LLM directory · Pricing · Benchmarks

LLM cost calculator and model directory

Per-token pricing, context windows, capabilities, and public benchmark scores for 3,917 models across 54 providers — chat, embeddings, image, audio, video, and rerank. Pricing verified weekly. Submit edits in one click. Route any model via Future AGI's Agent Command Center for unified caching, fallback, and observability.

Get the gateway free → GitHub ↗
Models
3,917
With pricing
3,491
Providers
54

Browse by provider

OpenAI
224
GPT-4o, GPT-4, o-series reasoning models, embeddings, audio, image, and Realtime API.
Anthropic
38
Claude family of frontier reasoning models with industry-leading context length and tool use.
Google AI
126
Gemini chat, embeddings, image and multimodal models served via the Google AI API.
Google Vertex AI
277
Enterprise GCP endpoint for Gemini, Anthropic, Meta, and Mistral models with VPC-SC and IAM.
Amazon Bedrock
555
AWS-managed endpoints for Anthropic, Meta, Mistral, Cohere, and Amazon Nova models.
Azure OpenAI
338
OpenAI models on Azure with regional endpoints, RBAC, and content-filtering policies.
Azure AI Foundry
157
Azure marketplace catalog for Mistral, Cohere, Meta, Phi, and other partner models.
Mistral AI
95
European frontier lab — Mistral Large, Codestral, Pixtral, Mistral Small.
Cohere
29
Command R+ chat, Embed v3 multilingual embeddings, Rerank, and enterprise RAG models.
Groq
20
LPU inference for Llama, Mixtral, Whisper — sub-second TTFT at high throughput.
Cerebras
9
Wafer-scale inference for Llama and Qwen models — among the fastest tokens/sec available.
xAI
90
Grok family of frontier models with native real-time search and tool use.
Perplexity
94
Sonar models with grounded web search and citation built-in.
Fireworks AI
342
Fast inference for Llama, Qwen, DeepSeek, Mixtral and 200+ open-source models.
Together AI
104
Open-model inference cloud — Llama, DeepSeek, Qwen, Mixtral, FLUX with serverless and dedicated endpoints.
DeepInfra
137
GPU inference for Llama, Qwen, DeepSeek, FLUX with per-token pricing.
Replicate
41
Hosted inference for Llama, FLUX, Stable Diffusion, Whisper, and community models.
OpenRouter
96
Unified gateway across 300+ models from 60+ providers with a single API key.
Novita AI
135
Pay-as-you-go GPU inference for Llama, Qwen, FLUX, and image/video models.
Databricks
71
Mosaic AI Model Serving — Llama, DBRX, Claude on Databricks with Unity Catalog governance.
Snowflake Cortex
37
In-warehouse LLM functions — Arctic, Llama, Mistral, with data residency in Snowflake.
IBM watsonx
31
Enterprise foundation models — Granite, Llama, Mistral with AI governance.
Alibaba DashScope
58
Qwen family of frontier models — Qwen-Max, Qwen-VL, Qwen-Audio.
Moonshot AI
24
Kimi K2 series — long-context Chinese-leading frontier models.
DeepSeek
11
DeepSeek-R1 reasoning model and DeepSeek-V3 MoE — open-weight frontier-class inference.
Deepgram
42
Nova/Aura speech-to-text and TTS — production-grade audio AI.
AssemblyAI
2
Universal-2 speech-to-text with diarization, sentiment, and entity detection.
ElevenLabs
5
Multilingual text-to-speech and voice cloning — production voice AI.
Stability AI
23
Stable Diffusion, Stable Image Ultra, Stable Audio for image and audio generation.
Lambda
20
Lambda Inference API — Llama, DeepSeek, Qwen on dedicated GPU clusters.
Nebius
61
European GPU cloud with Inference Studio for Llama, Qwen, DeepSeek, FLUX.
AI21 Labs
12
Jamba models — hybrid Mamba-Transformer with 256K context.
Voyage AI
31
voyage-3 family of state-of-the-art retrieval embeddings and rerankers.
Jina AI
1
Multilingual embeddings, rerankers, and Reader API for grounding.
GitHub Copilot
62
GitHub Copilot Chat completions — Claude, GPT, and Gemini routed through Copilot.
SambaNova
19
Reconfigurable Dataflow Unit inference for Llama, DeepSeek, Qwen.
Hyperbolic
16
Decentralized GPU inference for Llama, Qwen, DeepSeek, and FLUX.
Nscale
16
Nordic GPU cloud with serverless inference for Llama and DeepSeek.
OVHcloud AI
15
EU-sovereign AI endpoints — Llama, Mistral, Qwen, Mixtral.
W&B Inference
43
Weights & Biases serverless inference for Llama and DeepSeek.
DigitalOcean Gradient
13
DigitalOcean Gradient AI Platform — managed inference for open-source models.
Oracle Cloud
50
Oracle Cloud Generative AI — Llama, Cohere, on OCI.
Anyscale
12
Ray-powered serverless inference for Llama, Mistral, and Qwen.
fal.ai
210
Real-time inference for FLUX, Stable Diffusion, Whisper, and audio models.
Z.ai
16
GLM family of frontier Chinese-leading reasoning and chat models.
MiniMax
12
MiniMax M2 reasoning, abab chat, and speech models.
Black Forest Labs
8
FLUX family — state-of-the-art image generation and editing.
Volcano Engine
20
ByteDance cloud — Doubao chat, image, and audio models.
Aleph Alpha
6
European sovereign AI — Pharia and Luminous foundation models.
AIMLAPI
13
Unified API for 200+ AI models — chat, image, audio, video.
LlamaGate
16
Llama-family inference gateway with OpenAI-compatible endpoints.
GMI Cloud
17
Asia-Pacific GPU cloud with serverless inference for Llama and Qwen.
PublicAI
9
Open inference network — Llama, DeepSeek, Qwen with public-good routing.
GigaChat
8
Sber GigaChat — Russian-leading frontier chat models.

Browse by category

One-click into the directory above, scoped to a single modality.

Chat & reasoning

2848

Conversational and instruction-following models.

2678 priced · browse all →

Embeddings

151

Vector-encoding models for retrieval, clustering, and semantic search.

136 priced · browse all →

Image generation

373

Text-to-image and diffusion models.

323 priced · browse all →

Image edit

44

Inpainting, editing, and image-to-image.

44 priced · browse all →

Speech to text

89

Audio transcription and diarization.

14 priced · browse all →

Text to speech

43

Voice synthesis and TTS models.

22 priced · browse all →

Video generation

54

Text-to-video and image-to-video models.

7 priced · browse all →

Rerank

37

Cross-encoder rerankers for RAG pipelines.

35 priced · browse all →

Moderation

7

Content classification and policy enforcement.

0 priced · browse all →

OCR

20

Document and image text extraction.

1 priced · browse all →

Realtime audio

54

Streaming voice + tool-use over WebSocket.

47 priced · browse all →

Highest-ranked chat models on Chatbot Arena

Sorted by Chatbot Arena ELO (real human pairwise preference). Open the full directory →

Model Provider Input / 1M Output / 1M Blended Context
Gemini 4 Argon Google AI $2.00/M $10.00/M $4.00/M 1,048,576
Claude Opus 5.5 Anthropic $4.00/M $20.00/M $8.00/M 1,000,000
Claude Fable 5 Anthropic $10.00/M $50.00/M $20.00/M 1,000,000
Claude Fable 5.1 Anthropic $10.00/M $50.00/M $20.00/M 1,000,000
Claude Opus 4.6 Anthropic $5.00/M $25.00/M $10.00/M 1,000,000
Gemini 3.8 Flash Google AI $0.750/M $3.75/M $1.50/M 1,048,576
Claude Opus 4.7 Anthropic $5.00/M $25.00/M $10.00/M 1,000,000
Claude Opus 5 Anthropic $5.00/M $25.00/M $10.00/M 1,000,000
Gemini 3.7 Flash Google AI $0.750/M $3.75/M $1.50/M 1,048,576
Kimi K3 Moonshot AI $3.00/M $15.00/M $6.00/M 1,048,576
Gemini 3.1 Pro preview Google AI $2.00/M $12.00/M $4.50/M 1,048,576
Gemini 3 Pro Preview Google AI $2.00/M $12.00/M $4.50/M 1,048,576
GPT-5.6 Sol OpenAI $4.00/M $20.00/M $8.00/M 922,000
Gemini 3.6 Flash Google AI $0.750/M $3.75/M $1.50/M 1,048,576
GLM 5.3 Z.ai $1.40/M $4.40/M $2.15/M 1,000,000

FAQ

How many models does the directory cover?

3,917 models across 54+ providers — chat, embeddings, image generation, image edit, speech-to-text, text-to-speech, video generation, rerank, moderation, OCR, and realtime audio. Maxim and most competitors only cover chat models on a handful of providers.

How often is pricing updated?

Pricing is verified weekly from litellm + models.dev + OpenRouter, with the per-model "Last verified" timestamp shown on every page. If you spot an outdated rate, click "suggest edit" on the row — submissions land in our review queue and roll out on the next refresh.

How accurate are these prices?

We aggregate from public, version-controlled sources (BerriAI/litellm, models.dev, OpenRouter) and pull the most-recently-published number. We do NOT contractually guarantee accuracy — for production billing decisions, always confirm against the provider's own pricing page (linked on every model page).

Do you cover deprecated and upcoming models?

Yes — every model carries a `deprecation_date` when one is published by the provider. Models retiring in the next 180 days show a countdown badge; deprecated models still render with a clear notice and migration recommendations to a current alternative.

Can I get pricing for a model that isn't listed?

Click "Request a model" on the hub — submissions land in a public queue, ranked by community votes. Models with active demand get added within a few days. No sign-up required.

How do I route across providers without changing my code?

Use Future AGI's Agent Command Center — an open-source OpenAI-compatible gateway. One config supports cost-optimized routing, latency-aware retries, model fallback, shadow / mirror traffic, exact + semantic caching, and 18 built-in guardrail scanners. Free for the first 100K requests/month. The "Production recipe" block on every model page has a ready-to-paste config.

Route every model via Agent Command Center →
One OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.