A static page for every model

Browse model API pages grouped by provider, with context windows and snapshot prices. Pay per request over x402 in USDC on Base or Solana.

Model directory

Live filterable model table. Prices and availability can change; each model page identifies its snapshot.

Aion Labs

Aion 3.0 — 128,000 token context window
Aion 3.0 Mini — 128,000 token context window
Aion 2.0 — 128,000 token context window

Alibaba

Qwen 2.5 7B — 32,000 token context window
Qwen 3.6 35B A3B (E2EE) — 128,000 token context window
Qwen 3.6 35B A3B Uncensored (E2EE) — 128,000 token context window
Qwen 3.7 Max — 256,000 token context window
Qwen 3.7 Plus — 256,000 token context window
Qwen 3 235B A22B Instruct 2507 — 128,000 token context window
Qwen 3 235B A22B Thinking 2507 — 128,000 token context window
Qwen3 30B A3B — 256,000 token context window
Qwen 3.5 35B A3B — 256,000 token context window
Qwen 3.5 9B — 256,000 token context window
Qwen 3.6 35B A3B — 262,144 token context window
Qwen 3 Coder 480b — 256,000 token context window
Qwen 3 Coder 480B Turbo — 256,000 token context window
Qwen 3 Next 80b — 256,000 token context window
Qwen3 VL 235B — 256,000 token context window
Qwen3 VL 30B A3B — 128,000 token context window
Qwen 3.5 397B — 128,000 token context window
Qwen3.5 Flash — 1,000,000 token context window
Qwen3.5 Plus — 1,000,000 token context window
Qwen 3.6 27B — 256,000 token context window
Qwen 3.6 Plus Uncensored — 1,000,000 token context window
Qwen: Qwen3.7 Flash — 1,000,000 token context window

Anthropic

Claude Fable 5 — 1,000,000 token context window
Claude Fable 5.1 — 1,000,000 token context window
Claude Haiku 4.5 — 200,000 token context window
Claude Haiku 5.5 — 100,000 token context window
Claude Opus 4.8 Fast — 1,000,000 token context window
Claude Opus 4.5 — 198,000 token context window
Claude Opus 4.6 — 1,000,000 token context window
Claude Opus 4.7 — 1,000,000 token context window
Claude Opus 4.8 — 1,000,000 token context window
Claude Opus 5 — 1,000,000 token context window
Claude Opus 5 (Fast) — 1,000,000 token context window
Claude Opus 5.5 — 1,000,000 token context window
Claude Sonnet 4.5 — 198,000 token context window
Claude Sonnet 4.6 — 1,000,000 token context window
Claude Sonnet 5 — 1,000,000 token context window
Claude Sonnet 5.5 — 1,000,000 token context window

ByteDance Seed

Seed 2.1 Turbo — 256,000 token context window
ByteDance Seed: Seed-2.0-Code — 262,144 token context window

Cohere

Cohere: Command A+ — 192,000 token context window

DeepSeek

DeepSeek R1 — 160,000 token context window
DeepSeek V3.1 — 128,000 token context window
DeepSeek V3.2 — 160,000 token context window
DeepSeek V4 Flash — 1,000,000 token context window
DeepSeek V4 Flash 0731 — 1,048,576 token context window
DeepSeek V4 Flash 0731 Fast — 1,000,000 token context window
DeepSeek: DeepSeek V4 Flash Vision Exp — 1,048,576 token context window
DeepSeek V4 Pro — 1,000,000 token context window
DeepSeek V4 Pro 0813 — 1,048,576 token context window
DeepSeek V4.1 Flash — 1,048,576 token context window
DeepSeek V4.1 Flash 1017 — 1,048,576 token context window
DeepSeek V4.1 Flash Uncensored — 1,048,576 token context window
DeepSeek V4 Flash E2EE — 1,000,000 token context window

Elorian

Elorian: Glimpse — 262,144 token context window

Fireworks

Fireworks: Ember-1 — 1,048,576 token context window

Google

Gemma 3 27B E2EE — 40,000 token context window
Gemma 4 26B A4B Uncensored (E2EE) — 262,144 token context window
Gemma 4 31B (E2EE) — 262,144 token context window
Gemini 2.5 Flash — 1,048,576 token context window
Gemini 2.5 Pro — 1,048,576 token context window
Gemini 3.5 Flash — 1,000,000 token context window
Gemini 3.5 Flash Lite — 1,000,000 token context window
Gemini 3.6 Flash — 1,000,000 token context window
Gemini 3 Flash Preview — 256,000 token context window
Gemini 3.1 Flash Lite — 1,048,576 token context window
Gemini 3.1 Pro — 1,048,576 token context window
Gemini 3.1 Pro Preview — 1,000,000 token context window
Gemini 3.7 Flash — 1,048,576 token context window
Gemini 3.8 Flash — 1,048,576 token context window
Google: Gemini 4 Argon — 1,048,576 token context window
Gemma 3 12B IT — 128,000 token context window
Gemma 3 27B — 40,000 token context window
Gemma 3 4B IT — 128,000 token context window
Gemma 4 26B A4B IT — 262,144 token context window
Gemma 4 31B — 256,000 token context window
Gemma 4 31B IT — 262,144 token context window
Gemma 4 E2B — 128,000 token context window
Gemma 4 Uncensored — 256,000 token context window

Inception

Inception: Mercury 2.5 — 260,000 token context window
Mercury 3 — 1,000,000 token context window

Inception Labs

Mercury 2 — 128,000 token context window

LiquidAI

LiquidAI: LFM2.5-24B-A2B — 128,000 token context window

MiniMax

MiniMax M2 — 1,000,000 token context window
MiniMax M2.1 — 198,000 token context window
MiniMax M2.5 — 198,000 token context window
MiniMax M2.7 — 198,000 token context window
MiniMax M2.7 Highspeed — 204,800 token context window
MiniMax M3 — 200,000 token context window
MiniMax M3 Preview — 524,288 token context window

Mistral

Mistral: Mistral Large 4 — 524,288 token context window

Mistral AI

Devstral 2 123B — 256,000 token context window
Magistral Small 2509 — 128,000 token context window
Ministral 14B 3.0 — 128,000 token context window
Ministral 3B — 128,000 token context window
Ministral 3 8B — 128,000 token context window
Venice Medium — 128,000 token context window
Mistral Large 3 — 256,000 token context window
Mistral Small 3.2 24B Instruct — 256,000 token context window
Mistral Small 4 — 256,000 token context window

Moondream

Moondream: Moondream 3 Preview — 32,000 token context window
Moondream: Moondream 3.1 — 32,000 token context window

Moonshot

Kimi K2 — 256,000 token context window
Kimi K2 Thinking — 256,000 token context window
Kimi K2.5 — 256,000 token context window
Kimi K2.6 — 256,000 token context window
Kimi K2.7 Code — 262,144 token context window
Kimi K3 — 1,000,000 token context window
Kimi K3 Fast — 1,000,000 token context window

MoonshotAI

Kimi K3.1 Pro — 1,048,576 token context window

NVIDIA

NVIDIA: Nemotron 3.5 Super VL — 262,144 token context window
NVIDIA Nemotron 3 Nano 30B — 128,000 token context window
NVIDIA Nemotron 3 Super 120B — 256,000 token context window
NVIDIA Nemotron 3 Ultra 550B — 1,000,000 token context window
NVIDIA Nemotron Nano 12B v2 VL BF16 — 128,000 token context window
NVIDIA Nemotron Nano 9B v2 — 128,000 token context window

OpenAI

GPT OSS 120B — 128,000 token context window
GPT OSS 20B — 128,000 token context window
GPT-4o — 128,000 token context window
GPT-4o Mini — 128,000 token context window
GPT 5 Mini — 400,000 token context window
GPT 5 Nano — 400,000 token context window
GPT-5.2 — 256,000 token context window
GPT-5.2 Codex — 256,000 token context window
GPT-5.3 Codex — 400,000 token context window
GPT-5.4 — 1,000,000 token context window
GPT-5.4 Mini — 400,000 token context window
GPT 5.4 Nano — 400,000 token context window
GPT-5.4 Pro — 1,000,000 token context window
GPT-5.5 — 1,000,000 token context window
GPT-5.5 Pro — 1,000,000 token context window
GPT-5.6 Luna — 1,050,000 token context window
GPT-5.6 Luna Pro — 1,050,000 token context window
GPT-5.6 Sol — 1,050,000 token context window
GPT-5.6 Sol Pro — 1,050,000 token context window
GPT-5.6 Terra — 1,050,000 token context window
GPT-5.6 Terra Pro — 1,050,000 token context window
GPT-6 Astra — 1,050,000 token context window
GPT-6 Luna — 1,050,000 token context window
GPT-6 Luna Pro — 1,050,000 token context window
GPT-6 Sol — 1,050,000 token context window
GPT-6 Sol Pro — 1,050,000 token context window
GPT-6.1 Sol — 1,050,000 token context window
OpenAI: GPT-6.1 Sol Pro — 1,050,000 token context window
OpenAI: GPT-6.1 Terra — 1,050,000 token context window
OpenAI: GPT-6.1 Terra Pro — 1,050,000 token context window
OpenAI GPT OSS 120B — 128,000 token context window
gpt-oss-20b — 128,000 token context window
GPT OSS Safeguard 120B — 128,000 token context window
GPT OSS Safeguard 20B — 128,000 token context window

Particle AI

Particle AI: Particle-1 — 1,048,576 token context window

Qwen

Qwen 3.8 27B — 262,144 token context window
Qwen3 32B — 32,000 token context window
Qwen3 Coder 30B A3B Instruct — 256,000 token context window
Qwen3 Coder Next — 256,000 token context window
Qwen3 VL 235B A22B — 256,000 token context window
Qwen3.8 2.4T A95B — 1,000,000 token context window
Qwen3.8 Flash — 1,000,000 token context window
Qwen: Qwen3.8 Max (0902) — 1,000,000 token context window
Qwen: Qwen3.8 Max Prime — 1,000,000 token context window
Qwen: Qwen3.8 Omni Flash — 1,000,000 token context window

Reflection

Reflection: Beam 1.0 501B A23B — 1,048,576 token context window

SpaceXAI

Grok 4.6 — 500,000 token context window
Grok 4.7 — 500,000 token context window

Tencent

Tencent HY3 — 262,144 token context window

Unbiased

Pareto 26.9 — 262,144 token context window

Venice AI

Venice Uncensored 1.2 — 128,000 token context window
Venice Role Play Uncensored — 128,000 token context window

Writer

Palmyra Vision 7B — 4,000 token context window

Xiaomi

MiMo-V2.5-Pro — 1,050,000 token context window
MiMo-V2.6-Flash — 1,048,576 token context window
MiMo-V2.6-Pro — 1,048,576 token context window
MiMo-V2.6-Pro-UltraSpeed — 1,048,576 token context window
MiMo-V2.5 — 1,000,000 token context window

Z.ai

GLM 5.2 E2EE — 524,288 token context window
GLM 4.5 — 128,000 token context window
GLM 4.6 — 198,000 token context window
GLM 4.7 — 128,000 token context window
GLM 4.7 Flash — 198,000 token context window
GLM 5 — 198,000 token context window
GLM 5.1 — 200,000 token context window
GLM 5.2 — 1,048,576 token context window
GLM 5.3 — 1,000,000 token context window
GLM 5.3 Flash — 1,048,576 token context window
Z.ai: GLM 5.3 FlashX — 1,048,576 token context window
Z.ai: GLM 5.3 Prime — 1,000,000 token context window

Zhipu AI

GLM 5.1 E2EE — 200,000 token context window
GLM 4.5 Air — 128,000 token context window
GLM 4.7 Flash Heretic — 200,000 token context window
GLM-5 Turbo — 200,000 token context window
GLM 5V Turbo — 200,000 token context window

inclusionAI

inclusionAI: Ling 3.1 Flash — 262,144 token context window

xAI

Grok 4.20 Beta — 2,000,000 token context window
Grok 4.20 Multi-Agent Beta — 2,000,000 token context window
Grok 4.3 — 1,000,000 token context window
Grok 4.5 — 500,000 token context window
Grok Build 0.1 — 256,000 token context window