.75 out per 1M · 1,050,000 context

Build & codeFast responseLong context

Details

Family: Gemini
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 1,050,000
Max output: 65,500
Catalog refreshed: Sep 27 2026, 14:03 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Grok

xAI Grok models for reasoning and coding.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Grok 4.5 API ID · click to copy Build & codeLong context	Grok	Chat CompletionsOpenAI-compatible	Input $2.00 Output $6.00	Context 500,000 Max output 65,500 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedAug 3 2026, 07:34 UTC
Display name Grok 4.6 API ID · click to copy Build & codeLong context	Grok	Chat CompletionsOpenAI-compatible	Input $2.00 Output $6.00	Context 500,000 Max output 65,500 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	At or above 200000 input tokens Input $4.00 Output $12.00	RefreshedAug 17 2026, 19:50 UTC
Display name Grok 4.7 API ID · click to copy Build & codeLong context	Grok	Chat CompletionsOpenAI-compatible	Input $2.40 Output $7.20	Context 500,000 Max output 65,500 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	At or above 200000 input tokens Input $4.80 Output $14.40	RefreshedOct 4 2026, 19:27 UTC

Grok 4.5

$2.00 in · $6.00 out per 1M · 500,000 context

Build & codeLong context

Details

Family: Grok
API surface: Chat Completions
Input: Text
Output: Text
Context: 500,000
Max output: 65,500
Catalog refreshed: Aug 3 2026, 07:34 UTC

Catalog-declared features

Chat
Tools
Streaming

Long-context pricing

No separate long-context rate published

Grok 4.6

$2.00 in · $6.00 out per 1M · 500,000 context

Build & codeLong context

Details

Family: Grok
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 500,000
Max output: 65,500
Catalog refreshed: Aug 17 2026, 19:50 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

At or above 200000 input tokens

Input: $4.00
Output: $12.00

Grok 4.7

$2.40 in · $7.20 out per 1M · 500,000 context

Build & codeLong context

Details

Family: Grok
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 500,000
Max output: 65,500
Catalog refreshed: Oct 4 2026, 19:27 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

At or above 200000 input tokens

Input: $4.80
Output: $14.40

DeepSeek

DeepSeek V3 and V4 Flash and Pro models.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name DeepSeek V4 Flash API ID · click to copy Build & codeFast responseLower published rateLong context 2 other versions DeepSeek V4 Flash (0731) $3.00 in · $9.00 out · 1,000,000 context DeepSeek V4 Flash New $2.00 in · $5.00 out · 1,000,000 context	DeepSeek	Chat CompletionsOpenAI-compatible	Input $0.19 Output $0.51	Context 1,000,000 Max output 384,000 Input Text Output Text	Chat Tools Reasoning Streaming Prompt caching	No separate long-context rate published	RefreshedJul 30 2026, 08:41 UTC
Display name DeepSeek V4 Pro Limited accessListed for comparison · not available in self-service checkoutAsk about access API ID · click to copy Build & codeLong context	DeepSeek	Chat CompletionsOpenAI-compatible	Input $1.00 Output $4.00	Context 1,000,000 Max output 384,000 Input Text Output Text	Chat Tools Reasoning Streaming	No separate long-context rate published	RefreshedSep 27 2026, 14:03 UTC
Display name DeepSeek V3.2 API ID · click to copy Build & codeLower published rateLong context	DeepSeek	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 200,000 Max output 131,072 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedAug 21 2026, 19:26 UTC
Display name DeepSeek V4.1 Flash API ID · click to copy Build & codeFast responseLong context	DeepSeek	Chat CompletionsOpenAI-compatible	Input $0.30 Output $1.20	Context 1,000,000 Max output 65,536 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedSep 11 2026, 17:08 UTC

DeepSeek V4 Flash

$0.19 in · $0.51 out per 1M · 1,000,000 context

Build & codeFast responseLower published rateLong context

2 other versions

DeepSeek V4 Flash (0731)
$3.00 in · $9.00 out · 1,000,000 context
DeepSeek V4 Flash New
$2.00 in · $5.00 out · 1,000,000 context

Details

Family: DeepSeek
API surface: Chat Completions
Input: Text
Output: Text
Context: 1,000,000
Max output: 384,000
Catalog refreshed: Jul 30 2026, 08:41 UTC

Catalog-declared features

Chat
Tools
Reasoning
Streaming
Prompt caching

Long-context pricing

No separate long-context rate published

DeepSeek V4 Pro

Limited accessListed for comparison · not available in self-service checkoutAsk about access

$1.00 in · $4.00 out per 1M · 1,000,000 context

Build & codeLong context

Details

Family: DeepSeek
API surface: Chat Completions
Input: Text
Output: Text
Context: 1,000,000
Max output: 384,000
Catalog refreshed: Sep 27 2026, 14:03 UTC

Catalog-declared features

Chat
Tools
Reasoning
Streaming

Long-context pricing

No separate long-context rate published

DeepSeek V3.2

$0.20 in · $0.60 out per 1M · 200,000 context

Build & codeLower published rateLong context

Details

Family: DeepSeek
API surface: Chat Completions
Input: Text
Output: Text
Context: 200,000
Max output: 131,072
Catalog refreshed: Aug 21 2026, 19:26 UTC

Catalog-declared features

Chat
Tools
Streaming

Long-context pricing

No separate long-context rate published

Qwen

Qwen Plus, Max and Flash models.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Qwen 3.7 Flash API ID · click to copy Build & codeFast responseLower published rate	Qwen	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 22 2026, 11:47 UTC
Display name Qwen 3.8 27B API ID · click to copy Build & codeLower published rate	Qwen	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 22 2026, 11:47 UTC
Display name Qwen 3.8 Flash API ID · click to copy Build & codeFast responseLower published rate	Qwen	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Responses API Streaming Image input	No separate long-context rate published	RefreshedAug 27 2026, 18:13 UTC
Display name Qwen 3.7 Max API ID · click to copy Build & codeLower published rateLong context	Qwen	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 1,000,000 Max output 65,536 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedSep 25 2026, 05:13 UTC
Display name Qwen 3.8 Max API ID · click to copy Build & codeLong context	Qwen	Chat CompletionsOpenAI-compatible	Input $2.00 Output $6.00	Context 1,000,000 Max output 131,072 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 20 2026, 16:40 UTC

Qwen 3.7 Flash

$0.20 in · $0.60 out per 1M

Build & codeFast responseLower published rate

Details

Family: Qwen
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 22 2026, 11:47 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Qwen 3.8 27B

$0.20 in · $0.60 out per 1M

Build & codeLower published rate

Details

Family: Qwen
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 22 2026, 11:47 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Qwen 3.8 Flash

$0.20 in · $0.60 out per 1M

Build & codeFast responseLower published rate

Details

Family: Qwen
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 27 2026, 18:13 UTC

Catalog-declared features

Chat
Tools
Vision
Responses API
Streaming
Image input

Long-context pricing

No separate long-context rate published

Kimi

Moonshot Kimi models for agentic coding.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Kimi K2.7 Code API ID · click to copy Build & code	Kimi	Chat CompletionsOpenAI-compatible	Input $1.2825 Output $5.40	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 22 2026, 11:47 UTC
Display name Kimi K2.6 API ID · click to copy Build & codeLower published rateLong context	Kimi	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 262,144 Max output 262,144 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 21 2026, 19:26 UTC
Display name Kimi K3 API ID · click to copy Build & codeLower published rateLong context	Kimi	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 200,000 Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedSep 25 2026, 05:13 UTC

Kimi K2.7 Code

$1.2825 in · $5.40 out per 1M

Build & code

Details

Family: Kimi
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 22 2026, 11:47 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Kimi K2.6

$0.20 in · $0.60 out per 1M · 262,144 context

Build & codeLower published rateLong context

Details

Family: Kimi
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 262,144
Max output: 262,144
Catalog refreshed: Aug 21 2026, 19:26 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Kimi K3

$0.20 in · $0.60 out per 1M · 200,000 context

Build & codeLower published rateLong context

Details

Family: Kimi
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 200,000
Max output: Limit unavailable
Catalog refreshed: Sep 25 2026, 05:13 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

MiniMax

MiniMax M-series models.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name MiniMax M3 API ID · click to copy Build & codeFast responseLower published rate	MiniMax	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 22 2026, 11:47 UTC
Display name MiniMax M2.5 API ID · click to copy Build & codeFast responseLower published rateLong context	MiniMax	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 200,000 Max output 131,072 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedAug 21 2026, 19:26 UTC
Display name MiniMax M2.7 API ID · click to copy Build & codeFast responseLower published rateLong context	MiniMax	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 204,800 Max output 131,072 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 21 2026, 19:26 UTC

MiniMax M3

$0.20 in · $0.60 out per 1M

Build & codeFast responseLower published rate

Details

Family: MiniMax
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 22 2026, 11:47 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

MiniMax M2.5

$0.20 in · $0.60 out per 1M · 200,000 context

Build & codeFast responseLower published rateLong context

Details

Family: MiniMax
API surface: Chat Completions
Input: Text
Output: Text
Context: 200,000
Max output: 131,072
Catalog refreshed: Aug 21 2026, 19:26 UTC

Catalog-declared features

Chat
Tools
Streaming

Long-context pricing

No separate long-context rate published

MiniMax M2.7

$0.20 in · $0.60 out per 1M · 204,800 context

Build & codeFast responseLower published rateLong context

Details

Family: MiniMax
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 204,800
Max output: 131,072
Catalog refreshed: Aug 21 2026, 19:26 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

More models

Hunyuan, MiMo, Mistral, Nemotron, LongCat, Step and other makers.

Active ScaleMax models with production planning fields and prices per one million tokens
Model	Family	API surface	Standard price / 1M	Planning limits	Catalog-declared features	Long context	Catalog record
Display name Hunyuan 4 API ID · click to copy Build & codeLower published rate 1 other version Hunyuan 4 Preview $3.00 in · $6.00 out	More models	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedSep 27 2026, 14:03 UTC
Display name Muse Spark 1.2 API ID · click to copy Build & codeFast responseLower published rate	More models	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context Limit unavailable Max output Limit unavailable Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 22 2026, 11:47 UTC
Display name Hunyuan 3 API ID · click to copy Build & codeLower published rateLong context	More models	Chat CompletionsOpenAI-compatible	Input $0.20 Output $0.60	Context 200,000 Max output 131,072 Input Text, Image Output Text	Chat Tools Vision Streaming Image input	No separate long-context rate published	RefreshedAug 21 2026, 19:26 UTC
Display name MiMo V2.5 Pro API ID · click to copy Build & codeLower published rateLong context	More models	Chat CompletionsOpenAI-compatible	Input $0.14 Output $0.28	Context 1,048,576 Max output 131,072 Input Text Output Text	Chat Tools Streaming	No separate long-context rate published	RefreshedAug 23 2026, 08:06 UTC
Display name Jev 1.13 (Free) API ID · click to copy Lower published rate	More models	Chat CompletionsOpenAI-compatible	Input $0.00 Output $0.00	Context 32,768 Max output 2,048 Input Text Output Json	Json output	No separate long-context rate published	RefreshedOct 8 2026, 05:47 UTC

Hunyuan 4

$0.20 in · $0.60 out per 1M

Build & codeLower published rate

1 other version

Hunyuan 4 Preview
$3.00 in · $6.00 out

Details

Family: More models
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Sep 27 2026, 14:03 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Muse Spark 1.2

$0.20 in · $0.60 out per 1M

Build & codeFast responseLower published rate

Details

Family: More models
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: Limit unavailable
Max output: Limit unavailable
Catalog refreshed: Aug 22 2026, 11:47 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Hunyuan 3

$0.20 in · $0.60 out per 1M · 200,000 context

Build & codeLower published rateLong context

Details

Family: More models
API surface: Chat Completions
Input: Text, Image
Output: Text
Context: 200,000
Max output: 131,072
Catalog refreshed: Aug 21 2026, 19:26 UTC

Catalog-declared features

Chat
Tools
Vision
Streaming
Image input

Long-context pricing

No separate long-context rate published

Embeddings

Vectors for search, retrieval and clustering. Billed per 1M input tokens; output is free. Call POST /v1/embeddings with a string or up to 2,048 strings per request; dimensions and encoding_format: "base64" are supported. Credit keys pay the rate shown; OpenAI and combined token packs are debited at the same dollar value.

curl https://api.scalemax.pro/v1/embeddings \
  -H "Authorization: Bearer $SCALEMAX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"text-embedding-3-small","input":"hello"}'

Text Embedding 3 Small

$0.02 / 1M tokens

Dimensions: 1,536 · shortenable
Max input: 8,191 tokens per input
Output: $0 · vectors only

Text Embedding 3 Large

$0.13 / 1M tokens

Dimensions: 3,072 · shortenable
Max input: 8,191 tokens per input
Output: $0 · vectors only

Text Embedding Ada 002

$0.10 / 1M tokens

Dimensions: 1,536
Max input: 8,191 tokens per input
Output: $0 · vectors only

Image generation

Priced for image generation with the published image-model rates; token keys use the platform dollar-to-token conversion. Call POST /v1/images/generations with the model id below.

Grok Imagine Image

$0.009–$0.317 / image

grok-imagine-image

Sizes: 1:1, 16:9, 9:16, 4:3 +4
Quality: low, medium, high
Images per call: 4

Grok Imagine Image Quality

$0.009–$0.317 / image

grok-imagine-image-quality

Sizes: 1:1, 16:9, 9:16, 4:3 +4
Quality: low, medium, high
Images per call: 4

ScaleMax Image 1.5

$0.014–$0.2 / image

gpt-image-1.5

Sizes: 1024x1024, 1536x1024, 1024x1536
Quality: low, medium, high
Images per call: 1

ScaleMax Image 2

$0.015–$0.2 / image

gpt-image-2

Sizes: 1024x1024, 1536x864, 864x1536
Quality: low, medium, high
Images per call: 1

ScaleMax Image 2.5 Flare

$0.03–$0.2 / image

gpt-image-2.5-flare

Sizes: 1024x1024, 1536x864, 864x1536
Quality: low, medium, high
Images per call: 1

ScaleMax Image 2.5 Sunburst

$0.03–$0.2 / image

gpt-image-2.5-sunburst

Sizes: 1024x1024, 1536x864, 864x1536
Quality: low, medium, high
Images per call: 1

Gemini 3.1 Flash Image

$0.075–$0.2 / image

gemini-3.1-flash-image

Sizes: 1024x1024, 1536x1024, 1024x1536, 1792x1024
Quality: low, medium, high
Images per call: 1

Claude, OpenAI, combined, Gemini, GLM, Local and Qwen token packs get every published image model and every published video model. Auto API and Voice keys cannot.

Video generation

Priced per clip by length and resolution: 480p costs 0.7x, 1080p 1.6x the 720p rate. Call POST /v1/videos/generations with the model id below, then poll GET /v1/videos/:id.

Grok Imagine Video

from $0.175 · 175,000 tokens / 6 s at 480p

grok-imagine-video

Text-to-video and image-to-video. 480p and 720p. Edit supported. 1080p and extend are not available on this model.

Duration: 1–15s
Aspect: 1:1, 16:9, 9:16, 4:3, 3:4
Resolution: 480p, 720p
Per second · 480p: $0.0292 · 29,167 tokens
Per second · 720p: $0.0417 · 41,667 tokens

Grok Imagine Video 1.5

from $0.263 · 262,500 tokens / 6 s at 480p

grok-imagine-video-1.5

Text-to-video and image-to-video. 480p, 720p, and 1080p. Edit and extend are not available on this model.

Duration: 1–15s
Aspect: 1:1, 16:9, 9:16, 4:3, 3:4
Resolution: 480p, 720p, 1080p
Per second · 480p: $0.0438 · 43,750 tokens
Per second · 720p: $0.0625 · 62,500 tokens
Per second · 1080p: $0.1 · 100,000 tokens

All models

Jump to a model

Browse by family

Choose by task

Anthropic

Claude Haiku 4.5 20251001

Catalog-declared features

Long-context pricing

Claude Haiku 5.5

Catalog-declared features

Long-context pricing

Claude Opus 4.6

Catalog-declared features

Long-context pricing

Claude Opus 4.7

Catalog-declared features

Long-context pricing

Claude Opus 4.8

Catalog-declared features

Long-context pricing

Claude Opus 5

Catalog-declared features

Long-context pricing

Claude Opus 5.5

Catalog-declared features

Long-context pricing

Claude Sonnet 5

Catalog-declared features

Long-context pricing

Claude Sonnet 5.5

Catalog-declared features

Long-context pricing

Sonnet 4.6

Catalog-declared features

Long-context pricing

Fable 5

Catalog-declared features

Long-context pricing

Fable 5.1

Catalog-declared features

Long-context pricing

OpenAI

GPT-5.6 Luna

Catalog-declared features

Long-context pricing

GPT-5.6 Sol

Catalog-declared features

Long-context pricing

GPT-5.6 Terra

Catalog-declared features

Long-context pricing

GPT-6.1 Sol

Catalog-declared features

Long-context pricing

GPT-6.1 Terra

Catalog-declared features

Long-context pricing

GPT-6 astra

Catalog-declared features

Long-context pricing

GPT-6 Luna

Catalog-declared features

Long-context pricing

GPT-6 Sol

Catalog-declared features

Long-context pricing

GLM

GLM 5.3 Flash

Catalog-declared features

Long-context pricing

GLM 5.3 (v2)

Catalog-declared features

Long-context pricing

GLM 5.2 v2

Catalog-declared features

Long-context pricing

GLM 5

Catalog-declared features

Long-context pricing

GLM 5.1