200+ Models Available

200+ Models · All Providers · One API

200+ models for text, image, video, audio, embedding, and moderation. Our domain-specialist Vedika models cover 4 astrology systems (Vedic, Western, KP, Vastu) with 600+ computation endpoints, classical text citations, and 14 Indic languages. Plus DeepSeek, Qwen, Google, Meta, Mistral, and more.

Get API Key View API Docs

No models match your search.

Try a different query or clear your filters.

Subquadratic
Subquadratic
First fully sub-quadratic LLM · O(n) architecture
12M
context
1,000x
less compute
150
tok/sec
1/5
cost
COMING SOON subq.ai →
BENCHMARK SubQ Gemini 3.1 Claude 4.6 GPT-5.5
SWE-Bench Verified 81.8% 80.6% 80.8% n/r
RULER @128K 95.0% — 94.8% —
MRCR v2 (8-needle, 1M) 65.9% 26.3% 78.3% 74.0%
✓ 12M context ✓ OpenAI-compatible ✓ Streaming + tools ✓ ~25% cheaper ✓ 10x faster exploration Team from Meta, Google, Oxford, Cambridge
Anthropic
Claude Mythos
Anthropic · Most capable model ever built · Autonomous cyber-grade reasoning
2M
context
271
0-days found
#1
cyber bench
COMING SOON

XALEN Models

Purpose-built for faith & culture
VedikaXALEN
Vedika Standard
XALEN · Chat | 128K | Multi-turn | 4 Systems

Deep analysis with classical text grounding. Vedic, Western, KP & Vastu. 14 languages.

Speed600–800 tok/s
Context128K
SystemsVedic / Western / KP / Vastu
Input$2.00 /1M
Output$4.00 /1M
Multi-turnGroundedCitation14 langs600+ endpoints
VedikaXALEN
Vedika Fast
XALEN · Chat | 128K | Sub-200ms | Streaming

Low-latency inference for real-time apps. Same intelligence, 10x faster.

Speed3,200 tok/s
First Token<50ms
Input$2.80 /1M
Output$5.60 /1M
Sub-200msStreamingVoice-ReadyReal-Time
VedikaXALEN
Vedika Voice
XALEN · Voice | 31 langs | 3 personas

Natural voice synthesis in Hindi, Tamil, Bengali, Telugu + 27 more. Pandit, Jajman, Seva personas.

PersonasPandit / Jajman / Seva
Languages31
Pricing$0.02 /sec
Latency<200ms
STT+LLM+TTSPanditJajmanSeva31 langs

Anthropic Claude

Frontier models for reasoning, coding & analysis
ANTHROPICANTHROPICNEW
Claude Opus 4.8
Anthropic via OpenRouter · Latest Frontier
Context1M
TypeChat + Reasoning
Input$15.00 /1M
Output$75.00 /1M
NEWFrontier1M ContextReasoningAgentic
OPENAIOPENAINEW
GPT-Audio
OpenAI via OpenRouter · Voice / Speech
ModalityText + Audio
OutputVoice (pcm16)
Input$2.50 /1M
Audio out$10.00 /1M
NEWVoiceTTSTranscriptStreamed
OPENAIOPENAINEW
GPT-Audio Mini
OpenAI via OpenRouter · Fast Voice
ModalityText + Audio
OutputVoice (pcm16)
Input$1.00 /1M
Audio out$4.00 /1M
NEWVoiceTTSLow-costFast
ANTHROPICANTHROPICNEW
Claude Fable 5
Anthropic via OpenRouter · New Flagship
ContextLarge
TypeChat + Creative
Input$3.00 /1M
Output$15.00 /1M
NEWFrontierCreativeLong-form
ANTHROPICANTHROPIC
Claude Opus 4.7
Anthropic · Frontier Reasoning
Context1M
TypeChat + Reasoning
Input$5.00 /1M
Output$25.00 /1M
Frontier1M ContextReasoningAgentic
ANTHROPICANTHROPIC
Claude Sonnet 4.6
Anthropic · Balanced Performance
Context1M
TypeChat + Reasoning
Input$3.00 /1M
Output$15.00 /1M
1M ContextBalancedCoding
ANTHROPICANTHROPIC
Claude Opus 4.6
Anthropic · Deep Reasoning
Context1M
TypeChat + Reasoning
Input$5.00 /1M
Output$25.00 /1M
1M ContextReasoningExtended Thinking
ANTHROPICANTHROPIC
Claude Haiku 4.5
Anthropic · Fast & Efficient
Context200K
TypeChat
Input$1.00 /1M
Output$5.00 /1M
200K ContextFastLow Cost
ANTHROPICANTHROPIC
Claude Sonnet 4.5
Anthropic · Hybrid Thinking
Context1M
TypeChat + Reasoning
Input$3.00 /1M
Output$15.00 /1M
1M ContextHybridCoding
ANTHROPICANTHROPIC
Claude 3.5 Haiku
Anthropic · Lightweight
Context200K
TypeChat
Input$0.80 /1M
Output$4.00 /1M
200K ContextLightweightAffordable

Featured Serverless

Top models with instant availability
DEEPSEEKDEEPSEEK
DeepSeek V4 Pro
DeepSeek · Chat + Reasoning
TierServerless
TypeChat + Reasoning
Input$2.10 /1M
Output$4.40 /1M
ServerlessChatReasoning
ZAIZAI
GLM 5.1 FP4
Zai · 435.2B Parameters
Parameters435.2B
QuantizationFP4
Input$1.40 /1M
Output$4.40 /1M
Serverless435BFP4
MOONSHOTMOONSHOT
Kimi K2.6 FP4
Moonshot AI · Chat
TierServerless
TypeChat
Input$1.20 /1M
Output$4.50 /1M
ServerlessChat
MINIMAXMINIMAX
MiniMax M2.7 FP4
MiniMax · 130.4B Parameters
Parameters130.4B
QuantizationFP4
Input$0.30 /1M
Output$1.20 /1M
Serverless130BEfficient
GOOGLEGOOGLE
Gemma 4 31B-it FP8
Google · 31B Instruct
Parameters31B
QuantizationFP8
Input$0.20 /1M
Output$0.50 /1M
Serverless31BInstruct
QWENQWEN
Qwen 3.5 397B A17b
Qwen · 397B MoE
Parameters397B (A17b)
ArchitectureMoE
Input$0.60 /1M
Output$3.60 /1M
ServerlessMoEReasoning
OPENAIOPENAI
GPT-OSS 120B
OpenAI · 120B Open-Source
Parameters120B
TierServerless
Input$0.15 /1M
Output$0.60 /1M
Serverless120BOpen-Source
OPENAIOPENAI
GPT-OSS 20B
OpenAI · 20B Open-Source
Parameters20B
TierServerless
Input$0.05 /1M
Output$0.20 /1M
Serverless20BFast
ZAIZAI
GLM 5 FP4
Zai · Chat
TierServerless
QuantizationFP4
Input$1.00 /1M
Output$3.20 /1M
ServerlessChatFP4
MOONSHOTMOONSHOT
Kimi K2.5
Moonshot AI · Chat
TierServerless
TypeChat
Input$0.50 /1M
Output$2.80 /1M
ServerlessChat
DEEPSEEKDEEPSEEK
DeepSeek R1-0528
DeepSeek · Advanced Reasoning
TierServerless
TypeReasoning
Input$3.00 /1M
Output$7.00 /1M
ServerlessReasoningCoT
DEEPSEEKDEEPSEEK
DeepSeek V3.1
DeepSeek · General Chat
TierServerless
TypeChat
Input$0.60 /1M
Output$1.70 /1M
ServerlessChat
QWENQWEN
Qwen 3.5 9B FP8
Qwen · 9B Fast
Parameters9B
QuantizationFP8
Input$0.10 /1M
Output$0.15 /1M
Serverless9BFast
QWENQWEN
Qwen 3 Coder Next FP8
Qwen · Code Generation
TierServerless
TypeCode
Input$0.50 /1M
Output$1.20 /1M
ServerlessCode
QWENQWEN
Qwen 3 Coder 480B A35B
Qwen · 480B MoE Code
Parameters480B (A35B)
ArchitectureMoE
Input$2.00 /1M
OutputOn Request
Serverless480B MoECode
ESSENTIAL AI
Cogito V2.1 671B
Essential AI · 671B Reasoning
Parameters671B
TypeReasoning
Input$1.25 /1M
OutputOn Request
Serverless671BReasoning
QWENQWEN
Qwen 3.6 Plus
Qwen · Latest Generation
TierServerless
TypeChat + Reasoning
Input$0.50 /1M
Output$3.00 /1M
ServerlessLatestReasoning

Chat Models

60+ general-purpose chat models
METAMETA
Llama 4 Maverick 17Bx128E
Meta · 400B MoE · 1M Context
Parameters400B MoE
Context1M
Input$0.27 /1M
Output$0.85 /1M
MoE1M Context
METAMETA
Llama 4 Scout 17Bx16E
Meta · 109B MoE
Parameters109B MoE
Context512K
Input$0.15 /1M
Output$0.40 /1M
MoE512K
METAMETA
Llama 3.3 70B Instruct Turbo
Meta · 70B
Parameters70B
Context128K
Input$0.12 /1M
Output$0.30 /1M
70BTurbo
METAMETA
Llama 3.1 405B Instruct Turbo
Meta · 405B
Parameters405B
Context128K
Input$0.80 /1M
Output$0.80 /1M
405BFrontier
METAMETA
Llama 3.1 8B Instruct Turbo
Meta · 8B Fast
Parameters8B
Context128K
Input$0.05 /1M
Output$0.08 /1M
8BFast
MISTRALMISTRAL
Mistral Large 2
Mistral · 123B
Parameters123B
Context128K
Input$0.80 /1M
Output$2.40 /1M
123BEU
MISTRALMISTRAL
Mistral Small 3.2 24B
Mistral · 24B
Parameters24B
Context128K
Input$0.10 /1M
Output$0.30 /1M
24BFast
GOOGLEGOOGLE
Gemma 3 27B-it
Google · 27B Instruct
Parameters27B
Context128K
Input$0.10 /1M
Output$0.20 /1M
27BInstruct
QWENQWEN
Qwen 3 235B A22B
Qwen · 235B MoE
Parameters235B (A22B)
ArchitectureMoE
Input$0.30 /1M
Output$0.80 /1M
MoE235B
QWENQWEN
Qwen 3 32B
Qwen · 32B
Parameters32B
Context128K
Input$0.15 /1M
Output$0.40 /1M
32B
QWENQWEN
Qwen 3 8B
Qwen · 8B
Parameters8B
Context128K
Input$0.05 /1M
Output$0.08 /1M
8BFast
QWENQWEN
Qwen 2.5 72B Instruct Turbo
Qwen · 72B Turbo
Parameters72B
Context128K
Input$0.12 /1M
Output$0.30 /1M
72BTurbo
DEEPSEEKDEEPSEEK
DeepSeek V3
DeepSeek · 671B MoE
Parameters671B MoE
Context128K
Input$0.40 /1M
Output$0.89 /1M
671BMoE
MICROSOFT
Phi-4 14B
Microsoft · 14B
Parameters14B
Context16K
Input$0.05 /1M
Output$0.15 /1M
14BEfficient
DATABRICKS
DBRX Instruct
Databricks · 132B MoE
Parameters132B MoE
Context32K
Input$0.60 /1M
Output$0.60 /1M
132BMoE

Reasoning Models

Chain-of-thought & deep reasoning
DEEPSEEKDEEPSEEK
DeepSeek R1
DeepSeek · 671B Reasoning
Parameters671B MoE
TypeReasoning
Input$1.50 /1M
Output$5.00 /1M
671BCoT
DEEPSEEKDEEPSEEK
DeepSeek R1 Distill Llama 70B
DeepSeek · 70B Distilled
Parameters70B
BaseLlama 3.1
Input$0.30 /1M
Output$0.80 /1M
70BDistilled
DEEPSEEKDEEPSEEK
DeepSeek R1 Distill Qwen 32B
DeepSeek · 32B Distilled
Parameters32B
BaseQwen 2.5
Input$0.15 /1M
Output$0.50 /1M
32BDistilled
QWENQWEN
QwQ 32B
Qwen · 32B Reasoning
Parameters32B
TypeReasoning
Input$0.15 /1M
Output$0.40 /1M
32BThinking

Code Models

Specialized for programming
QWENQWEN
Qwen 2.5 Coder 32B Instruct
Qwen · 32B Code
Parameters32B
TypeCode
Input$0.15 /1M
Output$0.30 /1M
32BCode
DEEPSEEKDEEPSEEK
DeepSeek Coder V2.5
DeepSeek · 236B MoE Code
Parameters236B MoE
TypeCode + Chat
Input$0.40 /1M
Output$0.80 /1M
MoECode
MISTRALMISTRAL
Devstral Small 24B
Mistral · 24B Code Agent
Parameters24B
TypeCode Agent
Input$0.10 /1M
Output$0.30 /1M
24BAgent
MISTRALMISTRAL
Codestral 22B
Mistral · 22B Code FIM
Parameters22B
Context32K
Input$0.30 /1M
Output$0.90 /1M
22BFIM

Vision Models

Multimodal chat with image understanding
METAMETA
Llama 3.2 90B Vision Instruct
Meta · 90B Vision
Parameters90B
TypeVision + Chat
Input$0.12 /1M
Output$0.30 /1M
90BVision
METAMETA
Llama 3.2 11B Vision Instruct
Meta · 11B Vision
Parameters11B
TypeVision + Chat
Input$0.05 /1M
Output$0.08 /1M
11BVision
QWENQWEN
Qwen 2.5 VL 72B Instruct
Qwen · 72B Vision
Parameters72B
TypeVision + Document
Input$0.40 /1M
Output$0.40 /1M
72BVisionDoc
QWENQWEN
Qwen 2.5 VL 7B Instruct
Qwen · 7B Vision
Parameters7B
TypeVision + Chat
Input$0.05 /1M
Output$0.10 /1M
7BVision

Image Generation

30+ image models
BFLBFL
FLUX.2 Dev
Black Forest Labs
TypeImage Gen
QualityDev
Price$0.025 /img
TierServerless
FLUX.2
BFLBFL
FLUX.2 Flex
Black Forest Labs
TypeImage Gen
QualityFlexible
Price$0.025 /img
TierServerless
FLUX.2Flex
BFLBFL
FLUX.2 Pro
Black Forest Labs
TypeImage Gen
QualityPro
Price$0.030 /img
TierServerless
FLUX.2Pro
BFLBFL
FLUX.2 Max
Black Forest Labs
TypeImage Gen
QualityMax
Price$0.030 /img
TierServerless
FLUX.2Max
BFLBFL
FLUX 1.1 Pro
Black Forest Labs · Fast Pro
TypeImage Gen
SpeedFast
Price$0.020 /img
TierServerless
FLUX 1.1Fast
BFLBFL
FLUX.1 Schnell
Black Forest Labs · Fastest
TypeImage Gen
Speed4 steps
Price$0.015 /img
TierServerless
FastestBudget
BFLBFL
FLUX.1 Kontext Pro
Black Forest Labs · Editing
TypeImage Editing
ModeContextual
Price$0.030 /img
TierServerless
EditingKontext
BFLBFL
FLUX.1 Kontext Max
Black Forest Labs · Max Edit
TypeImage Editing
ModeMax
Price$0.030 /img
TierServerless
EditingMax
OPENAIOPENAI
GPT Image 1.5
OpenAI · Image Gen
TypeImage Gen
QualityHigh
Price$0.034 /img
TierServerless
GPTImage
GOOGLEGOOGLE
Imagen 4.0 Fast
Google · Fast Gen
TypeImage Gen
SpeedFast
Price$0.020 /img
TierServerless
Imagen 4Fast
GOOGLEGOOGLE
Imagen 4.0 Ultra
Google · Ultra Quality
TypeImage Gen
QualityUltra
Price$0.060 /img
TierServerless
Imagen 4Ultra
GOOGLEGOOGLE
Imagen 4.0 Preview
Google · Preview
TypeImage Gen
QualityPreview
Price$0.040 /img
TierServerless
Imagen 4Preview
IDEOGRAM
Ideogram 3.0
Ideogram · Typography
TypeImage + Text
SpecialtyTypography
Price$0.060 /img
TierServerless
Typography
BYTEDANCEBYTEDANCE
Seedream 3.0 / 4.0
ByteDance · Image Gen
TypeImage Gen
Range3.0 to 4.0
PriceOn Request
TierServerless
Seedream
QWENQWEN
Qwen Image / 2.0 Pro
Qwen · Image Gen
TypeImage Gen
RangeStandard to Pro
PriceOn Request
TierServerless
QwenImage
GOOGLEGOOGLE
Gemini 3 / 3.1 Flash Image
Google · Multimodal Image
TypeMultimodal Image
ModeFlash
PriceOn Request
TierServerless
GeminiFlash
HIDREAM
HiDream
HiDream · Creative
TypeImage Gen
StyleCreative
PriceOn Request
TierServerless
Creative
RUNDIFFUSION
Juggernaut
RunDiffusion · Photorealistic
TypeImage Gen
StylePhoto
PriceOn Request
TierServerless
Photo
RUNDIFFUSION
Dreamshaper
RunDiffusion · Artistic
TypeImage Gen
StyleArtistic
PriceOn Request
TierServerless
Artistic
STABILITYSTABILITY
Stable Diffusion XL
Stability AI · SDXL
TypeImage Gen
Res1024x1024
PriceOn Request
TierServerless
SDXLOSS
STABILITYSTABILITY
Stable Diffusion 3
Stability AI · SD3
TypeImage Gen
ArchMMDiT
PriceOn Request
TierServerless
SD3

Video Generation

20+ video models
GOOGLEGOOGLE
Veo 3.0
Google · Premium Video
TypeVideo Gen
QualityPremium
Price$3.20 /vid
TierServerless
Veo 3Premium
GOOGLEGOOGLE
Veo 3.0 Fast
Google · Fast Video
TypeVideo Gen
SpeedFast
Price$1.60 /vid
TierServerless
Veo 3Fast
GOOGLEGOOGLE
Veo 2.0
Google · Standard
TypeVideo Gen
QualityStandard
Price$0.80 /vid
TierServerless
Veo 2
OPENAIOPENAI
Sora 2
OpenAI · Video Gen
TypeVideo Gen
QualityStandard
Price$0.80 /vid
TierServerless
Sora 2
OPENAIOPENAI
Sora 2 Pro
OpenAI · Pro Video
TypeVideo Gen
QualityPro
Price$3.00 /vid
TierServerless
Sora 2Pro
KUAISHOU
Kling 2.1 Master
Kuaishou · Master
TypeVideo Gen
QualityMaster
Price$0.92 /vid
TierServerless
KlingMaster
KUAISHOU
Kling 2.1 Pro
Kuaishou · Pro
TypeVideo Gen
QualityPro
Price$0.46 /vid
TierServerless
KlingPro
KUAISHOU
Kling 2.1 Standard
Kuaishou · Standard
TypeVideo Gen
QualityStandard
Price$0.18 /vid
TierServerless
KlingBudget
VIDUVIDU
Vidu Q1 / Q3 / 2.0
Vidu · Efficient Video
TypeVideo Gen
RangeQ1 to 2.0
Price$0.10-$0.80 /vid
TierServerless
Vidu
PIXVERSEPIXVERSE
PixVerse v5 / v6
PixVerse · Creative
TypeVideo Gen
Rangev5 to v6
Price$0.09-$0.30 /vid
TierServerless
PixVerseAffordable
BYTEDANCEBYTEDANCE
Seedance 1.0 / 2.0
ByteDance · Motion
TypeVideo Gen
SpecialtyMotion
PriceOn Request
TierServerless
SeedanceMotion
MINIMAXMINIMAX
MiniMax Hailuo 02
MiniMax · Hailuo
TypeVideo Gen
QualityCreative
PriceOn Request
TierServerless
Hailuo
WAN-AIWAN-AI
Wan 2.6 / 2.7
Wan-AI · Open Video
TypeVideo Gen
Range2.6 to 2.7
PriceOn Request
TierServerless
WanOSS

Audio Models

TTS, STT & voice synthesis
KOKORO
Kokoro 82M
Kokoro · 82M TTS
Params82M
TypeTTS
Price$4.00 /1M ch
TierServerless
TTSFast
ORPHEUS
Orpheus 3B
Orpheus · 3B Expressive
Params3B
TypeTTS
Price$15.00 /1M ch
TierServerless
TTSExpressive
OPENAIOPENAI
Whisper Large V3
OpenAI · STT
TypeSTT
Langs99+
PriceOn Request
TierServerless
STTMultilingual
CARTESIACARTESIA
Cartesia Sonic / 2 / 3
Cartesia · Streaming TTS
TypeStreaming TTS
LatencyUltra-low
Price$65.00 /1M ch
TierServerless
TTSStreaming
NVIDIANVIDIA
Nvidia Parakeet
Nvidia · Enterprise STT
TypeSTT
QualityEnterprise
PriceOn Request
TierServerless
STTEnterprise
DEEPGRAMDEEPGRAM
Deepgram Nova 3
Deepgram · Fast STT
TypeSTT
SpeedReal-time
PriceOn Request
TierServerless
STTReal-time
DEEPGRAMDEEPGRAM
Deepgram Aura 2
Deepgram · Natural TTS
TypeTTS
QualityNatural
PriceOn Request
TierServerless
TTSNatural
DEEPGRAMDEEPGRAM
Deepgram Flux
Deepgram · Versatile TTS
TypeTTS
QualityVersatile
PriceOn Request
TierServerless
TTS
MISTRALMISTRAL
Voxtral Mini 3B
Mistral · 3B Voice STT
Params3B
TypeSTT
PriceOn Request
TierServerless
STT3B

Embedding & Rerank

Search, RAG, and retrieval
INTFLOAT
E5 Large Multilingual
Intfloat · 1024d
Dims1024
TypeEmbedding
Price$0.01 /1M
TierServerless
EmbeddingMultilingual
BAAIBAAI
BGE Large EN v1.5
BAAI · 1024d English
Dims1024
TypeEmbedding
Price$0.01 /1M
TierServerless
EmbeddingEnglish
BAAIBAAI
BGE Reranker V2 M3
BAAI · Cross-Encoder
TypeReranker
ModeCross-Encoder
Price$0.01 /1M
TierServerless
RerankRAG
MIXEDBREAD
Mxbai Embed Large v1
Mixedbread · 1024d
Dims1024
TypeEmbedding
Price$0.01 /1M
TierServerless
Embedding
MIXEDBREAD
Mxbai Rerank Large v2
Mixedbread · Reranker
TypeReranker
ModeCross-Encoder
Price$0.01 /1M
TierServerless
Rerank

Moderation

Safety & content filtering
METAMETA
Llama Guard 4 12B
Meta · 12B Safety
Params12B
TypeSafety
Price$0.05 /1M
TierServerless
GuardSafety
METAMETA
Llama Guard 3 8B
Meta · 8B Safety
Params8B
TypeSafety
Price$0.05 /1M
TierServerless
Guard8B

Start building with 200+ models today

One API key. Unified billing. OpenAI-compatible. Switch models without changing your code.

Get API Key Free Read the Docs