Models

Every model, one key.

39 models from 8 makers, priced per token on the default plan and callable from the SDK you already use.

Sort

Anthropic: Claude Fable 5
A Mythos-class model for demanding reasoning and long-running autonomous work, with always-on adaptive thinking.
$10 / $50
anthropic/claude-fable-5Jun 9, 20261M contextanthropic
Anthropic: Claude Haiku 4.5
The fastest and cheapest model in the family, for high-volume work where latency matters more than depth.
$2 / $10
anthropic/claude-haiku-4-5Oct 15, 2025200K contextanthropic
Anthropic: Claude Opus 4.8
The previous Opus generation for complex reasoning and agentic work, superseded by Opus 5.
$10 / $50
anthropic/claude-opus-4-8May 28, 20261M contextanthropic
Anthropic: Claude Opus 5
Anthropic's flagship model for complex agentic coding and long-horizon professional work, with adaptive reasoning across a million-token window.
$5 / $25
anthropic/claude-opus-5Jul 24, 20261M contextanthropic
Anthropic: Claude Sonnet 4.6
The previous Sonnet generation for general coding and assistant workloads, superseded by Sonnet 5.
$6 / $30
anthropic/claude-sonnet-4-6Feb 17, 20261M contextanthropic
Anthropic: Claude Sonnet 5
A mid-tier model balancing latency against reasoning quality for everyday application and assistant work.
$4 / $20
anthropic/claude-sonnet-5Jun 30, 20261M contextanthropic
DeepSeek: DeepSeek V4 Flash
The faster, cheaper V4 tier with the same window and output ceiling as V4 Pro.
$0.88 / $2.64
deepseek/deepseek-v4-flashJul 31, 20261M contextopenai
DeepSeek: DeepSeek V4 Pro
The higher-capability V4 text model, with thinking mode on by default and a million-token window.
$2.64 / $7.92
deepseek/deepseek-v4-proAug 13, 20261M contextopenai
Google: Gemini 3 Flash Preview
The preview-channel Flash model, with the same multimodal input envelope as 3.5 Flash.
$1 / $6
google/gemini-3-flash-previewDec 17, 20251M contextopenai
Google: Gemini 3.5 Flash
A multimodal Flash model for agentic and coding work, taking text, images, audio, video, and documents.
$1 / $6
google/gemini-3.5-flashMay 19, 20261M contextopenai
Z.ai: GLM-4.5 Air
The lightweight, lower-priced member of the GLM-4.5 family.
$0.4 / $2.20
zai/glm-4.5-airJul 28, 2025128K contextopenai
Z.ai: GLM-4.5V
A vision-language model taking images, video, and documents alongside text.
$1.20 / $3.60
zai/glm-4.5vAug 11, 2025openai
Z.ai: GLM-4.7
A prior-generation text model for code generation and long-context understanding.
$1.20 / $4.40
zai/glm-4.7Dec 22, 2025200K contextopenai
Z.ai: GLM-5
The first GLM-5 generation for agentic engineering, with thinking mode.
$2 / $6.40
zai/glm-5Feb 12, 2026200K contextopenai
Z.ai: GLM-5 Turbo
A GLM-5 variant tuned for agent scenarios, emphasising tool calls over long execution chains.
$2.40 / $8
zai/glm-5-turbo200K contextopenai
Z.ai: GLM-5.1
A text model for autonomous multi-step execution, with planning and iterative refinement.
$2.80 / $8.80
zai/glm-5.1Apr 7, 2026200K contextopenai
Z.ai: GLM-5.2
A long-context text model aimed at long-horizon coding and engineering tasks.
$2.80 / $8.80
zai/glm-5.2Jun 16, 20261M contextopenai
Z.ai: GLM-5.3
The current GLM flagship for software engineering and agent workloads, with configurable reasoning effort.
$1.40 / $4.40
zai/glm-5.3Aug 18, 20261M contextopenai
OpenAI: GPT-4.1
A non-reasoning model oriented toward instruction following and tool calling at low latency.
$4 / $16
openai/gpt-4.1Apr 14, 20251M contextopenai
OpenAI: GPT-5.4
An earlier flagship reasoning model, priced below GPT-5.5.
$5 / $30
openai/gpt-5.4Mar 5, 20261.1M contextopenai
OpenAI: GPT-5.5
A prior flagship reasoning model for coding and professional work.
$5 / $30
openai/gpt-5.5Apr 24, 20261.1M contextopenai
OpenAI: GPT-5.6 Luna
The cost-optimised GPT-5.6 tier, built for high-volume workloads.
$0.2 / $1.20
openai/gpt-5.6-lunaJul 9, 20261.1M contextopenai
OpenAI: GPT-5.6 Sol
The flagship GPT-5.6 tier for complex professional work, with reasoning effort configurable from none to maximum.
$5 / $30
openai/gpt-5.6-solJul 9, 20261.1M contextopenai
OpenAI: GPT-5.6 Terra
The middle GPT-5.6 tier, trading some capability for a lower price.
$2 / $12
openai/gpt-5.6-terraJul 9, 20261.1M contextopenai
xAI: Grok 4.6
xAI's frontier model for coding, agentic tasks, and knowledge work, with four reasoning-effort levels.
$2 / $6
xai/grok-4.6Aug 12, 2026500K contextopenai
Moonshot AI: Kimi K2.6
A general-purpose multimodal model offering both thinking and non-thinking modes.
$1.90 / $8
moonshotai/kimi-k2.6Apr 21, 2026262K contextanthropicopenai
Moonshot AI: Kimi K2.7 Code
A coding-oriented multimodal model supporting extended reasoning.
$1.90 / $8
moonshotai/kimi-k2.7-codeJun 16, 2026262K contextanthropicopenai
Moonshot AI: Kimi K2.7 Code Highspeed
The higher-throughput serving variant of K2.7 Code, at twice the price.
$3.80 / $16
moonshotai/kimi-k2.7-code-highspeedJun 16, 2026262K contextanthropicopenai
Moonshot AI: Kimi K3
Moonshot's flagship multimodal model, with always-on reasoning and a selectable effort level.
$6 / $30
moonshotai/kimi-k3Jul 22, 20261M contextanthropicopenai
Qwen: Qwen Coder Plus
An earlier-generation programming and code-generation model.
$1 / $2.01
qwen/qwen-coder-plus129K contextopenai
Qwen: Qwen Flash
A speed- and cost-oriented model with switchable thinking mode.
$0.264 / $2.12
qwen/qwen-flash998K contextopenai
Qwen: Qwen Max
An earlier-generation flagship text model with a short window.
$6.34 / $31.60
qwen/qwen-max31K contextopenai
Qwen: Qwen Plus
The balanced tier, supporting function calling, structured output, and batch inference.
$2.12 / $6.34
qwen/qwen-plus998K contextopenai
Qwen: Qwen VL Max
The higher-capability vision-language tier, taking text, images, and video.
$1.60 / $6.40
qwen/qwen-vl-max129K contextopenai
Qwen: Qwen VL Plus
The balanced vision-language tier, taking text, images, and video.
$0.42 / $1.26
qwen/qwen-vl-plus129K contextopenai
Qwen: Qwen3 Coder Flash
The smaller Coder tier, with the same window and multi-turn tool use.
$0.6 / $3
qwen/qwen3-coder-flash998K contextopenai
Qwen: Qwen3 Coder Plus
A code model with agentic tool calling and repository-level understanding.
$2 / $10
qwen/qwen3-coder-plus998K contextopenai
Qwen: Qwen3.5 Flash
A lower-cost Qwen 3.5 tier taking text, images, and video.
$0.2 / $0.8
qwen/qwen3.5-flash992K contextopenai
Qwen: Qwen3.7 Max
The Qwen flagship, with hybrid thinking and non-thinking modes.
$5 / $15
qwen/qwen3.7-max992K contextopenai

One key, every model on this page.

Get an API key