zintus
How it worksFeaturesSupported AIsFAQInstallDownloadPricingDocs
StarOpen app

Catalog

Providers and models Zintus routes to

57 providers · 100 models · 18 free · 22 routable today, 35 planned (not yet routable).

57Providers
100Models
18Free models
10MMax context

100 of 100 models

GPT-OSS 120B

FREE
Groq · gpt-oss
131K contextFree

OpenAI open-weight · free on Groq/OR

Gemma 4 31B

FREE
OpenRouter · gemma
256K contextFree

Multimodal · 140 languages · free

Gemma 4 26B MoE

FREE
OpenRouter · gemma
256K contextFree

Efficient MoE · 3.8B active params

Llama 4 Scout

FREE
OpenRouter · llama4
10M contextFree

10M context · longest free ctx ever

Llama 4 Maverick

FREE
OpenRouter · llama4
1M contextFree

Multimodal · 1M context · free

Llama 3.3 70B

FREE
Groq · llama3
131K contextFree

Most-used free model on OR

DeepSeek R1

FREE
OpenRouter · deepseek
164K contextFree

Best free reasoning model

DeepSeek V3

FREE
OpenRouter · deepseek
164K contextFree

Strong general · free

Qwen3 Coder 480B

FREE
OpenRouter · qwen
262K contextFree

Best free coder globally · Jun 2026

Qwen 2.5 7B

FREE
OpenRouter · qwen
32K contextFree

Lightweight free · classification

Mistral Small

FREE
OpenRouter · mistral
32K contextFree

EU option · free

Nemotron 3 Ultra 550B

FREE
OpenRouter · nemotron
1M contextFree

1M ctx · frontier reasoning · free

Nemotron 3 Super 120B

FREE
OpenRouter · nemotron
1M contextFree

Agentic · 1M ctx · free

GLM-4.5-Air

FREE
OpenRouter · glm
131K contextFree

Chinese/multilingual · free

Poolside Laguna

FREE
OpenRouter · poolside
256K contextFree

Coding agents · free

Owl Alpha

FREE
OpenRouter · owl
131K contextFree

Tool use · agentic · free

MiMo V2.5

FREE
OpenRouter · mimo
131K contextFree

Top OR coding ranking Jun 2026

Phi-4

FREE
OpenRouter · phi
16K contextFree

Microsoft open · tiny but capable

Ministral 3B

T0
Mistral AI · mistral
128K context$0.04 in · $0.04 out / 1M

Cheapest Mistral · equal in/out

Command R7B

T0
Cohere · command
128K context$0.04 in · $0.15 out / 1M

Cheapest first-party RAG model

GPT-OSS 20B

T0
Together AI · gpt-oss
32K context$0.05 in · $0.20 out / 1M

Ultra-cheap OpenAI open model

Llama 3.1 8B Instant

T0
Groq · llama3
128K context$0.05 in · $0.08 out / 1M

Cheapest + fastest · default T0

Nemotron 3 Nano 30B

T0
OpenRouter · nemotron
128K context$0.05 in · $0.10 out / 1M

Edge · tiny MoE · fast

Gemini 1.5 Flash

T0
Google Gemini · gemini
1M context$0.07 in · $0.30 out / 1M

Legacy · still competitive

Nemotron 3 Super 120B

PlannedT0
DeepInfra · nemotron
1M context$0.09 in · $0.45 out / 1M

Cheapest 1M ctx paid model

GPT-4.1 Nano

BYOK
OpenAI · gpt
1M context$0.10 in · $0.40 out / 1M

Cheapest OpenAI · 1M context

Gemini 2.5 Flash Lite

T0
Google Gemini · gemini
1M context$0.10 in · $0.40 out / 1M

Cheapest Google paid

Llama 4 Scout

T0
Together AI · llama4
10M context$0.10 in · $0.30 out / 1M

Cheapest long-context paid option

Mistral 7B

T0
Together AI · mistral
32K context$0.10 in · $0.10 out / 1M

Original · ultra-cheap

Embed v3 English

T0
Cohere · embed
512 context$0.10 in · $0 out / 1M

Best English embeddings

GLM-4 Plus

T0
OpenRouter · glm
128K context$0.10 in · $0.10 out / 1M

Budget GLM · equal in/out pricing

Mistral Nemo

T0
Mistral AI · mistral
131K context$0.13 in · $0.13 out / 1M

Budget EU option

DeepSeek V4 Flash

T0
DeepSeek · deepseek
1M context$0.14 in · $0.28 out / 1M

Best cheap coder · MIT · 1M ctx

Yi Lightning

T0
OpenRouter · yi
16K context$0.14 in · $0.14 out / 1M

Fast · cheap · 01.AI

Llama 4 Maverick

T0
Fireworks AI · llama4
1M context$0.15 in · $0.60 out / 1M

Strong general open model

Command R

T0
Cohere · command
128K context$0.15 in · $0.60 out / 1M

Grounded generation · citations

QwQ 32B

T0
Together AI · qwen
131K context$0.15 in · $0.15 out / 1M

Alibaba reasoning · strong benchmarks

Command Nightly

T0
Cohere · command
128K context$0.15 in · $0.60 out / 1M

Latest Cohere research build

Llama 3.2 11B Vision

T0
Groq · llama3
128K context$0.18 in · $0.18 out / 1M

Vision + text · multimodal T0

SOLAR Pro

T0
OpenRouter · solar
4K context$0.18 in · $0.18 out / 1M

Upstage AI · Korean/English bilingual

Gemma 4 31B (paid)

T0
Together AI · gemma
128K context$0.20 in · $0.20 out / 1M

Equal input/output pricing

DeepSeek V3

T0
DeepSeek · deepseek
164K context$0.20 in · $0.77 out / 1M

Strong general · MIT

Grok 4.1 Fast

T0
xAI (Grok) · grok
2M context$0.20 in · $0.50 out / 1M

2M ctx · cheapest long-context

Sonar Small

T0
Perplexity (Sonar) · sonar
131K context$0.20 in · $0.20 out / 1M

Web-grounded · live citations

Step 3.7 Flash

T0
OpenRouter · step
256K context$0.20 in · $1.15 out / 1M

Fast · multimodal · coding

Jamba 1.6 Mini

T0
OpenRouter · jamba
256K context$0.20 in · $0.40 out / 1M

Hybrid SSM-Transformer · AI21

Gemini 2.5 Flash

T0
Google Gemini · gemini
1M context$0.30 in · $2.50 out / 1M

Fast capable Google

Codestral

T0
Mistral AI · mistral
256K context$0.30 in · $0.90 out / 1M

Code-specialized Mistral

Sonar

T0
Perplexity (Sonar) · sonar
131K context$0.30 in · $0.30 out / 1M

Balanced search-grounded

MiniMax M3

T0
OpenRouter · minimax
1M context$0.30 in · $1.20 out / 1M

1M ctx · top OR coding rankings

MiniMax M2.7

T0
Together AI · minimax
1M context$0.30 in · $1.20 out / 1M

Prior MiniMax · stable pricing

Yi Large

T0
OpenRouter · yi
32K context$0.30 in · $0.30 out / 1M

01.AI · multilingual

Qwen3.6 27B

PlannedT0
DeepInfra · qwen
262K context$0.32 in · $3.20 out / 1M

Multimodal · image + video + text

GPT-4.1 Mini

BYOK
OpenAI · gpt
1M context$0.40 in · $1.60 out / 1M

Best budget OpenAI

Qwen3.7 Plus

T0
Together AI · qwen
1M context$0.40 in · $1.60 out / 1M

1M context Qwen

Mistral Medium 3

T0
Mistral AI · mistral
131K context$0.40 in · $2 out / 1M

Solid EU mid-range

Nemotron 4 340B

PlannedT0
NVIDIA NIM · nemotron
128K context$0.40 in · $0.40 out / 1M

Reward model · RLHF training data

Jamba 1.6 Large

T0
OpenRouter · jamba
256K context$0.40 in · $1.60 out / 1M

Large hybrid SSM-Transformer

Qwen3 235B MoE

T0
OpenRouter · qwen
131K context$0.46 in · $1.82 out / 1M

Flagship open-weight · top OR volume

Qwen3.6 Plus

T0
Together AI · qwen
1M context$0.50 in · $3 out / 1M

Balanced Qwen · 1M context

GLM-5.1

T0
Together AI · glm
200K context$0.50 in · $2 out / 1M

Z.AI coding flagship

DeepSeek R1

T0
DeepSeek · deepseek
164K context$0.55 in · $2.19 out / 1M

MIT reasoning · matches o1 benchmarks

Llama 3.3 70B

T0
Groq · llama3
128K context$0.59 in · $0.79 out / 1M

Fastest 70B · 394 TPS on Groq

Llama 3.1 70B

T0
Groq · llama3
128K context$0.59 in · $0.79 out / 1M

Reliable workhorse

DeepSeek V3.1

T0
Together AI · deepseek
164K context$0.60 in · $1.70 out / 1M

US-hosted DeepSeek · stable latency

Qwen3.5 397B MoE

T1
Together AI · qwen
131K context$0.60 in · $3.60 out / 1M

Large MoE Qwen · strong reasoning

Hermes 3 70B

PlannedT0
DeepInfra · hermes
131K context$0.70 in · $0.70 out / 1M

Strong instruction · agentic

Claude Haiku 3.5

T1
Anthropic · claude
200K context$0.80 in · $4 out / 1M

Older Haiku · still available

Qwen 2.5 72B

T0
Together AI · qwen
131K context$0.90 in · $0.90 out / 1M

Solid mid-size Qwen

Kimi K2.7 Code

T1
OpenRouter · kimi
1M context$0.95 in · $4 out / 1M

Frontier coding · Moonshot AI

Kimi K2.6

T1
Fireworks AI · kimi
1M context$0.95 in · $4 out / 1M

Coding · Moonshot AI

Claude Haiku 4.5

T1
Anthropic · claude
200K context$1 in · $5 out / 1M

Claude quality at T1 price

Grok Build 0.1

T1
xAI (Grok) · grok
256K context$1 in · $2 out / 1M

Coding specialist

Sonar Reasoning

T1
Perplexity (Sonar) · sonar
131K context$1 in · $5 out / 1M

Reasoning + web grounding

o3-mini

BYOK
OpenAI · o-series
200K context$1.10 in · $4.40 out / 1M

Budget reasoning

o4-mini

BYOK
OpenAI · o-series
200K context$1.10 in · $4.40 out / 1M

Latest budget reasoning

Mixtral 8x22B

T1
Together AI · mistral
64K context$1.20 in · $1.20 out / 1M

MoE classic · strong benchmark

Gemini 2.5 Pro

T1
Google Gemini · gemini
1M context$1.25 in · $10 out / 1M

Best Google reasoning value

Gemini 1.5 Pro

T1
Google Gemini · gemini
2M context$1.25 in · $5 out / 1M

Legacy 2M context option

Grok 4.3

T1
xAI (Grok) · grok
1M context$1.25 in · $2.50 out / 1M

Flagship · real-time data · X access

Grok 4.20 (standard)

T1
xAI (Grok) · grok
1M context$1.25 in · $2.50 out / 1M

xAI production standard

Grok 4.20 Reasoning

T1
xAI (Grok) · grok
1M context$1.25 in · $2.50 out / 1M

Chain-of-thought reasoning

Grok 4.20 Multi-Agent

T1
xAI (Grok) · grok
2M context$1.25 in · $2.50 out / 1M

2M context · multi-agent orchestration

Gemini 3.5 Flash

T1
Google Gemini · gemini
1M context$1.50 in · $9 out / 1M

Beats 3.1 Pro on coding · May 2026

DeepSeek V4 Pro

T1
DeepSeek · deepseek
1M context$1.74 in · $3.48 out / 1M

Hard reasoning + code

GPT-4.1

BYOK
OpenAI · gpt
1M context$2 in · $8 out / 1M

OpenAI flagship · 1M context

o3

BYOK
OpenAI · o-series
200K context$2 in · $8 out / 1M

Strong reasoning · 80% cheaper than launch

Gemini 3.1 Pro

T2
Google Gemini · gemini
1M context$2 in · $12 out / 1M

Google flagship

Mistral Large 2

T1
Mistral AI · mistral
128K context$2 in · $6 out / 1M

EU flagship · GDPR-native

Rerank v3

T0
Cohere · rerank
4K context$2 in · $0 out / 1M

Reranking for RAG pipelines · $2/1K search units (not per-token)

Sonar Reasoning Pro

T1
Perplexity (Sonar) · sonar
200K context$2 in · $8 out / 1M

Deep reasoning + deep research

GPT-4o

BYOK
OpenAI · gpt
128K context$2.50 in · $10 out / 1M

Previous gen · multimodal

Command R+

T1
Cohere · command
128K context$2.50 in · $10 out / 1M

RAG flagship · full retrieval stack

Claude Sonnet 4.6

T2
Anthropic · claude
1M context$3 in · $15 out / 1M

Managed ceiling · best balance

Grok 4 Heavy

BYOK
xAI (Grok) · grok
256K context$3 in · $15 out / 1M

Multi-agent · HLE 50.7% · BYOK only

Sonar Pro

T1
Perplexity (Sonar) · sonar
200K context$3 in · $15 out / 1M

Deep research · 200K ctx

Llama 3.1 405B

T2
Together AI · llama3
128K context$3.50 in · $3.50 out / 1M

Largest open model available

Claude Opus 4.8

BYOK
Anthropic · claude
1M context$5 in · $25 out / 1M

Best coder · frontier · BYOK only

Claude Opus 4.7

BYOK
Anthropic · claude
1M context$5 in · $25 out / 1M

Vision + long-horizon agents

GPT-5.5

BYOK
OpenAI · gpt
400K context$5 in · $30 out / 1M

Latest OpenAI frontier

zintus

Source-available AI router. BYOK. Zero markup. Routes intelligently across 12 free providers.

Product

PricingChangelogChatDesktop App

Developers

DocsDevelopersGitHubCLI InstallAPI Referencellms.txt

Company

AboutBlogContactTwitter/X

Legal

PrivacySecurityLicense (BUSL-1.1)Terms
© 2026 Zintus · YS Ventures LLC · Business Source License 1.1Made with ❤️ in Pittsburgh, PA