gpt-6.1-solGPT-6.1 Sol is OpenAI's upgrade to the Sol tier of the GPT-6 family, released on 29 September 2026. On APIMODELS it costs $1.00 per 1M input tokens and $5.00 per 1M output — exactly half OpenAI's $2 / $10 list — with cached input at $0.05, half of OpenAI's new $0.10 cached rate (GPT-6 Sol's cached rate was $0.20). OpenAI's announcement reports GPT-6.1 Sol at 75.2% on DeepSWE v1.1 at high reasoning effort, above GPT-6 Sol's best of 68.8% at roughly 76% lower cost per task, and 31.7% on AutomationBench at medium effort, 4.8 points above GPT-6 Sol. The specifications: a 1,050,000-token context window with up to 922,000 input tokens, 128,000 max output, text and image input, and a knowledge cutoff of 30 April 2026. reasoning_effort takes low / medium (default) / high / xhigh / max — unlike GPT-6 Sol there is no none level — and reasoning tokens are billed as output. Requests whose input exceeds 272K tokens bill input and cached input at 2× and output at 1.5×, the same long-context tier as the rest of the family. Call it through the OpenAI-compatible /v1/chat/completions or /v1/responses with one key; streaming, function calling and structured outputs work, and failed requests are not charged. The bare alias gpt-6.1 routes here; gpt-6 still routes to GPT-6 Sol.
View complete API reference with all parameters and examples.
Enable real-time streaming responses with Server-Sent Events.
{
"model": "gpt-6.1-sol",
"stream": true,
"messages": [...]
}Enable the model to use tools and call functions.
{
"model": "gpt-6.1-sol",
"tools": [{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "City name"}
},
"required": ["location"]
}
}
}],
"messages": [{"role": "user", "content": "What's the weather in Tokyo?"}]
}Get structured JSON responses from the model.
{
"model": "gpt-6.1-sol",
"response_format": {"type": "json_object"},
"messages": [{"role": "user", "content": "Extract info as JSON: John is 30 years old"}]
}| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Model identifier (e.g., gpt-6.1-sol) |
| messages | array | Yes | Array of message objects with role and content |
| max_tokens | integer | No | Maximum tokens in the response |
| stream | boolean | No | Enable streaming responses (SSE) |
| temperature | number | No | Sampling temperature (0.0 - 2.0) |
| top_p | number | No | Nucleus sampling threshold (0.0 - 1.0) |
| tools | array | No | Function calling tools definition |
| response_format | object | No | Output format (e.g., json_object) |
View complete API reference with streaming, thinking, and more.
Billing: Cost = (input_tokens * input_price + output_tokens * output_price) / 1,000,000
$1.00 / $5.00 per 1M tokens against the $2 / $10 list; cached input $0.05
OpenAI: 75.2% on DeepSWE v1.1 vs 68.8% for GPT-6 Sol, at about 76% lower cost per task
Text and image input; knowledge cutoff 30 April 2026; >272K bills input 2× and output 1.5×
Five levels (low / medium / high / xhigh / max), default medium; no none level; reasoning tokens count as output
GPT-6.1 Sol is a Large Language Model API provided by OpenAI. GPT-6.1 Sol is OpenAI's upgrade to the Sol tier of the GPT-6 family, released on 29 September 2026. On APIMODELS it costs $1.00 per 1M input tokens and $5.00 per 1M output — exactly half OpenAI's $2 / $10 list — with cached input at $0.05, half of OpenAI's new $0.10 cached rate (GPT-6 Sol's cached rate was $0.20). OpenAI's announcement reports GPT-6.1 Sol at 75.2% on DeepSWE v1.1 at high reasoning effort, above GPT-6 Sol's best of 68.8% at roughly 76% lower cost per task, and 31.7% on AutomationBench at medium effort, 4.8 points above GPT-6 Sol. The specifications: a 1,050,000-token context window with up to 922,000 input tokens, 128,000 max output, text and image input, and a knowledge cutoff of 30 April 2026. reasoning_effort takes low / medium (default) / high / xhigh / max — unlike GPT-6 Sol there is no none level — and reasoning tokens are billed as output. Requests whose input exceeds 272K tokens bill input and cached input at 2× and output at 1.5×, the same long-context tier as the rest of the family. Call it through the OpenAI-compatible /v1/chat/completions or /v1/responses with one key; streaming, function calling and structured outputs work, and failed requests are not charged. The bare alias gpt-6.1 routes here; gpt-6 still routes to GPT-6 Sol. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: Input: $1.00, Output: $5.00 per 1M tokens.
Build intelligent conversational systems to automatically answer user queries and improve service efficiency.
Automatically write articles, emails, ad copy, and other text content to boost productivity.
Assist with code writing, debugging, and code review to accelerate software development.
Understand and analyze unstructured data, extract key insights, and generate summary reports.
GPT-6.1 Sol is available through APIMODELS at: Input: $1.00, Output: $5.00 per 1M tokens. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same GPT-6.1 Sol model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
$1.00 per 1M input tokens, $5.00 per 1M output and $0.05 for cached input — exactly half OpenAI's $2 / $10 / $0.10 list. When a single request's input exceeds 272K tokens, input and cached input bill at 2× and output at 1.5×, matching OpenAI's own long-context tier. Billing is per actual token, reasoning tokens count as output, and failed requests are free.
GPT-6.1 Sol is OpenAI's Sol upgrade released on 29 September 2026. The list price is the same $2 / $10, but cached input drops from $0.20 to $0.10. OpenAI reports 75.2% on DeepSWE v1.1 at high effort versus GPT-6 Sol's best of 68.8%, at about 76% lower cost per task, and 31.7% on AutomationBench, 4.8 points higher. Here both cost $1.00 / $5.00, and 6.1's cache is more affordable ($0.05 vs $0.10). Start new work on gpt-6.1-sol; for existing code just change the model name — the one thing to watch is that 6.1 has no reasoning_effort: none.
GPT-6.1 Sol accepts low / medium (default) / high / xhigh / max — there is no none. Reasoning tokens bill at the $5.00 output rate and count against max_tokens, so use low for simple work. If max_tokens is very small, reasoning can use the whole budget and leave the answer empty; raise max_tokens or lower the effort if that happens.
POST https://api.apimodels.app/v1/chat/completions or /v1/responses with model gpt-6.1-sol and Authorization: Bearer your apimodels key; with the OpenAI SDK only base_url changes. Streaming, function calling, structured outputs and image input work. The bare name gpt-6.1 routes to GPT-6.1 Sol; gpt-6 still points to GPT-6 Sol and is not upgraded automatically.
On APIMODELS, GPT-6.1 Sol runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports 50% Below Official, Newer than GPT-6 Sol, 1.05M Context, Reasoning Effort, and you can weigh it on price and capability against other Large Language Model models, then switch by changing a single model-name string — no new account or integration. Browse every Large Language Model option with live pricing at apimodels.app/models.
GPT-6.1 Sol supports: 50% Below Official, Newer than GPT-6 Sol, 1.05M Context, Reasoning Effort. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes GPT-6.1 Sol through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.
How to get access, regional availability, and how this model compares with its alternatives.