GPT-6 Sol vs GPT-6 Astra
GPT-6 Sol is the lower-priced of the two on Router One at base-tier rates (GPT-6 Sol and GPT-6 Astra: request input ≤ 272,000 tokens) — about 80% 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 Sol counts against the Premium models allowance on Pro, Max and Ultra; GPT-6 Astra counts against the Flagship models allowance on Max and Ultra.
GPT-6 Sol and GPT-6 Astra 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 Sol vs GPT-6 Astra: rates, context window, and capabilities
| Spec | GPT-6 Sol | GPT-6 Astra |
|---|---|---|
| Input / 1M tokens | $0.40 | $2.00 |
| Output / 1M tokens | $2.00 | $10.00 |
| Cached input / 1M tokens | $0.04 | $0.20 |
| Context window | 1.05M | 1.05M |
| Capabilities | Chat, Streaming, Tool calling, Vision | Chat, Streaming, Tool calling, Vision |
| Subscription plans | Premium models — Pro, Max, Ultra | Flagship models — Max, Ultra |
| Detail page | GPT-6 Sol | GPT-6 Astra |
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.
GPT-6 Astra: request input ≤ 272,000 tokens: Input $2.00 / 1M tokens, Output $10.00 / 1M tokens, Cache write $2.50 / 1M tokens, Cached input $0.20 / 1M tokens; request input > 272,000 tokens: Input $4.00 / 1M tokens, Output $15.00 / 1M tokens, Cache write $5.00 / 1M tokens, Cached input $0.40 / 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 Sol vs GPT-6 Astra?
Base-tier rates: For a workload of 1M input plus 1M output tokens at current rates: GPT-6 Sol comes to $2.40, GPT-6 Astra comes to $12.00 — GPT-6 Sol is about 80% 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 Sol and GPT-6 Astra
The API key, base URL and endpoints stay the same, but code written for GPT-6 Sol may still need changes. Per OpenAI's GPT-6 guide (checked 2026-10-01), GPT-6 Astra does not accept the none reasoning effort (OpenAI suggests low) and takes tool calls only on the Responses API, while GPT-6 Sol supports function calling on Chat Completions with reasoning_effort set to none; at any effort other than none, both models take no temperature, top_p or logprobs settings. So GPT-6 Sol code that relies on none, or sends tools on /v1/chat/completions, has to change before it runs on GPT-6 Astra. On a Pro, Max or Ultra plan the billing changes too: as of the 2026-10-06 plan response, GPT-6 Sol counts against the Premium models allowance on Pro, Max and Ultra, while GPT-6 Astra counts against the Flagship models allowance on Max and Ultra (on Pro it bills the wallet).
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-sol", "messages": [{"role": "user", "content": "Hello"}]}'
# Same request, other model — change one string:
# "model": "openai/gpt-6-astra"FAQ
Is GPT-6 Sol cheaper than GPT-6 Astra?
Compared at base-tier rates (GPT-6 Sol and GPT-6 Astra: request input ≤ 272,000 tokens). Input: GPT-6 Sol $0.40 vs GPT-6 Astra $2.00 / 1M tokens; GPT-6 Sol has the lower rate. Output: GPT-6 Sol $2.00 vs GPT-6 Astra $10.00 / 1M tokens; GPT-6 Sol has the lower rate. Total cost depends on the workload's input, output and cache usage. 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. GPT-6 Astra: request input ≤ 272,000 tokens: Input $2.00 / 1M tokens, Output $10.00 / 1M tokens, Cache write $2.50 / 1M tokens, Cached input $0.20 / 1M tokens; request input > 272,000 tokens: Input $4.00 / 1M tokens, Output $15.00 / 1M tokens, Cache write $5.00 / 1M tokens, Cached input $0.40 / 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 Sol or GPT-6 Astra included in a Router One subscription?
GPT-6 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-6 Astra counts against the Flagship models allowance on Max and Ultra: Max 150 and Ultra 450 requests per 30-day cycle, shared by every model in that tier. Requests to GPT-6 Sol or GPT-6 Astra 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 Sol and GPT-6 Astra without changing code?
The API key, base URL and endpoints stay the same, but code written for GPT-6 Sol may still need changes. Per OpenAI's GPT-6 guide (checked 2026-10-01), GPT-6 Astra does not accept the none reasoning effort (OpenAI suggests low) and takes tool calls only on the Responses API, while GPT-6 Sol supports function calling on Chat Completions with reasoning_effort set to none; at any effort other than none, both models take no temperature, top_p or logprobs settings. So GPT-6 Sol code that relies on none, or sends tools on /v1/chat/completions, has to change before it runs on GPT-6 Astra. On a Pro, Max or Ultra plan the billing changes too: as of the 2026-10-06 plan response, GPT-6 Sol counts against the Premium models allowance on Pro, Max and Ultra, while GPT-6 Astra counts against the Flagship models allowance on Max and Ultra (on Pro it bills the wallet).
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 2026-11-11 (UTC) and refresh within the hour.