OpenAI's GPT API models on APIMart: the GPT-6 family (Astra, 6.1 Sol, 6.1 Terra and Luna), GPT-5.6, the Codex models and o-series reasoning models through one OpenAI-compatible API key.
Service Highlights
Guides, comparisons and pricing analysis from the APIMart blog.
What's on your mind?
Ask APIMart
gpt-6.1-terra
Transparent pricing with no hidden fees. Pay only for what you use.
Per 1M tokens
Up to 272,000 input tokens
| Rate | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|
| Input | 8~$0.8 | 7.6~$0.76 | 7.2~$0.72 | 10~$1 | 20% |
| Cached input | 0.4~$0.04 | 0.38~$0.038 | 0.36~$0.036 | 0.5~$0.05 | 20% |
| Cache write (30 min) | 10~$1 | 9.5~$0.95 | 9~$0.9 | 12.5~$1.25 | 20% |
| Cache write (12 hr) | 20~$2 | 19~$1.9 | 18~$1.8 | 25~$2.5 | 20% |
| Output | 40~$4 | 38~$3.8 | 36~$3.6 | 50~$5 | 20% |
Over 272,000 input tokens
| Rate | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|
| Input | 16~$1.6 | 15.2~$1.52 | 14.4~$1.44 | 20~$2 | 20% |
| Cached input | 0.8~$0.08 | 0.76~$0.076 | 0.72~$0.072 | 1~$0.1 | 20% |
| Cache write (30 min) | 20~$2 | 19~$1.9 | 18~$1.8 | 25~$2.5 | 20% |
| Cache write (12 hr) | 40~$4 | 38~$3.8 | 36~$3.6 | 50~$5 | 20% |
| Output | 60~$6 | 57~$5.7 | 54~$5.4 | 75~$7.5 | 20% |
Call OpenAI's current GPT-6 family on APIMart: GPT-6 Astra for the hardest work, GPT-6.1 Sol for near-Astra results at a lower price, GPT-6.1 Terra for visual reasoning and writing, and GPT-6 Luna for high-volume tasks. Use Chat Completions or the Responses API with the same key and pay per token.
50K+
Active Users
99.9%
Uptime
2x
Faster
70%
Cost Savings
Pick the GPT-6 model that fits each job, then call it through the OpenAI-compatible API you already use.
Match each workload to the GPT model and API that fit it.
Three steps to your first GPT-6 request on APIMart.
Create an APIMart account and top up your balance. It works for every model on the platform, including the GPT API.
Generate an API key in your dashboard. The same key calls every GPT model and all other models on APIMart.
Point the OpenAI SDK at api.apimart.ai and call /v1/chat/completions or /v1/responses with a model ID such as gpt-6.1-sol, or try it in the playground above.
What developers say about our GPT API
“The o3 model handles our legal document analysis with impressive accuracy. Game changer for our compliance team.”
Sarah Jones
Product Manager
“GPT-5 Codex is incredible for automated code reviews. It catches things our linters miss.”
Mike Brown
Engineering Lead
“We use GPT-4o-mini for real-time chat and o3-mini for background reasoning tasks. Best of both worlds.”
Emily Zhang
AI Engineer
“Reliable API. Documentation is clear and the playground makes testing easy.”
David Li
Startup Founder
“The pricing is significantly better than going direct. Highly recommended for startups watching their budget.”
Lisa Wang
Full Stack Developer
Answers about GPT-6 models, pricing, keys and integration on APIMart.
The GPT API on APIMart includes the GPT-6 family (GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol and GPT-6 Luna), GPT-5.6 (Sol, Luna and Terra), GPT-5.5, GPT-5.4 (including Pro, Mini and Nano), the Codex models, GPT-5, GPT-4.1, GPT-4o and the o-series reasoning models (o1, o3, o3-mini and o4-mini). The model list on this page is loaded live, so it always shows what you can call today.
Start with GPT-6.1 Sol for most complex coding and professional work. Move up to GPT-6 Astra when you need OpenAI's most capable model, use GPT-6.1 Terra for visual reasoning, computer use and writing, and pick GPT-6 Luna for focused, high-volume tasks. For coding agents, the Codex models are also available.
According to OpenAI's changelog, GPT-6 Astra was released on September 3, 2026, GPT-6 Sol and GPT-6 Luna on September 22, GPT-6.1 Sol on September 29 and GPT-6.1 Terra on October 26, 2026. In October OpenAI recommended the GPT-6 family for production API use.
The GPT API is billed per million input and output tokens, and each model has its own rates. As of October 2026, Gold member prices for requests up to 272K input tokens are $1.60 input / $8 output for GPT-6.1 Sol, $8 / $40 for GPT-6 Astra and $0.08 / $0.40 for GPT-6 Luna; longer requests use a higher tier. The pricing table on this page shows current rates for every model.
Both work with the same APIMart key. Chat Completions (/v1/chat/completions) suits existing chat code. The Responses API (/v1/responses) adds web search, file search, function calling and remote MCP tools, image input and 12-hour prompt caching.
Yes. GPT-5.6 and later models support caching of prompt prefixes of at least 1,024 tokens. The default is a 30-minute cache, and a 12-hour cache is available through the Responses API only. The TTL is a minimum lifetime, not a guarantee that every request hits the cache, and cached input is billed at the lower rate shown in the pricing table.
Yes. Keep your OpenAI SDK code, set the base URL to APIMart and use your APIMart API key, then call the same model IDs, such as gpt-6.1-sol or gpt-6-astra.
Sign up for APIMart, open the API Keys page in your dashboard and create a new key. The same key calls the OpenAI GPT API and every other model on the platform, with pay-as-you-go billing and no subscription.
No. Under APIMart's Terms of Service, your data is not used to train AI models or shared with third parties except as needed to provide the service. Requests are processed only to serve your API calls.
No. APIMart does not offer free credits for the GPT API. OpenAI GPT models, including the Codex models, are pay-as-you-go by token usage, you only pay for successful requests, and Gold members get 20% off all prices.
Yes. Prices shown on this page are Gold member prices, already 20% off list price. Platinum and Diamond members save more, up to 28%, and you only pay for successful requests.
GPT-6 Astra is OpenAI's most capable model for the most demanding work. GPT-6.1 Sol targets near-Astra performance for complex coding and professional work at a much lower price: OpenAI lists Astra at $10 / $50 and GPT-6.1 Sol at $2 / $10 per million input and output tokens.
Explore more models in the same category.
Gemini 4 Argon
Gemini-4-Argon is an AI assistant that brings together analytical thinking and creative expression. From untangling complex problems to refining writing and code, it offers clear reasoning, natural conversation, and practical suggestions to help turn rough ideas into actionable next steps.
Claude Haiku 5.5
Claude Haiku 5.5 API on APIMart delivers fast, cost-efficient AI, offering responsive conversations, capable coding assistance, and reliable performance for high-volume workflows.
Claude Opus 5
Claude Opus 5 is Anthropic’s next-generation flagship large language model, featuring enhanced capabilities in code development, complex reasoning, knowledge analysis, and agent execution, making it ideal for large-scale project development and professional work scenarios.
Kimi K3
Kimi-K3 is a next-generation large language model launched by Moonshot AI. It features ultra-long context, multimodal understanding, and strong coding capabilities, making it suitable for complex reasoning, software development, knowledge analysis, and agent automation tasks.