Skip to main content

ScaleMax models

Pick the right model for the job.

Browse every model by maker. Copy the exact API ID into your app or coding tool.

Open live model catalogRead the model guide

All models

Every model, by who makes it.

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. Which models your key can call depends on what you bought; GET /v1/models with your key lists exactly those. Select a model name for its pricing examples, code samples and client setup.

Anthropic

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

Sonnet 4.6

Local Models packTools
claude-sonnet-4-6

Fast general-purpose model with tool calling, sold in the Local Models pack

Context
1,000,000 tokens
Input / 1M
$0.44
Output / 1M
$1.32

Claude Haiku 4.5

Image inputToolsReasoning
claude-haiku-4-5-20251001

Fast Anthropic model for low-latency chat and everyday work

Context
1,000,000 tokens
Input / 1M
$1
Output / 1M
$5

Claude Haiku 5.5

Image inputTools
claude-haiku-5-5

Latest fast Anthropic model for low-latency chat and high-volume work

Context
1,000,000 tokens
Input / 1M
$0.20
Output / 1M
$1

Claude Opus 4.6

Image inputToolsReasoning
claude-opus-4-6

High-capability Anthropic reasoning model for complex work

Context
1,000,000 tokens
Input / 1M
$5
Output / 1M
$25

Claude Opus 4.7

Image inputToolsReasoning
claude-opus-4-7

High-capability Anthropic model for advanced coding and reasoning

Context
1,000,000 tokens
Input / 1M
$5
Output / 1M
$25

Claude Opus 4.8

Image inputToolsReasoning
claude-opus-4-8

Premium Anthropic model for deep analysis and demanding tasks

Context
1,000,000 tokens
Input / 1M
$5
Output / 1M
$25

Claude Opus 5

Image inputToolsReasoning
claude-opus-5

Premium Anthropic model for advanced coding, agents, and deep reasoning

Context
1,000,000 tokens
Input / 1M
$5
Output / 1M
$25

Claude Opus 5.5

Image inputToolsReasoning
claude-opus-5-5

Latest premium Anthropic model for advanced coding, agents, and deep reasoning

Context
1,000,000 tokens
Input / 1M
$5
Output / 1M
$25

Claude Sonnet 5

Image inputTools
claude-sonnet-5

Balanced Anthropic model for strong reasoning and production workflows

Context
1,000,000 tokens
Input / 1M
$2
Output / 1M
$10

Claude Sonnet 5.5

Image inputTools
claude-sonnet-5-5

Latest balanced Anthropic model for strong reasoning and production workflows

Context
1,000,000 tokens
Input / 1M
$2
Output / 1M
$10

Fable 5.1

Image inputTools
fable-5.1

Newer Anthropic-family Fable model through ScaleMax

Context
1,000,000 tokens
Input / 1M
$10
Output / 1M
$50

OpenAI

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

GPT OSS 120B

Local Models packToolsReasoning
gpt-oss-120b
Input / 1M
$0.15
Output / 1M
$0.60

Codex Auto Review

Image inputToolsReasoning
codex-auto-review
Context
272,000 tokens
Input / 1M
$0
Output / 1M
$0

GPT-5.6 Luna

Image inputToolsReasoning
gpt-5.6-luna

Low-cost GPT model for quick tasks and checks

Context
1,050,000 tokens
Input / 1M
$0.522
Output / 1M
$3.132

GPT-5.6 Sol

Image inputToolsReasoning
gpt-5.6-sol
Context
1,050,000 tokens
Input / 1M
$5
Output / 1M
$30

GPT-5.6 Terra

Image inputToolsReasoning
gpt-5.6-terra
Context
1,050,000 tokens
Input / 1M
$2
Output / 1M
$12

GPT-6.1 Sol

Image inputToolsReasoning
gpt-6.1-sol
Context
1,050,000 tokens
Input / 1M
$2
Output / 1M
$10

GPT-6.1 Terra

Image inputToolsReasoning
gpt-6.1-terra
Context
1,050,000 tokens
Input / 1M
$1
Output / 1M
$5

GPT-6 astra

Image inputToolsReasoning
gpt-6-astra
Context
1,050,000 tokens
Input / 1M
$15
Output / 1M
$60

GPT-6 Luna

Image inputToolsReasoning
gpt-6-luna
Context
1,050,000 tokens
Input / 1M
$0.10
Output / 1M
$0.50

GPT-6 Sol

Image inputToolsReasoning
gpt-6-sol
Context
1,050,000 tokens
Input / 1M
$2
Output / 1M
$10

GLM

Zhipu GLM models for coding and general chat.

GLM 5.3 Flash

Local Models packImage inputToolsReasoning
glm-5.3-flash
2 other versions

  • GLM 5.3 Flash (v2)

    glm-5.3-flash-v2$0.1875 in · $0.625 out

  • GLM 5.3 Flash v3

    glm-5.3-flash-v3$0.1875 in · $0.625 out
Context
1,048,576 tokens
Input / 1M
$0.1875
Output / 1M
$0.625

GLM 5.3 (v2)

Local Models packToolsReasoning
glm-5.3-v2
Input / 1M
$1.75
Output / 1M
$5.50

GLM 5.2 v2

Local Models packToolsReasoning
glm-5.2-v2
Input / 1M
$1.75
Output / 1M
$5.50

GLM 5.1

Local Models packToolsReasoning
glm-5.1
Context
200,000 tokens
Input / 1M
$1.925
Output / 1M
$3.828

Gemini

Google Gemini Flash and Flash Lite models.

Gemini 3.1 Flash Lite Preview

Local Models packImage inputTools
gemini-3.1-flash-lite-preview

Preview lightweight general-purpose model for high-volume work

Context
1,050,000 tokens
Input / 1M
$0.25
Output / 1M
$1.50

Gemini 3.5 Flash Lite

Local Models packImage inputTools
gemini-3.5-flash-lite

Lightweight general-purpose model for high-volume work, sold in the Local Models pack

Context
1,050,000 tokens
Input / 1M
$0.25
Output / 1M
$1.50

Gemini 3.8 Flash

Local Models packImage inputTools
gemini-3.8-flash

Fast general-purpose model with tool calling, sold in the Local Models pack

Context
1,050,000 tokens
Input / 1M
$0.75
Output / 1M
$3.75

Gemini 3 Flash Preview

Local Models packImage inputTools
gemini-3-flash-preview

Preview general-purpose model tuned for fast responses

Context
1,050,000 tokens
Input / 1M
$0.50
Output / 1M
$3

Gemini 4 Argon

Image inputTools
gemini-4-argon
Context
1,048,576 tokens
Input / 1M
$8
Output / 1M
$40

Grok

xAI Grok models for reasoning and coding.

Grok 4.5

Local Models packToolsReasoning
grok-4.5

General-purpose model for reasoning, coding, and everyday assistance

Context
500,000 tokens
Input / 1M
$2
Output / 1M
$6

Grok 4.6

Local Models packImage inputToolsReasoning
grok-4.6

Latest general-purpose model for reasoning, coding, and everyday assistance

Context
500,000 tokens
Input / 1M
$2
Output / 1M
$6

Grok 4.7

Image inputToolsReasoning
grok-4.7
Context
500,000 tokens
Input / 1M
$2.40
Output / 1M
$7.20

DeepSeek

DeepSeek V3 and V4 Flash and Pro models.

DeepSeek V4 Flash

Local Models packToolsReasoning
deepseek-v4-flash

Fast general-purpose model for everyday coding and chat

Context
1,000,000 tokens
Input / 1M
$0.19
Output / 1M
$0.51

DeepSeek V4 Pro

Local Models packToolsReasoning
deepseek-v4-pro

High-capability general-purpose model for demanding reasoning and coding

Context
1,000,000 tokens
Input / 1M
$1
Output / 1M
$4

DeepSeek V4.1 Flash

Image inputToolsReasoning
deepseek-v4.1-flash
Context
1,000,000 tokens
Input / 1M
$0.30
Output / 1M
$1.20

Qwen

Qwen Plus, Max and Flash models.

Qwen 3.7 Flash

Local Models packImage inputToolsReasoning
qwen-3.7-flash
Input / 1M
$0.20
Output / 1M
$0.60

Qwen 3.8 27B

Local Models packImage inputToolsReasoning
qwen-3.8-27b
Input / 1M
$0.20
Output / 1M
$0.60

Qwen 3.8 Flash

Local Models packImage inputToolsReasoning
qwen3.8-flash
Input / 1M
$0.20
Output / 1M
$0.60

Qwen 3.7 Max

Local Models packImage inputToolsReasoning
qwen-3.7-max
Context
1,000,000 tokens
Input / 1M
$0.20
Output / 1M
$0.60

Qwen 3.8 Max

Local Models packImage inputTools
qwen3.8-max
Context
1,000,000 tokens
Input / 1M
$2
Output / 1M
$6

Kimi

Moonshot Kimi models for agentic coding.

Kimi K2.7 Code

Local Models packImage inputToolsReasoning
kimi-k2.7-code
Input / 1M
$1.2825
Output / 1M
$5.40

Kimi K2.6

Local Models packImage inputToolsReasoning
kimi-k2.6

Long-context general-purpose model for extended conversations and large codebases

Context
262,144 tokens
Input / 1M
$0.20
Output / 1M
$0.60

Kimi K3

Local Models packImage inputToolsReasoning
kimi-k3
Context
200,000 tokens
Input / 1M
$0.20
Output / 1M
$0.60

Kimi K3.1 Pro

Image inputTools
kimi-k3.1-pro
Context
200,000 tokens
Input / 1M
$4
Output / 1M
$20

MiniMax

MiniMax M-series models.

MiniMax M3

Local Models packImage inputToolsReasoning
minimax-m3
Input / 1M
$0.20
Output / 1M
$0.60

MiniMax M2.5

Local Models packToolsReasoning
minimax-m2.5

General-purpose model for reasoning and coding

Context
200,000 tokens
Input / 1M
$0.20
Output / 1M
$0.60

MiniMax M2.7

Local Models packImage inputToolsReasoning
minimax-m2.7

Latest general-purpose model for reasoning and coding

Context
204,800 tokens
Input / 1M
$0.20
Output / 1M
$0.60

More models

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

Hunyuan 4

Local Models packImage inputToolsReasoning
hy4

Reasoning model with tool calling, sold in the Local Models pack

1 other version

  • Hunyuan 4 Preview

    hy4-preview$3 in · $6 out
Input / 1M
$0.20
Output / 1M
$0.60

Muse Spark 1.2

Local Models packImage inputToolsReasoning
muse-spark-1.2
Input / 1M
$0.20
Output / 1M
$0.60

Hunyuan 3

Local Models packImage inputToolsReasoning
hunyuan-3

General-purpose model for reasoning and everyday coding

Context
200,000 tokens
Input / 1M
$0.20
Output / 1M
$0.60

Embeddings

Text embedding models billed per input token on /v1/embeddings.

Text Embedding 3 Small

text-embedding-3-small

Text embeddings

Context
8,191 tokens
Input / 1M
$0.02
Output / 1M
$0

Text Embedding 3 Large

text-embedding-3-large

Text embeddings

Context
8,191 tokens
Input / 1M
$0.13
Output / 1M
$0

Text Embedding Ada 002

text-embedding-ada-002

Text embeddings

Context
8,191 tokens
Input / 1M
$0.10
Output / 1M
$0

Image generation

Text-to-image models billed per image on /v1/images/generations.

Gemini 3.1 Flash Image

gemini-3.1-flash-image
Per image
$0.075–$0.20
4 sizes
1024x1024, 1536x1024, 1024x1536, 1792x1024
Images per call
1

ScaleMax Image 1.5

gpt-image-1.5
Per image
$0.014–$0.20
3 sizes
1024x1024, 1536x1024, 1024x1536
Images per call
1

ScaleMax Image 2

gpt-image-2
Per image
$0.015–$0.20
3 sizes
1024x1024, 1536x864, 864x1536
Images per call
1

ScaleMax Image 2.5 Flare

gpt-image-2.5-flare
Per image
$0.03–$0.20
3 sizes
1024x1024, 1536x864, 864x1536
Images per call
1

ScaleMax Image 2.5 Sunburst

gpt-image-2.5-sunburst
Per image
$0.03–$0.20
3 sizes
1024x1024, 1536x864, 864x1536
Images per call
1

ScaleMax Image 2.6

gpt-image-2.6
Per image
$0.03–$0.20
3 sizes
1024x1024, 1536x864, 864x1536
Images per call
1

ScaleMax Image 2.6 Flare

gpt-image-2.6-flare
Per image
$0.03–$0.20
3 sizes
1024x1024, 1536x864, 864x1536
Images per call
1

ScaleMax Image 2.6 Sunburst

gpt-image-2.6-sunburst
Per image
$0.03–$0.20
3 sizes
1024x1024, 1536x864, 864x1536
Images per call
1

Grok Imagine Image

grok-imagine-image
Per image
$0.009–$0.317
8 sizes
1:1, 16:9, 9:16, 4:3 +4
Images per call
4

Grok Imagine Image 2.0

grok-imagine-image-2.0
Per image
$0.018–$0.633
8 sizes
1:1, 16:9, 9:16, 4:3 +4
Images per call
4

Grok Imagine Image Quality

grok-imagine-image-quality
Per image
$0.018–$0.633
8 sizes
1:1, 16:9, 9:16, 4:3 +4
Images per call
4

Video generation

Text- and image-to-video models billed per video on /v1/videos/generations.

Grok Imagine Video

Text or image to video
grok-imagine-video
Per 6 s at 720p
$0.25
Resolutions
480p, 720p
Aspect ratios
1:1, 16:9, 9:16, 4:3 +1

Grok Imagine Video 1.5

Text or image to video
grok-imagine-video-1.5
Per 6 s at 720p
$0.375
Resolutions
480p, 720p, 1080p
Aspect ratios
1:1, 16:9, 9:16, 4:3 +1

Grok Imagine Video 1.5 Lite

Text or image to video
grok-imagine-video-1.5-lite
Per 6 s at 720p
$0.10
Resolutions
480p, 720p
Aspect ratios
1:1, 16:9, 9:16, 4:3 +1

See what your key can use.

Sign in to see every model your key can call, with its exact ID, limits and current rate.

Check current models