Model catalogue

Every model in rotation, grouped by the provider it comes from. Prices are per 1M tokens in USD and match what you are billed; the pricing page shows the provider's list price beside ours.

Anthropic

Claude Fable 5 — $3.00 in / $14.60 out per 1M tokens · 1M context · 70% off
Claude Opus 4.8 — $1.60 in / $8.00 out per 1M tokens · 1M context · 68% off
Claude Sonnet 5 — $0.60 in / $3.10 out per 1M tokens · 1M context · 80% off
Claude Fable 5.1 — $2.40 in / $12.00 out per 1M tokens · 1M context · 76% off
Claude Haiku 4.5 — $0.34 in / $1.70 out per 1M tokens · 200K context · 66% off
Claude Haiku 4.5 — $1.00 in / $5.00 out per 1M tokens · 200K context
Claude Opus 4.6 — $5.00 in / $25.00 out per 1M tokens · 1M context
Claude Opus 4.7 — $5.00 in / $25.00 out per 1M tokens · 1M context
Claude Opus 5 — $1.05 in / $5.25 out per 1M tokens · 1M context · 79% off
Claude Opus 5.5 — $1.04 in / $5.20 out per 1M tokens · 1M context · 74% off
Claude Sonnet 4.6 — $0.60 in / $3.00 out per 1M tokens · 1M context · 80% off

Google

Gemini 3.1 Pro (Preview) — $0.35 in / $2.10 out per 1M tokens · 2M context · 83% off
Gemini 3.1 Flash Image — $0.30 in / $1.80 out per 1M tokens · 1M context · 80% off
Gemini 3.5 Flash — $0.30 in / $1.80 out per 1M tokens · 1M context · 80% off
Gemini 3.5 Flash-Lite — $0.069 in / $0.57 out per 1M tokens · 1M context · 77% off
Gemini 3.6 Flash — $0.32 in / $1.57 out per 1M tokens · 1M context · 79% off
Gemini 3.7 Flash — $0.28 in / $1.42 out per 1M tokens · 1M context · 81% off
Gemini 3.8 Flash — $0.27 in / $1.35 out per 1M tokens · 1M context · 82% off

OpenAI

GPT-5.5 — $0.70 in / $4.00 out per 1M tokens · 1M context · 86% off
GPT-5.6 Sol — $0.65 in / $3.90 out per 1M tokens · 1M context · 87% off
GPT-5.4 — $0.35 in / $2.10 out per 1M tokens · 1M context · 86% off
GPT-5.4 mini — $0.11 in / $0.66 out per 1M tokens · 1M context · 85% off
GPT-5.6 Luna — $0.14 in / $0.80 out per 1M tokens · 1M context · 86% off
GPT-5.6 Terra — $0.35 in / $2.00 out per 1M tokens · 1M context · 86% off
GPT-6 Luna — $0.011 in / $0.055 out per 1M tokens · 1M context · 89% off
GPT-6 Sol — $0.22 in / $1.10 out per 1M tokens · 1M context · 89% off

DeepSeek

DS DeepSeek Flash — $0.15 in / $0.60 out per 1M tokens · 1M context
DS DeepSeek Flash (free) — $0.0015 in / $0.006 out per 1M tokens · 1M context · 99% off
DS DeepSeek V4 Flash — $0.14 in / $0.28 out per 1M tokens · 1M context
DS DeepSeek V4 Flash (free) — $0.0014 in / $0.0028 out per 1M tokens · 1M context · 99% off
DS DeepSeek V4 Flash Vision — $0.22 in / $0.66 out per 1M tokens · 1M context
DS DeepSeek V4 Pro — $0.55 in / $1.10 out per 1M tokens · 1M context
DS DeepSeek V4 Pro (0425) — $0.43 in / $0.87 out per 1M tokens · 1M context

GLM

GLM GLM-5.2 — $1.70 in / $5.30 out per 1M tokens · 1M context
GLM-5.3 — $1.40 in / $4.40 out per 1M tokens · 1M context
GLM-5.3 Flash — $0.70 in / $2.20 out per 1M tokens · 1M context
GLM-5.3 Flash (free) — $0.007 in / $0.022 out per 1M tokens · 1M context · 99% off

Moonshot

Kimi K3 — $0.75 in / $3.75 out per 1M tokens · 1M context · 75% off
Kimi K3 (1M) — $0.75 in / $3.75 out per 1M tokens · 1M context · 75% off

xAI

Grok 4.6 — $0.40 in / $1.20 out per 1M tokens · 500K context · 80% off

Using these models

Point a client at the OpenAI-compatible endpoint with any id above, or use the protocol the family prefers — models & routing has the matrix and the API reference has the request shapes.