Which AI model APIs can I compare?

The live directory lists the currently published models from providers such as OpenAI, Anthropic, Google, DeepSeek, Qwen, Meta, and others available in the catalogue.

What do the model prices mean?

Token models show input and output rates per one million tokens. Fixed or task models show a per-request or per-usage rate. Where length tiers apply, use the selector on the model card.

How do I choose a lower-cost model?

Compare models for the workload you actually need: context size, provider, input price, output price, and any length-tier pricing shown on the model page.

LIVE PRODUCTION PRICING

Model Directory & Live Pricing

Pay-as-you-go pricing directly mapped to upstream production models. Zero lock-in, zero monthly commitment.

Uptime

99.98%

Production SLA with automatic failover across channels, so service continues around the clock.

Flagship Foundation Models

Token and usage pricing in USD

GPT 6.1 Sol

OpenAI

84% off

Input

$2$0.338

1M tokens

Output

$10$1.69

1M tokens

Cache read / 1M $0.1$0.0169Cache write / 1M $2.5$0.4225

Claude Opus 5.5

Anthropic

82% off

Input

$4$0.728

1M tokens

Output

$20$3.64

1M tokens

Cache read / 1M $0.2$0.0364Cache write / 1M $5$0.91

Kimi K3.1 Pro

Moonshot AI

71% off

Input

$2$0.598

1M tokens

Output

$10$2.99

1M tokens

Cache read / 1M $0.2$0.0598Cache write / 1M $2$0.598

Grok 4.7

xAI

74% off

Input

$2$0.52

1M tokens

Output

$6$1.56

1M tokens

Cache read / 1M $0.5$0.13

DeepSeek V4.1 Flash 1017

NEW

DeepSeek

84% off

Input

$0.3$0.0507

1M tokens

Output

$1.2$0.2028

1M tokens

Cache read / 1M $0.007$0.001183

Gemini 4 Argon

Google

77% off

Input

$2$0.468

1M tokens

Output

$10$2.34

1M tokens

Cache read / 1M $0.1$0.0234

Glm 5.3

Z.AI

62% off

Input

$1.4$0.546

1M tokens

Output

$4.4$1.716

1M tokens

Cache read / 1M $0.26$0.1014Cache write / 1M $0$0

MiniMax M3.1 Flash

MiniMax

72% off

Input

$0.15$0.0429

1M tokens

Output

$0.6$0.1716

1M tokens

Cache read / 1M $0.015$0.00429

Muse Spark 1.3 Contributor

Qwen3.7 Plus

Qwen

35% off

Input

$0.4$0.26

1M tokens

Output

$1.6$1.04

1M tokens

Cache read / 1M $0.04$0.026Cache write / 1M $0.5$0.325

GPT 6.1 Terra

NEW

OpenAI

85% off

Input

$1$0.156

1M tokens

Output

$5$0.78

1M tokens

Cache read / 1M $0.05$0.0078Cache write / 1M $1.25$0.195

Claude Fable 5.1

Anthropic

81% off

Input

$10$1.95

1M tokens

Output

$50$9.75

1M tokens

Cache read / 1M $0.25$0.04875Cache write / 1M $12.5$2.4375

Kimi K3.1 Pro Highspeed

Moonshot AI

46% off

Input

$4$2.184

1M tokens

Output

$20$10.92

1M tokens

Cache read / 1M $0.2$0.1092Cache write / 1M $4$2.184

Grok 4.6

xAI

74% off

Input

$2$0.52

500K tokens

Output

$6$1.56

500K tokens

Cache read / 1M $0.5$0.13

DeepSeek V4.1 Flash

DeepSeek

89% off

Input

0.3$0.0351

1M tokens

Output

1.2$0.1404

1M tokens

Gemini 3.8 Flash

Google

82% off

Input

$0.75$0.1365

1M tokens

Output

$3.75$0.6825

1M tokens

Cache read / 1M $0.075$0.01365

Glm 5.3 Flash

Z.AI

61% off

Input

$0.15$0.0585

1M tokens

Output

$0.5$0.195

1M tokens

Cache read / 1M $0.03$0.0117Cache write / 1M $0$0

MiniMax M3

MiniMax

71% off

Input

$0.3$0.0897

1M tokens

Output

$1.2$0.3588

1M tokens

Cache read / 1M $0.06$0.01794

Muse Spark 1.2 Contributor

Qwen3.8 Flash

Qwen

35% off

Input

$0.15$0.0975

1M tokens

Output

$0.47$0.3055

1M tokens

Cache read / 1M $0.016$0.0104Cache write / 1M $0.2$0.13

GPT 6 Sol

OpenAI

85% off

Input

$2$0.312

1M tokens

Output

$10$1.56

1M tokens

Cache read / 1M $0.2$0.0312Cache write / 1M $2.5$0.39

Claude Haiku 5.5

Anthropic

71% off

Input

$0.1$0.0299

1M tokens

Output

$0.5$0.1495

1M tokens

Cache read / 1M $0.01$0.00299Cache write / 1M $0.125$0.037375

Kimi K3

Moonshot AI

65% off

Input

$3$1.053

1M tokens

Output

$15$5.265

1M tokens

Cache read / 1M $0.3$0.1053Cache write / 1M $3$1.053

DeepSeek V4 Pro

DeepSeek

55% off

Mon–Fri · 01:00–04:00 / 06:00–10:00 · UTC

Input

$1.32$0.6006

1M tokens

Output

$3.96$1.8018

1M tokens

Cache read / 1M $0.044$0.02002

Gemini 3.7 Flash

Google

82% off

Input

$0.75$0.1365

1M tokens

Output

$3.75$0.6825

1M tokens

Cache read / 1M $0.075$0.01365

Glm 5.2

Z.AI

62% off

Input

$1.4$0.546

1M tokens

Output

$4.4$1.716

1M tokens

Cache read / 1M $0.26$0.1014Cache write / 1M $0$0