Model catalog

One endpoint, every model. Compare context windows, capabilities and real per-token pricing side by side, then swap the model string in your request — nothing else changes.

472
Models: 48
Providers: 4
Free to try: $0.0001
Cheapest input / 1M

72 of 472 models

GPT-6 Astra
openai/gpt-6-astra
Language
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
Context
1.1M
In / 1M
$10.00
Out / 1M
$50.00
- Reasoning
- Tool use
- Vision
- +7
GPT-6 Astra (Fast)
openai/gpt-6-astra-fast
Language
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
Context
1.1M
In / 1M
$20.00
Out / 1M
$100
- Reasoning
- Tool use
- Vision
- +7
GPT 5.6 Luna
openai/gpt-5.6-luna
Language
GPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.
Context
1.1M
In / 1M
$0.200
Out / 1M
$1.20
- Reasoning
- Tool use
- Vision
- +7
GPT 5.6 Luna (Fast)
openai/gpt-5.6-luna-fast
Language
GPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost in the series.
Context
1.1M
In / 1M
$0.400
Out / 1M
$2.40
- Reasoning
- Tool use
- Vision
- +7
GPT 5.6 Sol
openai/gpt-5.6-sol
Language
GPT-5.6 Sol is the flagship of OpenAI's GPT-5.6 series, its most capable model for long-horizon agentic work across coding, biology, and cybersecurity.
Context
1.1M
In / 1M
$4.00
Out / 1M
$20.00
- Reasoning
- Tool use
- Vision
- +7
GPT 5.6 Sol (Fast)
openai/gpt-5.6-sol-fast
Language
GPT-5.6 Sol is the flagship of OpenAI's GPT-5.6 series, its most capable model for long-horizon agentic work across coding, biology, and cybersecurity.
Context
1.1M
In / 1M
$8.00
Out / 1M
$40.00
- Reasoning
- Tool use
- Vision
- +7
GPT 5.6 Terra
openai/gpt-5.6-terra
Language
GPT-5.6 Terra is a balanced GPT-5.6 model for everyday work, with performance comparable to the previous generation at half the cost.
Context
1.1M
In / 1M
$2.00
Out / 1M
$12.00
- Reasoning
- Tool use
- Vision
- +7
GPT 5.6 Terra (Fast)
openai/gpt-5.6-terra-fast
Language
GPT-5.6 Terra is a balanced GPT-5.6 model for everyday work, with performance comparable to the previous generation at half the cost.
Context
1.1M
In / 1M
$4.00
Out / 1M
$24.00
- Reasoning
- Tool use
- Vision
- +7
GPT-6.1 Sol
openai/gpt-6.1-sol
Language
GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support multi-step workflows.
Context
1.1M
In / 1M
$2.00
Out / 1M
$10.00
- Reasoning
- Tool use
- Vision
- +6
GPT-6.1 Sol (Fast)
openai/gpt-6.1-sol-fast
Language
GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support multi-step workflows.
Context
1.1M
In / 1M
$4.00
Out / 1M
$20.00
- Reasoning
- Tool use
- Vision
- +6
GPT-6 Luna
openai/gpt-6-luna
Language
GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.
Context
1.1M
In / 1M
$0.100
Out / 1M
$0.500
- Reasoning
- Tool use
- Vision
- +6
GPT-6 Luna (Fast)
openai/gpt-6-luna-fast
Language
GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.
Context
1.1M
In / 1M
$0.200
Out / 1M
$1.00
- Reasoning
- Tool use
- Vision
- +6
GPT-6 Sol
openai/gpt-6-sol
Language
GPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools make it suited to software development and multi-step automation.
Context
1.1M
In / 1M
$2.00
Out / 1M
$10.00
- Reasoning
- Tool use
- Vision
- +6
GPT-6 Sol (Fast)
openai/gpt-6-sol-fast
Language
GPT-6 Sol is OpenAI's reasoning model for complex coding and agentic workflows. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools make it suited to software development and multi-step automation.
Context
1.1M
In / 1M
$4.00
Out / 1M
$20.00
- Reasoning
- Tool use
- Vision
- +6
Qwen3.8 27B
alibaba/qwen3.8-27b
Language
Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.
Context
1M
In / 1M
$0.500
Out / 1M
$3.00
- Reasoning
- Tool use
- Vision
- +6
Kimi K3
moonshotai/kimi-k3
Language
Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
Context
1M
In / 1M
$3.00
Out / 1M
$15.00
- Reasoning
- Tool use
- Vision
- +6
Claude Opus 5.5
anthropic/claude-opus-5.5
Language
Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic tasks, knowledge work, communication, and vision. It is more token-efficient per completed task and reports progress, findings, and next steps in clear language.
Context
1M
In / 1M
$4.00
Out / 1M
$20.00
- Reasoning
- Tool use
- Vision
- +5
Claude Opus 5.5 (Fast)
anthropic/claude-opus-5.5-fast
Language
Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic tasks, knowledge work, communication, and vision. It is more token-efficient per completed task and reports progress, findings, and next steps in clear language.
Context
1M
In / 1M
$8.00
Out / 1M
$40.00
- Reasoning
- Tool use
- Vision
- +5
Claude Opus 5
anthropic/claude-opus-5
Language
Claude Opus 5 is the latest model in Anthropic's Opus family and a step-change improvement over Opus 4.8. It delivers major gains over Opus 4.8 in agentic coding, professional knowledge work, and long-horizon reasoning, and it is stronger per token across effort levels.
Context
1M
In / 1M
$5.00
Out / 1M
$25.00
- Reasoning
- Tool use
- Vision
- +5
Claude Opus 5 (Fast)
anthropic/claude-opus-5-fast
Language
Claude Opus 5 is the latest model in Anthropic's Opus family and a step-change improvement over Opus 4.8. It delivers major gains over Opus 4.8 in agentic coding, professional knowledge work, and long-horizon reasoning, and it is stronger per token across effort levels.
Context
1M
In / 1M
$10.00
Out / 1M
$50.00
- Reasoning
- Tool use
- Vision
- +5
Claude Opus 4.8
anthropic/claude-opus-4.8
Language
Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic's best generally available model for coding, agentic tasks, and enterprise workflows. It builds on the strengths of previous Opus models with stronger performance on complex, multi-step coding tasks. Anthropic recommends using it on long-horizon coding and agentic tasks. It is also stronger on professional work, including document drafting, data analysis, and presentations.
Context
1M
In / 1M
$5.00
Out / 1M
$25.00
- Reasoning
- Tool use
- Vision
- +5
Claude Opus 4.8 (Fast)
anthropic/claude-opus-4.8-fast
Language
Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic's best generally available model for coding, agentic tasks, and enterprise workflows. It builds on the strengths of previous Opus models with stronger performance on complex, multi-step coding tasks. Anthropic recommends using it on long-horizon coding and agentic tasks. It is also stronger on professional work, including document drafting, data analysis, and presentations.
Context
1M
In / 1M
$10.00
Out / 1M
$50.00
- Reasoning
- Tool use
- Vision
- +5
Claude Haiku 5.5
anthropic/claude-haiku-5.5
Language
Claude Haiku 5.5 brings adaptive reasoning to Anthropic’s low-cost Haiku family for everyday tasks, tool use, and scaled sub-agent deployments. It is the first Haiku with adjustable effort levels, letting developers balance reasoning depth and token usage for each task, with the option to turn thinking off for simpler requests.
Context
1M
In / 1M
$0.100
Out / 1M
$0.500
- Reasoning
- Tool use
- Vision
- +4
GPT-6.1 Sol (Batch)
openai/gpt-6.1-sol-batch
Language
GPT-6.1 Sol is OpenAI's reasoning model for complex coding, computer use, and professional work. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support multi-step workflows.
Context
1.1M
In / 1M
$1.00
Out / 1M
$5.00
- Reasoning
- Tool use
- Vision
- +4

Showing 24 of 72