We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.

Models692 models

Updated 54 minutes ago

Browse 692 AI models from 86 providers (chat and reasoning LLMs, image, video, speech, transcription, embeddings and rerank models) with USD prices, context length and capabilities. Every model is callable through one OpenAI-compatible API.

Providers

Input modalities

Features

Min contextClear all

Showing 1–60 of 692 models

Model	Provider	Context	Price	Modalities
Recursive: Flint (free)recursive/flint-v1.0:free	Recursive	262K	Free	→ text
Baseten: Mammoth 1 (free)baseten/mammoth-1:free	Baseten	16K	Free	→ decisions
Baseten: Elephant 1 (free)baseten/elephant-1:free	Baseten	16K	Free	→ decisions
Nace.AI: Drex Maxnace-ai/drex-max	Nace.AI	262K	Input $0.21 / 1M tokens	→ decisions
NVIDIA: Nemotron 3.5 Embed 1B (free)nvidia/nemotron-3.5-embed-1b:free	NVIDIA	33K	Free	→ embeddings
NVIDIA: Nemotron 3.5 Embed 8B (free)nvidia/nemotron-3.5-embed-8b:free	NVIDIA	33K	Free	→ embeddings
NVIDIA: Nemotron 3.5 Rerank 8B (free)nvidia/nemotron-3.5-rerank-8b:free	NVIDIA	33K	Free	→ rerank
Mistral: Voxtral TTS 3mistralai/voxtral-mini-tts-3-0	Mistral	4K	Characters $45.50 / 1M characters	→ speech
Mistral: Voxtral Small Transcribe 3mistralai/voxtral-small-transcribe-3-0	Mistral	66K	Audio $0.01 / minute	→ transcription
Mistral: Voxtral Mini Transcribe 3mistralai/voxtral-mini-transcribe-3-0	Mistral	66K	Audio $0.01 / minute	→ transcription
MiniMax: MiniMax M3.1 Flashminimax/minimax-m3.1-flash	MiniMax	1M	Input $0.52 / 1M tokensOutput $2.10 / 1M tokens	→ text
DeepSeek: DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017	DeepSeek	1M	Input $0.52 / 1M tokensOutput $2.10 / 1M tokens	→ text
Elorian: Glimpseelorian/glimpse	Elorian	262K	Input $2.10 / 1M tokensOutput $10.50 / 1M tokens	→ text
Qwen: Qwen Image 2.1 Turboqwen/qwen-image-2.1-turbo	Qwen	66K	Image output $0.06 / image	→ image
Qwen: Qwen Image 2.1 Proqwen/qwen-image-2.1-pro	Qwen	66K	Image output $0.16 / image	→ image
Perplexity: Decider Flash V1.2perplexity/pplx-decider-flash-v1.2	Perplexity	262K	Input $0.04 / 1M tokens	→ decisions
Perplexity: Decider V1.2perplexity/pplx-decider-v1.2	Perplexity	262K	Input $0.07 / 1M tokens	→ decisions
XingChen: Xing4.0 29B A4B (free)xingchen-agi/xing4.0-29b-a4b:free	XingChen	262K	Free	→ text
Perplexity: Decider Flash Latest~perplexity/pplx-decider-flash-latest	Perplexity	262K	Input $0.04 / 1M tokens	→ decisions
Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b	Reflection	1M	Input $0.88 / 1M tokensOutput $3.50 / 1M tokens	→ text
Inception: Mercury 3inception/mercury-3	Inception	1M	Input $0.35 / 1M tokensOutput $1.22 / 1M tokens	→ text
Respan: Span-02respan/span-02	Respan	131K	Input $0.04 / 1M tokens	→ decisions
LiquidAI: d1-ultraliquid/d1-ultra	LiquidAI	33K	Input $0.15 / 1M tokensCache read $0.15 / 1M tokens	→ decisions
Krea: K3 Editkrea/k3-edit	Krea	66K	Image input $25.15 / 1M tokensImage output $25.15 / 1M tokens	→ image
Moondream: Moondream 3 Previewmoondream/moondream3-preview	Moondream	32K	Input $1.05 / 1M tokensOutput $8.75 / 1M tokens	→ text
Moondream: Moondream 3.1moondream/moondream3.1-9b-a2b	Moondream	32K	Input $1.05 / 1M tokensOutput $8.75 / 1M tokens	→ text
Meta: Muse Spark Openmeta/muse-spark-open	Meta	1M	Input $4.38 / 1M tokensOutput $14.88 / 1M tokens	→ text
Black Forest Labs: FLUX 3 Image Kleinblack-forest-labs/flux-3-image-klein	Black Forest Labs	47K	Image output $0.03 / image	→ image
NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl	NVIDIA	1M	Input $0.52 / 1M tokensOutput $1.75 / 1M tokens	→ text
NVIDIA: Nemotron 3.5 Super VL (free)nvidia/nemotron-3.5-super-vl:free	NVIDIA	1M	Free	→ text
Pareto 26.10unbiased/pareto-26.10	Unbiased	1M	Input $2.80 / 1M tokensOutput $11.20 / 1M tokens	→ text
TypeSafe: Jev 1.14typesafe/jev-1.14	TypeSafe	262K	Input $0.15 / 1M tokens	→ decisions
AssemblyAI: Universal-3.6 Proassemblyai/universal-3-6-pro	AssemblyAI	-	Audio $0.02 / minute	→ transcription
Perplexity: Decider Latest~perplexity/pplx-decider-latest	Perplexity	262K	Input $0.07 / 1M tokens	→ decisions
Pareto Latest~unbiased/pareto-latest	Unbiased	1M	Input $2.80 / 1M tokensOutput $11.20 / 1M tokens	→ text
Pareto 26.9unbiased/pareto-26.9	Unbiased	262K	Input $8.75 / 1M tokensOutput $26.25 / 1M tokens	→ text
HeyGen: HeyGen Voiceheygen/heygen-voice-1	HeyGen	-	Characters $52.50 / 1M characters	→ speech
HeyGen: HeyGen Voice Turboheygen/heygen-voice-1-turbo	HeyGen	-	Characters $14.00 / 1M characters	→ speech
LiquidAI: LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b	LiquidAI	128K	Input $0.18 / 1M tokensOutput $2.45 / 1M tokens	→ text
Fish Audio: Drama 3fish-audio/drama-3	Fish Audio	-	Characters $7.00 / 1M characters	→ speech
Google: Gemini 4 Argongoogle/gemini-4-argon	Google	1M	Input $7.00 / 1M tokensOutput $35.00 / 1M tokens	→ text
Google: Gemini 4 Argon (batch)google/gemini-4-argon:batch	Google	1M	Input $3.50 / 1M tokensOutput $17.50 / 1M tokens	→ text
ScaleDown: Summarizescaledown/summarize	ScaleDown	1M	Input $0.14 / 1M tokens	→ text
ScaleDown: Extractscaledown/extract	ScaleDown	1M	Input $0.14 / 1M tokens	→ text
ScaleDown: Classify-1scaledown/classify-1	ScaleDown	1M	Input $0.14 / 1M tokens	→ decisions
Nace.AI: Drex v2.0nace-ai/drex-v2.0	Nace.AI	131K	Input $0.21 / 1M tokens	→ decisions
Meta: Muse Wondermeta/muse-wonder	Meta	1M	Input $14.00 / 1M tokensOutput $70.00 / 1M tokens	→ text
Microsoft: Microsoft-Decision-1microsoft/microsoft-decision-1	Microsoft	33K	Input $0.15 / 1M tokens	→ decisions
Nace.AI: Drex v1.5nace-ai/drex-v1.5	Nace.AI	131K	Input $0.14 / 1M tokens	→ decisions
Cloudflare: Clef Omnicloudflare/clef-omni	Cloudflare	66K	Input $0.52 / 1M tokens	→ decisions
StepFun: Step 5 Previewstepfun/step-5-preview	StepFun	1M	Input $3.50 / 1M tokensOutput $9.45 / 1M tokens	→ text
Upstage: Solar Decide Flashupstage/solar-decide-flash	Upstage	524K	Input $0.18 / 1M tokensCache read $0.18 / 1M tokens	→ decisions
Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5	Anthropic	1M	Input $0.35 / 1M tokensOutput $1.75 / 1M tokens	→ text
Anthropic: Claude Haiku 5.5 (batch)anthropic/claude-haiku-5.5:batch	Anthropic	1M	Input $0.18 / 1M tokensOutput $0.88 / 1M tokens	→ text
ElevenLabs: Eleven v4elevenlabs/eleven-v4	ElevenLabs	-	Characters $280.00 / 1M characters	→ speech
ElevenLabs: Eleven v4 Turboelevenlabs/eleven-v4-turbo	ElevenLabs	-	Characters $140.00 / 1M characters	→ speech
ElevenLabs: Eleven v3elevenlabs/eleven-v3	ElevenLabs	-	Characters $280.00 / 1M characters	→ speech
ElevenLabs: Eleven v3 Conversationalelevenlabs/eleven-v3-conversational	ElevenLabs	-	Characters $140.00 / 1M characters	→ speech
ElevenLabs: Eleven Flash v2.5elevenlabs/eleven-flash-v2.5	ElevenLabs	-	Characters $140.00 / 1M characters	→ speech
ElevenLabs: Eleven Turbo v2elevenlabs/eleven-turbo-v2	ElevenLabs	-	Characters $140.00 / 1M characters	→ speech

Catalog at a glance

Models: 692
Providers: 86
Free models: 41
Added in the last 30 days: 109
Largest context: 2M

Lowest-cost LLMs by input price

Z.ai: GLM Flash LatestInput $0.02 / 1M tokensOutput $0.69 / 1M tokens
Z.ai: GLM 5.3 FlashInput $0.02 / 1M tokensOutput $0.69 / 1M tokens
IBM: Granite 4.0 MicroInput $0.06 / 1M tokensOutput $0.39 / 1M tokens
OpenAI: gpt-oss-20bInput $0.06 / 1M tokensOutput $0.32 / 1M tokens
inclusionAI: Ling 3.0 FlashInput $0.07 / 1M tokensOutput $0.22 / 1M tokens
OpenAI: gpt-oss-20b (batch)Input $0.08 / 1M tokensOutput $0.39 / 1M tokens

Longest context windows

Newest models

Recursive: Flint (free)yesterday
Baseten: Mammoth 1 (free)yesterday
Baseten: Elephant 1 (free)yesterday
Nace.AI: Drex Maxyesterday
NVIDIA: Nemotron 3.5 Embed 1B (free)yesterday
NVIDIA: Nemotron 3.5 Embed 8B (free)yesterday

Top providers

OpenAI 127 Google 55 Qwen 54 Mistral 35 Anthropic 34 NVIDIA 21 Z.ai 20 DeepSeek 18 xAI 16 Recraft 16 MiniMax 14 Microsoft 12

How model prices work

Text and embedding models are priced per 1M input and output tokens; a token is roughly three quarters of an English word.

Image models are priced per image or per 1M image tokens, video per second of output, speech per 1M characters and transcription per minute of audio.

The price shown on each model is the price you pay, debited from your USD balance after each successful request. Failed requests are free.

Pricing

AI model catalog: FAQ

How many AI models are available?

692 models from 86 providers today. The catalog updates every hour, so new models appear automatically and retired ones are removed.

What is a context window?

The maximum number of tokens a model reads in one request: prompt, chat history and documents together. Long-context models can take whole codebases or books.

Are there free models?

Yes, 41 models currently cost $0 per token. They have stricter upstream rate limits, so use them for testing and low-volume tasks.

How do I call a model from this list?

Copy its id (for example ~z-ai/glm-flash-latest) and pass it as model in an OpenAI SDK request with baseURL set to https://api14.com/api/v1.