GPT-6.1 Sol vs GPT-6 Sol
GPT-6.1 Sol and GPT-6 Sol come to the same total on Router One at base-tier rates (GPT-6.1 Sol and GPT-6 Sol: request input ≤ 272,000 tokens) for a 1M-input + 1M-output mix ($2.40), with matching input and output rates. Their cached-input rates differ: GPT-6.1 Sol $0.02 vs GPT-6 Sol $0.04 per 1M tokens. Both carry a 1.05M context window. Both answer on /v1/chat/completions and /v1/responses (Codex CLI).
GPT-6.1 Sol and GPT-6 Sol compared on current per-token rates, context window, and capabilities — both callable through one OpenAI-compatible endpoint that logs each request it forwards.
GPT-6.1 Sol vs GPT-6 Sol: rates, context window, and capabilities
| Spec | GPT-6.1 Sol | GPT-6 Sol |
|---|---|---|
| Input / 1M tokens | $0.40 | $0.40 |
| Output / 1M tokens | $2.00 | $2.00 |
| Cached input / 1M tokens | $0.02 | $0.04 |
| Context window | 1.05M | 1.05M |
| Capabilities | Chat, Streaming, Tool calling, Vision | Chat, Streaming, Tool calling, Vision |
| Subscription plans | Premium models — Pro, Max, Ultra | Premium models — Pro, Max, Ultra |
| Detail page | GPT-6.1 Sol | GPT-6 Sol |
GPT-6.1 Sol: request input ≤ 272,000 tokens: Input $0.40 / 1M tokens, Output $2.00 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.02 / 1M tokens; request input > 272,000 tokens: Input $0.80 / 1M tokens, Output $3.00 / 1M tokens, Cache write $1.00 / 1M tokens, Cached input $0.04 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.
GPT-6 Sol: request input ≤ 272,000 tokens: Input $0.40 / 1M tokens, Output $2.00 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.04 / 1M tokens; request input > 272,000 tokens: Input $0.80 / 1M tokens, Output $3.00 / 1M tokens, Cache write $1.00 / 1M tokens, Cached input $0.08 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.
What does 1M tokens cost on GPT-6.1 Sol vs GPT-6 Sol?
Base-tier rates: For a workload of 1M input plus 1M output tokens at current rates, GPT-6.1 Sol and GPT-6 Sol both come to $2.40, but their cached-input rates differ (see the table above), so the gap grows with the share of cached input in your requests. Context window and listed capabilities match, so compare them on your own prompts in your request traces.
Switch between GPT-6.1 Sol and GPT-6 Sol
The API key, base URL and endpoints stay the same, but GPT-6 Sol code may still need changes. Per OpenAI's GPT-6 guide (checked 2026-10-30), GPT-6.1 Sol does not accept the none reasoning effort on OpenAI's own API (OpenAI suggests low), and the guide says to remove temperature, top_p and top_logprobs, plus logprobs on Chat Completions, whenever the effort is not none, so drop them from GPT-6 Sol code you move over. Tool calls change too: per the same guide, GPT-6.1 Sol takes them only on the Responses API, while GPT-6 Sol also supports function calling on Chat Completions at none. Send tool-using requests to /v1/responses. The GPT-6.1 Sol API guide covers the rest of the migration.
curl https://api.router.one/v1/chat/completions \
-H "Authorization: Bearer sk-your-router-one-key" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-6.1-sol", "messages": [{"role": "user", "content": "Hello"}]}'
# Same request, other model — change one string:
# "model": "openai/gpt-6-sol"FAQ
Is GPT-6.1 Sol cheaper than GPT-6 Sol?
Compared at base-tier rates (GPT-6.1 Sol and GPT-6 Sol: request input ≤ 272,000 tokens). Input: GPT-6.1 Sol $0.40 vs GPT-6 Sol $0.40 / 1M tokens; the rates are equal. Output: GPT-6.1 Sol $2.00 vs GPT-6 Sol $2.00 / 1M tokens; the rates are equal. Cached input: GPT-6.1 Sol $0.02 vs GPT-6 Sol $0.04 / 1M tokens; GPT-6.1 Sol has the lower rate. Total cost depends on the workload's input, output and cache usage. GPT-6.1 Sol: request input ≤ 272,000 tokens: Input $0.40 / 1M tokens, Output $2.00 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.02 / 1M tokens; request input > 272,000 tokens: Input $0.80 / 1M tokens, Output $3.00 / 1M tokens, Cache write $1.00 / 1M tokens, Cached input $0.04 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. GPT-6 Sol: request input ≤ 272,000 tokens: Input $0.40 / 1M tokens, Output $2.00 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.04 / 1M tokens; request input > 272,000 tokens: Input $0.80 / 1M tokens, Output $3.00 / 1M tokens, Cache write $1.00 / 1M tokens, Cached input $0.08 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Rates change; the /models page is the live source of truth.
Is GPT-6.1 Sol or GPT-6 Sol included in a Router One subscription?
GPT-6.1 Sol and GPT-6 Sol both count against the Premium models allowance on Pro, Max and Ultra: Pro 300, Max 1,000 and Ultra 5,000 requests per 30-day cycle, one pool shared by every model in that tier. Requests to GPT-6.1 Sol or GPT-6 Sol above the model's long-context threshold count as more than one quota request. Requests beyond a plan's allowance bill the wallet per token.
Can I switch between GPT-6.1 Sol and GPT-6 Sol without changing code?
The API key, base URL and endpoints stay the same, but GPT-6 Sol code may still need changes. Per OpenAI's GPT-6 guide (checked 2026-10-30), GPT-6.1 Sol does not accept the none reasoning effort on OpenAI's own API (OpenAI suggests low), and the guide says to remove temperature, top_p and top_logprobs, plus logprobs on Chat Completions, whenever the effort is not none, so drop them from GPT-6 Sol code you move over. Tool calls change too: per the same guide, GPT-6.1 Sol takes them only on the Responses API, while GPT-6 Sol also supports function calling on Chat Completions at none. Send tool-using requests to /v1/responses. The GPT-6.1 Sol API guide covers the rest of the migration.
Where do these numbers come from?
Specs and prices on this page render from the live Router One catalog — the same data as the /models page — and refresh with it. Pricing methodology is documented on /pricing-methodology. Rates on this page were read from the live catalog on 2026-11-15 (UTC) and refresh within the hour.