GPT-6.1 Sol vs GPT-5.6 Terra
GPT-5.6 Terra is the lower-priced of the two on Router One at base-tier rates (GPT-6.1 Sol and GPT-5.6 Terra: request input ≤ 272,000 tokens) — about 27% less on a 1M-input + 1M-output mix. Both carry a 1.05M context window. Both answer on /v1/chat/completions and /v1/responses (Codex CLI). GPT-6.1 Sol counts against the Premium models allowance on Pro, Max and Ultra; GPT-5.6 Terra counts against the Mid-tier models allowance on Pro, Max and Ultra.
GPT-6.1 Sol and GPT-5.6 Terra compared on current per-token rates, context window, and capabilities — both callable through one OpenAI-compatible endpoint with per-request cost traces.
GPT-6.1 Sol vs GPT-5.6 Terra: rates, context window, and capabilities
| Spec | GPT-6.1 Sol | GPT-5.6 Terra |
|---|---|---|
| Input / 1M tokens | $0.40 | $0.25 |
| Output / 1M tokens | $2.00 | $1.50 |
| Cached input / 1M tokens | $0.02 | $0.125 |
| Context window | 1.05M | 1.05M |
| Capabilities | Chat, Streaming, Tool calling, Vision | Chat, Streaming, Tool calling, Vision |
| Subscription plans | Premium models — Pro, Max, Ultra | Mid-tier models — Pro, Max, Ultra |
| Detail page | GPT-6.1 Sol | GPT-5.6 Terra |
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-5.6 Terra: request input ≤ 272,000 tokens: Input $0.25 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.25 / 1M tokens, Cached input $0.125 / 1M tokens; request input > 272,000 tokens: Input $0.50 / 1M tokens, Output $2.25 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.25 / 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-5.6 Terra?
Base-tier rates: For a workload of 1M input plus 1M output tokens at current rates: GPT-6.1 Sol comes to $2.40, GPT-5.6 Terra comes to $1.75 — GPT-5.6 Terra is about 27% cheaper on this mix. Real workloads skew heavily toward input tokens, so weigh the input rate by your own ratio; the cached-input row above is the posted catalog rate for that model.
Switch between GPT-6.1 Sol and GPT-5.6 Terra
The API key, base URL and endpoints stay the same, but GPT-5.6 Terra code may need changes before it runs on GPT-6.1 Sol. Per OpenAI's GPT-6 guide (checked 2026-10-31), GPT-6.1 Sol does not accept the none reasoning effort (OpenAI suggests low) and takes tool calls only on the Responses API, and the guide says to remove temperature, top_p and top_logprobs, plus logprobs on Chat Completions, whenever the effort is not none. Per OpenAI's GPT-5.6 Terra model page (checked 2026-10-31), GPT-5.6 Terra accepts the reasoning efforts none to max, with medium as the default. So GPT-5.6 Terra code that relies on none, sends tools on /v1/chat/completions or sets those sampling parameters has to change before it runs on GPT-6.1 Sol; send tool-using requests to /v1/responses. On a Pro, Max or Ultra plan the allowance changes too: as of the 2026-10-31 plan response, GPT-6.1 Sol counts against the Premium models allowance and GPT-5.6 Terra against the Mid-tier models allowance.
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-5.6-terra"FAQ
Is GPT-6.1 Sol cheaper than GPT-5.6 Terra?
Compared at base-tier rates (GPT-6.1 Sol and GPT-5.6 Terra: request input ≤ 272,000 tokens). Input: GPT-6.1 Sol $0.40 vs GPT-5.6 Terra $0.25 / 1M tokens; GPT-5.6 Terra has the lower rate. Output: GPT-6.1 Sol $2.00 vs GPT-5.6 Terra $1.50 / 1M tokens; GPT-5.6 Terra 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-5.6 Terra: request input ≤ 272,000 tokens: Input $0.25 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.25 / 1M tokens, Cached input $0.125 / 1M tokens; request input > 272,000 tokens: Input $0.50 / 1M tokens, Output $2.25 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.25 / 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-5.6 Terra included in a Router One subscription?
GPT-6.1 Sol counts against the Premium models allowance on Pro, Max and Ultra: Pro 300, Max 1,000 and Ultra 5,000 requests per 30-day cycle, shared by every model in that tier. GPT-5.6 Terra counts against the Mid-tier models allowance on Pro, Max and Ultra: Pro 1,200, Max 4,500 and Ultra 15,000 requests per 30-day cycle, shared by every model in that tier. Requests to GPT-6.1 Sol or GPT-5.6 Terra 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-5.6 Terra without changing code?
The API key, base URL and endpoints stay the same, but GPT-5.6 Terra code may need changes before it runs on GPT-6.1 Sol. Per OpenAI's GPT-6 guide (checked 2026-10-31), GPT-6.1 Sol does not accept the none reasoning effort (OpenAI suggests low) and takes tool calls only on the Responses API, and the guide says to remove temperature, top_p and top_logprobs, plus logprobs on Chat Completions, whenever the effort is not none. Per OpenAI's GPT-5.6 Terra model page (checked 2026-10-31), GPT-5.6 Terra accepts the reasoning efforts none to max, with medium as the default. So GPT-5.6 Terra code that relies on none, sends tools on /v1/chat/completions or sets those sampling parameters has to change before it runs on GPT-6.1 Sol; send tool-using requests to /v1/responses. On a Pro, Max or Ultra plan the allowance changes too: as of the 2026-10-31 plan response, GPT-6.1 Sol counts against the Premium models allowance and GPT-5.6 Terra against the Mid-tier models allowance.
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 2026-11-01 (UTC) and refresh within the hour.