Model Registry

Majestix model cards

A product-facing registry for the Majestix lineup. Compare pricing, context, output limits, fit, benchmarks, and existing swarm usage without leaving the app shell.

Visible cards
44
Anthropic

Claude Haiku 4.5

claude-haiku

Claude Haiku 4.5 is a fast model in the Majestix lineup built for fast, efficient, general workloads, with 200K context and $1.20 / $5.25 per 1M tokens.

Guru+fast$1.20 / $5.25
Context
200K
Max Output
64K
FastEfficientGeneralChat
7 swarm templates use thisOpen card
Anthropic

Claude Opus 4.6

claude-opus

Claude Opus 4.6 is a reasoning model in the Majestix lineup built for reasoning, coding, analysis workloads, with 200K context and $6.00 / $26.25 per 1M tokens.

Guru+reasoning$6.00 / $26.25
Context
200K
Max Output
128K
ReasoningCodingAnalysisCreative Writing
No public swarm templates pinnedOpen card
Anthropic

Claude Sonnet 4.6

claude-sonnet

Claude Sonnet 4.6 is a flagship model in the Majestix lineup built for reasoning, writing, analysis workloads, with 200K context and $3.60 / $15.75 per 1M tokens.

Guru+flagship$3.60 / $15.75
Context
200K
Max Output
64K
ReasoningWritingAnalysisCoding
7 swarm templates use thisOpen card
DeepSeek

DeepSeek R1

deepseek-r1

DeepSeek R1 is a reasoning model in the Majestix lineup built for reasoning, math, coding workloads, with 64K context and $0.84 / $2.62 per 1M tokens.

Guru+reasoning$0.84 / $2.62
Context
64K
Max Output
32K
ReasoningMathCodingStep By Step
No public swarm templates pinnedOpen card
DeepSeek

DeepSeek V3.2

deepseek-v3.2

DeepSeek V3.2 is a flagship model in the Majestix lineup built for reasoning, coding, math workloads, with 163K context and $0.31 / $0.60 per 1M tokens.

Guru+flagship$0.31 / $0.60
Context
163K
Max Output
65K
ReasoningCodingMathAnalysis
No public swarm templates pinnedOpen card
Google

Gemini 2.5 Flash

gemini-2.5-flash

Gemini 2.5 Flash is a fast model in the Majestix lineup built for fast, general, multimodal workloads, with 1M context and $0.36 / $2.62 per 1M tokens.

Guru+fast$0.36 / $2.62
Context
1M
Max Output
65K
FastGeneralMultimodalChat
No public swarm templates pinnedOpen card
Google

Gemini 2.5 Pro

gemini-2.5-pro

Gemini 2.5 Pro is a reasoning model in the Majestix lineup built for reasoning, multimodal, analysis workloads, with 1M context and $1.50 / $10.50 per 1M tokens.

Guru+reasoning$1.50 / $10.50
Context
1M
Max Output
65K
ReasoningMultimodalAnalysisLong Context
No public swarm templates pinnedOpen card
Google

Gemini 3 Flash

gemini-3-flash

Gemini 3 Flash is a fast model in the Majestix lineup built for fast, multimodal, general workloads, with 1M context and $0.60 / $3.15 per 1M tokens.

Guru+fast$0.60 / $3.15
Context
1M
Max Output
64K
FastMultimodalGeneralChat
No public swarm templates pinnedOpen card
Google

Gemini 3 Pro Image

gemini-3-image

Gemini 3 Pro Image is a image model in the Majestix lineup built for image generation, image editing, text rendering workloads, with 65K context and $2.40 / $12.60 per 1M tokens.

Guru+image$2.40 / $12.60
Context
65K
Max Output
8K
Image GenerationImage EditingText RenderingPhotorealism
No public swarm templates pinnedOpen card
Google

Gemini 3.1 Pro

gemini-3.1-pro

Gemini 3.1 Pro is a reasoning model in the Majestix lineup built for reasoning, multimodal, analysis workloads, with 1M context and $2.40 / $12.60 per 1M tokens.

Guru+reasoning$2.40 / $12.60
Context
1M
Max Output
65K
ReasoningMultimodalAnalysisLong Context
No public swarm templates pinnedOpen card
Google

Gemma 3 27B

gemma-3-27b

Gemma 3 27B is a vision model in the Majestix lineup built for vision, multimodal, reasoning workloads, with 131K context and $0.15 / $0.60 per 1M tokens.

Free Tiervision$0.15 / $0.60
Context
131K
Max Output
32K
VisionMultimodalReasoningGeneral
No public swarm templates pinnedOpen card
Google

Gemma 4 31B

gemma-4-31b

Gemma 4 31B is a vision model in the Majestix lineup built for vision, multimodal, reasoning workloads, with 256K context and $0.15 / $0.60 per 1M tokens.

Guru+vision$0.15 / $0.60
Context
256K
Max Output
32K
VisionMultimodalReasoningGeneral
No public swarm templates pinnedOpen card
OpenAI

GPT-5 Image

gpt-5-image

GPT-5 Image is a image model in the Majestix lineup built for image generation, photorealism, creative workloads, with 400K context and $12.00 / $10.50 per 1M tokens.

Guru+image$12.00 / $10.50
Context
400K
Max Output
32K
Image GenerationPhotorealismCreativeText Rendering
No public swarm templates pinnedOpen card
OpenAI

GPT-5 Mini

gpt-5-mini

GPT-5 Mini is a fast model in the Majestix lineup built for fast, general, coding workloads, with 400K context and $0.30 / $2.10 per 1M tokens.

Guru+fast$0.30 / $2.10
Context
400K
Max Output
100K
FastGeneralCodingChat
No public swarm templates pinnedOpen card
OpenAI

GPT-5.3

gpt-5.3

GPT-5.3 is a flagship model in the Majestix lineup built for flagship, general, analysis workloads, with 128K context and $2.10 / $14.70 per 1M tokens.

Guru+flagship$2.10 / $14.70
Context
128K
Max Output
32K
FlagshipGeneralAnalysisReasoning
No public swarm templates pinnedOpen card
OpenAI

GPT-5.3 Codex

gpt-5.3-codex

GPT-5.3 Codex is a flagship model in the Majestix lineup built for coding, agentic, debugging workloads, with 400K context and $2.10 / $14.70 per 1M tokens.

Guru+flagship$2.10 / $14.70
Context
400K
Max Output
32K
CodingAgenticDebuggingTool Use
No public swarm templates pinnedOpen card
OpenAI

GPT-5.4

gpt-5.4

GPT-5.4 is a flagship model in the Majestix lineup built for flagship, reasoning, analysis workloads, with 1.05M context and $3.00 / $15.75 per 1M tokens.

Guru+flagship$3.00 / $15.75
Context
1.05M
Max Output
100K
FlagshipReasoningAnalysisLong Context
No public swarm templates pinnedOpen card
OpenAI

GPT-5.4 Mini

gpt-5.4-mini

GPT-5.4 Mini is a fast model in the Majestix lineup built for fast, reasoning, general workloads, with 400K context and $0.90 / $4.73 per 1M tokens.

Guru+fast$0.90 / $4.73
Context
400K
Max Output
100K
FastReasoningGeneralCoding
No public swarm templates pinnedOpen card
OpenAI

GPT-5.4 Nano

gpt-5.4-nano

GPT-5.4 Nano is a fast model in the Majestix lineup built for fast, efficient, general workloads, with 400K context and $0.24 / $1.31 per 1M tokens.

Guru+fast$0.24 / $1.31
Context
400K
Max Output
100K
FastEfficientGeneralChat
No public swarm templates pinnedOpen card
OpenAI

GPT-OSS 120B

gpt-oss-120b

GPT-OSS 120B is a flagship model in the Majestix lineup built for reasoning, coding, general workloads, with 131K context and $0.15 / $0.60 per 1M tokens.

Free Tierflagship$0.15 / $0.60
Context
131K
Max Output
32K
ReasoningCodingGeneralMultilingual
No public swarm templates pinnedOpen card
xAI

Grok 4.1 Fast

grok-4.1-fast

Grok 4.1 Fast is a flagship model in the Majestix lineup built for web research, agentic, long context workloads, with 2M context and $0.24 / $0.60 per 1M tokens.

Guru+flagship$0.24 / $0.60
Context
2M
Max Output
131K
Web ResearchAgenticLong ContextGeneral
6 swarm templates use thisOpen card
xAI

Grok 4.20

grok-4.20

Grok 4.20 is a reasoning model in the Majestix lineup built for reasoning, web research, analysis workloads, with 2M context and $2.40 / $6.30 per 1M tokens.

Guru+reasoning$2.40 / $6.30
Context
2M
Max Output
131K
ReasoningWeb ResearchAnalysisLong Context
4 swarm templates use thisOpen card
OpenRouter

Healer Alpha

healer-alpha

Healer Alpha is a flagship model in the Majestix lineup built for agentic, vision, reasoning workloads, with 262K context and $0.15 / $0.60 per 1M tokens.

Guru+flagship$0.15 / $0.60
Context
262K
Max Output
65K
AgenticVisionReasoningGeneral
No public swarm templates pinnedOpen card
OpenRouter

Hunter Alpha

hunter-alpha

Hunter Alpha is a flagship model in the Majestix lineup built for agentic, planning, long context workloads, with 1M context and $0.15 / $0.60 per 1M tokens.

Free Tierflagship$0.15 / $0.60
Context
1M
Max Output
131K
AgenticPlanningLong ContextGeneral
No public swarm templates pinnedOpen card
Moonshot AI

Kimi K2.5

kimi-k2.5

Kimi K2.5 is a flagship model in the Majestix lineup built for agentic, coding, multimodal workloads, with 262K context and $0.54 / $2.62 per 1M tokens.

Guru+flagship$0.54 / $2.62
Context
262K
Max Output
131K
AgenticCodingMultimodalLong Context
No public swarm templates pinnedOpen card
Moonshot AI

Kimi K2.6

kimi-k2.6

Kimi K2.6 is a flagship model in the Majestix lineup built for agentic, coding, multimodal workloads, with 262K context and $0.95 / $4.00 per 1M tokens.

Guru+flagship$0.95 / $4.00
Context
262K
Max Output
131K
AgenticCodingMultimodalSwarm Orchestration
No public swarm templates pinnedOpen card
Meta

Llama 3.3 70B

llama-3.3-70b

Llama 3.3 70B is a flagship model in the Majestix lineup built for general, coding, reasoning workloads, with 128K context and $0.15 / $0.60 per 1M tokens.

Free Tierflagship$0.15 / $0.60
Context
128K
Max Output
32K
GeneralCodingReasoningMultilingual
12 swarm templates use thisOpen card
Meta

Llama 4 Maverick

llama-4-maverick

Llama 4 Maverick is a flagship model in the Majestix lineup built for long context, general, coding workloads, with 1M context and $0.18 / $0.63 per 1M tokens.

Guru+flagship$0.18 / $0.63
Context
1M
Max Output
65K
Long ContextGeneralCodingMultimodal
17 swarm templates use thisOpen card
MiMo

MiMo V2 Flash

mimo-v2-flash

MiMo V2 Flash is a fast model in the Majestix lineup built for fast, general, reasoning workloads, with 262K context and $0.15 / $0.60 per 1M tokens.

Guru+fast$0.15 / $0.60
Context
262K
Max Output
65K
FastGeneralReasoningChat
No public swarm templates pinnedOpen card
MiniMax

MiniMax M2.5

minimax-m2.5

MiniMax M2.5 is a coding model in the Majestix lineup built for coding, agentic, tool use workloads, with 128K context and $0.32 / $1.00 per 1M tokens.

Guru+coding$0.32 / $1.00
Context
128K
Max Output
32K
CodingAgenticTool UseReasoning
No public swarm templates pinnedOpen card
MiniMax

MiniMax M2.7

minimax-m2.7

MiniMax M2.7 is a flagship model in the Majestix lineup built for flagship, coding, reasoning workloads, with 204K context and $0.36 / $1.26 per 1M tokens.

Guru+flagship$0.36 / $1.26
Context
204K
Max Output
65K
FlagshipCodingReasoningGeneral
2 swarm templates use thisOpen card
Mistral

Mistral Small 4

mistral-small

Mistral Small 4 is a fast model in the Majestix lineup built for fast, general, coding workloads, with 262K context and $0.18 / $0.63 per 1M tokens.

Guru+fast$0.18 / $0.63
Context
262K
Max Output
65K
FastGeneralCodingMultimodal
No public swarm templates pinnedOpen card
Google

Nano Banana 2

nano-banana-2

Nano Banana 2 is a image model in the Majestix lineup built for image generation, image editing, creative workloads, with 65K context and $0.60 / $3.15 per 1M tokens.

Guru+image$0.60 / $3.15
Context
65K
Max Output
8K
Image GenerationImage EditingCreativeIteration
No public swarm templates pinnedOpen card
NVIDIA

Nemotron 3 Nano 30B

nemotron-30b

Nemotron 3 Nano 30B is a flagship model in the Majestix lineup built for agentic, classification, reasoning workloads, with 256K context and $0.15 / $0.60 per 1M tokens.

Free Tierflagship$0.15 / $0.60
Context
256K
Max Output
32K
AgenticClassificationReasoningFast
2 swarm templates use thisOpen card
NVIDIA

Nemotron 3 Super 120B

nemotron-super-120b

Nemotron 3 Super 120B is a flagship model in the Majestix lineup built for agentic, reasoning, tool use workloads, with 262K context and $0.15 / $0.60 per 1M tokens.

Free Tierflagship$0.15 / $0.60
Context
262K
Max Output
32K
AgenticReasoningTool UseGeneral
4 swarm templates use thisOpen card
NVIDIA

Nemotron 70B

nemotron-70b

Nemotron 70B is a flagship model in the Majestix lineup built for reasoning, analysis, general workloads, with 131K context and $1.44 / $1.26 per 1M tokens.

Free Tierflagship$1.44 / $1.26
Context
131K
Max Output
32K
ReasoningAnalysisGeneralLong Context
No public swarm templates pinnedOpen card
NVIDIA

Nemotron Nano 12B VL

nemotron-12b-vl

Nemotron Nano 12B VL is a vision model in the Majestix lineup built for vision, documents, ocr workloads, with 128K context and $0.24 / $0.63 per 1M tokens.

Free Tiervision$0.24 / $0.63
Context
128K
Max Output
32K
VisionDocumentsOcrGeneral
No public swarm templates pinnedOpen card
Qwen

Qwen3 Coder 480B

qwen3-coder

Qwen3 Coder 480B is a flagship model in the Majestix lineup built for coding, agentic, tool use workloads, with 262K context and $0.26 / $1.05 per 1M tokens.

Guru+flagship$0.26 / $1.05
Context
262K
Max Output
65K
CodingAgenticTool UseReasoning
No public swarm templates pinnedOpen card
Qwen

Qwen3 Coder 480B

qwen3-coder-free

Qwen3 Coder 480B is a flagship model in the Majestix lineup built for coding, agentic, tool use workloads, with 262K context and $0.48 / $1.68 per 1M tokens.

Free Tierflagship$0.48 / $1.68
Context
262K
Max Output
65K
CodingAgenticTool UseReasoning
No public swarm templates pinnedOpen card
Qwen

Qwen3 Next 80B

qwen3-next-80b

Qwen3 Next 80B is a flagship model in the Majestix lineup built for reasoning, general, tool use workloads, with 262K context and $0.15 / $1.16 per 1M tokens.

Free Tierflagship$0.15 / $1.16
Context
262K
Max Output
65K
ReasoningGeneralTool UseLong Context
No public swarm templates pinnedOpen card
Qwen

Qwen3.5 397B

qwen3.5-397b

Qwen3.5 397B is a flagship model in the Majestix lineup built for reasoning, coding, general workloads, with 262K context and $0.47 / $2.46 per 1M tokens.

Guru+flagship$0.47 / $2.46
Context
262K
Max Output
65K
ReasoningCodingGeneralMultilingual
No public swarm templates pinnedOpen card
Majestix

Qwen3.5 Custom

qwen3.5-35b

Qwen3.5 Custom is a flagship model in the Majestix lineup built for marketing, coding, fast workloads, with 262K context and $0.17 / $1.00 per 1M tokens.

Free (/freechat)flagship$0.17 / $1.00
Context
262K
Max Output
262K
MarketingCodingFastGeneral
11 swarm templates use thisOpen card
ByteDance

Seed 2.0 Mini

seed-2.0-mini

Seed 2.0 Mini is a fast model in the Majestix lineup built for fast, general, creative workloads, with 262K context and $0.15 / $0.60 per 1M tokens.

Guru+fast$0.15 / $0.60
Context
262K
Max Output
65K
FastGeneralCreativeChat
No public swarm templates pinnedOpen card
ByteDance

Seedream 4.5

seedream-4.5

Seedream 4.5 is a image model in the Majestix lineup built for image generation, photorealism, text rendering workloads, with 4K context and roughly 42 credits per image.

Guru+image~42 cr / image
Context
4K
Max Output
4K
Image GenerationPhotorealismText RenderingAds
No public swarm templates pinnedOpen card