Explore Models →
Model Observatory • 92 Index Items

AI Model Pricing & Token Cost Observatory

Granular input/output token pricing, batch scheduling discounts, cache write multipliers, and self-hosted GPU breakeven analysis.

Augment Code
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
BGE M3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
BGE Reranker Large
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cartesia Sonic Multilingual
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cartesia Sonic
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Claude 3.7 Sonnet Hybrid
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Claude 3.7 Sonnet
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Claude 3.7 Sonnet Thinking
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Claude Code Cli
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Claude Haiku 3.5
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cloudflare D1
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Codestral 22B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Codestral
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cohere Command R Plus
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cohere Command R Plus
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cohere Embed V3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Cohere Rerank 3.5
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Command R 08.2024
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Command R
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Continue Dev
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Continue Dev
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Convex Backend
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Deepgram Aura TTS
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Deepgram Nova 3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek Coder V2
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek R1 Distill 14B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek R1 Distill 32B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek R1 Distill 70B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek R1 Distill 8B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek R1
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek R1 Zero
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek V3 1
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
DeepSeek V3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
ElevenLabs Flash V2 5
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Flux 1
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 1.5 Flash
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 1.5 Pro
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 2.0 Flash Lite
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 2.0 Pro Exp
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 2.5 Pro
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 2 Flash
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 2 Flash Thinking
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gemini 4 Argon
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Google Gemini 2 Flash Thinking
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gpt 4o Mini
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Gpt 4o
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Grok 3 Mini
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Grok 3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Hailuo AI Video
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Hume AI Evi
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Jina Embeddings V3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Jina Reranker V2
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Kling AI API
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Llama 3.1 405B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Llama 3.3 70B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Luma Dream Machine API
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
MiniMax Video 01
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Mistral Large 2
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Mistral Small 3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Mixedbread Mxbai Embed Large
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Mongodb Atlas
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Neon Postgres
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
o1
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
o3 Mini
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
OpenAI o1 Pro
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
OpenAI Realtime API
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
OpenAI Text Embedding 3 Large
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
OpenAI Text Embedding 3 Small
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Phi 4
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Pixtral 12B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Pixtral Large
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Planetscale
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Qwen 2.5 72B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Qwen 2.5 Coder 14B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Qwen 2.5 Coder 32B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Qwen 2.5 Coder 7B
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Qwen 2.5 Max
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
QwQ 32B Preview
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Runway Gen 3 API
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Supabase Explained
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Turso Database
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Upstash Redis
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Void Editor
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Voyage AI Voyage 3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Voyage Code 3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Voyage Finance 2
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Voyage Law 2
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Voyage Multimodal 3
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Wan 2.1 API
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Whisper Large V3 Turbo
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Windsurf Cascade
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →
Windsurf Cascade
Live 2026 pricing rates, unit token economics, throughput latency, and architectural trade-offs.
Explore Benchmark →

Related Architecture Benchmarks & Rate Cards

Verified Context
About CheckAPICost Independent Research Observatory Topical sibling cross-reference within the root domain cluster AI Architecture & Cost Optimization Guides Topical sibling cross-reference within the root domain cluster Frontier LLM Token Pricing & Latency Matrix Topical sibling cross-reference within the root domain cluster Cloud & AI Inference Provider Pricing Hub Topical sibling cross-reference within the root domain cluster AI Model Head-to-Head Showdowns Topical sibling cross-reference within the root domain cluster
4.9 out of 5
★★★★★
Developer Community Benchmark Rating
Verified across 164 community production token & cost audits
Rate this benchmark: