Roster · Flat Rates · 44 Models
Thirty-plus masters across every great school — each with an honest flat rate on the wall, up to 30× below the direct APIs. Pick the one whose vibe fits your task.
OpenAI
The Headmaster of First Drafts
Trained ten thousand katas before sunrise. Whatever you throw at him, he writes a polite reply, then another, then a sonnet about it.
Anthropic
The Diplomat in the Bamboo Forest
Never raises his voice, never breaks a vase. He'll explain why your idea won't work, suggest a kinder one, and pour you tea while you decide.
The Many-Faced Onmyōji
Can shapeshift into text, image, or video on command. Carries a satchel of bananas (Nano™) and a film reel (Veo). Nobody asks where the bananas come from.
xAI
The Unfiltered Ronin
Wanders in from the desert, says exactly what it thinks, and occasionally checks what's happening on X mid-sentence.
MoonshotAI
The Midnight Code Sensei
Sleeps by day, ships by night. Hand it a broken build at 3am — it returns green CI and a note: 'also refactored your tests.'
Perplexity
The All-Seeing Librarian
Never answers from memory alone — sprints to the archives mid-question and returns with citations stapled to everything.
Deepseek
The Frugal River Monk
Meditates underwater for hours, surfaces with the answer. Doesn't charge extra for the dramatic silence.
Xiaomi MiMo
The Lightning Apprentice
Two characters, one mission: deliver tokens before the kettle whistles.
MiniMax
The Kabuki Stage Master
Every reply is a performance. Long, expressive, occasionally wears a mask. Standing ovations encouraged.
Qwen
The Wandering Polyglot
Speaks 200 dialects, including JSON. Carries a scroll of every language he's ever met — and he's met them all.
Z.ai
The Last Letter of the Alphabet
Arrives last, leaves a mark. GLM-5.1 lands the closing blow when everyone else has packed up for the night.
Nvidia
The Forge Master
Built in the same forge as the GPUs it runs on. Answers arrive slightly warm.
Grab an API key — every model on this page answers to the same single endpoint, at the same single price.
Rate Card · No Surprises
Flat per-model rates, billed per 1M tokens — input and output priced separately. Images are a flat price per generated picture. What you see here is exactly what the API bills.
| Model ID | Name | Input / 1M | Output / 1M |
|---|---|---|---|
anthropic/claude-haiku-4.5 | Claude Haiku 4.5 | $0.18 | $0.9 |
anthropic/claude-sonnet-4.6 | Claude Sonnet 4.6 | $0.54 | $2.7 |
anthropic/claude-sonnet-5 | Claude Sonnet 5 | $0.36 | $1.8 |
anthropic/claude-opus-4.6 | Claude Opus 4.6 | $0.8 | $0.8 |
anthropic/claude-opus-4.7 | Claude Opus 4.7 | $0.8 | $0.8 |
anthropic/claude-opus-4.8 | Claude Opus 4.8 | $0.8 | $0.8 |
anthropic/claude-fable-5 | Claude Fable 5 | $6 | $30 |
openai/gpt-5.4-mini | GPT 5.4 Mini | $0.045 | $0.27 |
openai/gpt-5.3-codex-spark | GPT 5.3 Codex Spark | $0.09 | $0.27 |
openai/gpt-5.4 | GPT 5.4 | $0.15 | $0.9 |
openai/gpt-5.5 | GPT 5.5 | $0.18 | $0.72 |
openai/gpt-5.6-luna | GPT 5.6 Luna | $0.06 | $0.36 |
openai/gpt-5.6-terra | GPT 5.6 Terra | $0.15 | $0.9 |
openai/gpt-5.6-sol | GPT 5.6 Sol | $0.3 | $1.8 |
google/gemini-3.1-flash-lite | Gemini 3.1 Flash Lite | $0.3 | $0.9 |
google/gemini-3-flash-preview | Gemini 3 Flash | $0.45 | $1.65 |
google/gemini-3.5-flash | Gemini 3.5 Flash | $1.2 | $4.2 |
google/gemini-3.1-pro-preview | Gemini 3.1 Pro Preview | $1.65 | $4.95 |
google/gemma-4-31b-it | Gemma 4 31B | $0.3 | $0.6 |
deepseek/deepseek-v4-flash | Deepseek V4 Flash | $0.0284 | $0.0568 |
deepseek/deepseek-v4-pro | Deepseek V4 Pro | $0.137 | $0.274 |
minimax/minimax-m3 | MiniMax M3 | $0.0946 | $0.378 |
minimax/minimax-m2.7 | MiniMax M2.7 | $0.3 | $0.9 |
moonshotai/kimi-k2.6 | Kimi K2.6 | $0.208 | $1.0742 |
moonshotai/kimi-k2.7-code | Kimi K2.7 Code | $0.2332 | $1.1026 |
moonshotai/kimi-k2.7-code-highspeed | Kimi K2.7 Code Highspeed | $1.2 | $4.2 |
nvidia/nemotron-3-ultra | Nemotron 3 Ultra | $0.45 | $1.5 |
perplexity/sonar | Sonar | $1.5 | $1.5 |
perplexity/sonar-pro | Sonar Pro | $1.8 | $8.4 |
perplexity/sonar-reasoning-pro | Sonar Reasoning Pro | $1.5 | $4.8 |
qwen/qwen3.7-plus | Qwen 3.7 Plus | $0.1008 | $0.4032 |
qwen/qwen3.7-max | Qwen 3.7 Max | $0.3938 | $1.1812 |
x-ai/grok-4.1-fast | Grok 4.1 Fast | $0.27 | $0.33 |
x-ai/grok-4.3 | Grok 4.3 | $0.9 | $1.8 |
x-ai/grok-4.5 | Grok 4.5 | $1.5 | $3.75 |
xiaomi/mimo-v2.5 | MiMo V2.5 | $0.033 | $0.0882 |
xiaomi/mimo-v2.5-pro | MiMo V2.5 Pro | $0.137 | $0.274 |
z-ai/glm-5.1 | GLM 5.1 | $0.3042 | $0.9564 |
z-ai/glm-5.2 | GLM 5.2 | $0.2836 | $0.901 |
anthropic/claude-haiku-4.5anthropic/claude-sonnet-4.6anthropic/claude-sonnet-5anthropic/claude-opus-4.6anthropic/claude-opus-4.7anthropic/claude-opus-4.8anthropic/claude-fable-5openai/gpt-5.4-miniopenai/gpt-5.3-codex-sparkopenai/gpt-5.4openai/gpt-5.5openai/gpt-5.6-lunaopenai/gpt-5.6-terraopenai/gpt-5.6-solgoogle/gemini-3.1-flash-litegoogle/gemini-3-flash-previewgoogle/gemini-3.5-flashgoogle/gemini-3.1-pro-previewgoogle/gemma-4-31b-itdeepseek/deepseek-v4-flashdeepseek/deepseek-v4-prominimax/minimax-m3minimax/minimax-m2.7moonshotai/kimi-k2.6moonshotai/kimi-k2.7-codemoonshotai/kimi-k2.7-code-highspeednvidia/nemotron-3-ultraperplexity/sonarperplexity/sonar-properplexity/sonar-reasoning-proqwen/qwen3.7-plusqwen/qwen3.7-maxx-ai/grok-4.1-fastx-ai/grok-4.3x-ai/grok-4.5xiaomi/mimo-v2.5xiaomi/mimo-v2.5-proz-ai/glm-5.1z-ai/glm-5.2| Model ID | Name | Per image |
|---|---|---|
openai/gpt-image-2 | GPT Image 2 | $0.036 |
openai/gpt-image-2-edit | GPT Image 2 Edit | $0.036 |
google/gemini-3.1-flash-lite-image | Gemini 3.1 Flash Lite Image | $0.024 |
google/gemini-3.1-flash-image-preview | Gemini 3.1 Flash Image | $0.015 |
google/gemini-3-pro-image | Gemini 3 Pro Image | $0.028 |
openai/gpt-image-2openai/gpt-image-2-editgoogle/gemini-3.1-flash-lite-imagegoogle/gemini-3.1-flash-image-previewgoogle/gemini-3-pro-imageMachine-readable version with the same prices: GET /v1/models