Models

Top models from Anthropic, OpenAI, Moonshot & xAI through one API.
One key, one endpoint. Pay only for tokens - no subscriptions, no markup.

Claude Fable 5

claude-fable-5

Claude Opus 5

claude-opus-5

Claude Sonnet 5

claude-sonnet-5

Claude Haiku 4.5

claude-haiku-4-5

Grok 4.6

grok-4.6

GPT-5.6 Sol

gpt-5.6-sol

GPT-5.6 Terra

gpt-5.6-terra

GPT-5.6 Luna

gpt-5.6-luna

Kimi K3

k3

Kimi K2.7 Code

kimi-for-coding

Overview

Context

200K

500K

400K

256K

Max output

128K

64K

128K

64K

Throughput

~50 t/s

~60 t/s

~85 t/s

~130 t/s

~55 t/s

~65 t/s

~75 t/s

~120 t/s

~45 t/s

~60 t/s

Latency

~2.4s

~1.8s

~1.1s

~0.5s

~1.5s

~1.2s

~0.6s

~2s

~1.6s

Best for

Everyday tasks, chat, high-volume work

Hard tasks, agents, code, long reasoning

mdl_best_sonnet

Simple tasks, classification, bulk calls

Reasoning, code, agentic work — at half the price

General tasks, agents, tool use

Coding, long context, cost-efficient model

Pricing - per 1M tokens

Input

$10

$0.20

$0.95

Output

$50

$25

$10

$30

$12

$1.20

$15

Cache write

$12.50

$6.25

$2.50

$1.25

$6.25

$2.50

$0.25

$0.95

Cache read

$0.50

$0.20

$0.10

$0.50

$0.20

$0.02

$0.30

$0.19

Features

Streaming (SSE)

✓

Images (vision)

✓

Tools (function calling)

✓

Prompt caching

✓

One API - every model

Switch models with one model field - same key, same endpoint.

Get API key