GPT Image 2.5 is live — OpenAI's newest image model, targeted edits that leave the rest of the frame alone
All resources

· reAPI Team

GPT-6.1 Sol Pricing: Token Rates, Cache Costs and Calculator

GPT-6.1 Sol pricing from OpenAI's price page: input, output, cache reads and writes, the 272K tier, Batch, Fast and Ultrafast, plus worked cost examples.

GPT-6.1 Sol Pricing: Token Rates, Cache Costs and Calculator

GPT-6.1 Sol pricing starts at $2.00 per million input tokens and $10.00 per million output tokens on OpenAI's Standard tier[1]. OpenAI released the model on September 29, 2026 as "near-Astra performance for complex work at a lower cost"[2][3]. Those two rates match GPT-6 Sol, but the rest of the bill does not: cached input costs half as much, there is a separate tier for prompts over 272K tokens, and reasoning tokens bill as output.

This guide lists every GPT-6.1 Sol rate from OpenAI's pricing page, retrieved October 28, 2026, shows how one request is priced, and works through five cost examples with the arithmetic written out. It also includes a real measured request from reAPI's own check of the model.

TL;DR

  • Standard rates per 1M tokens: $2.00 input, $0.10 cached input, $2.50 cache writes (30-minute lifetime), $10.00 output[1].
  • Over 272K input tokens, the full request moves to $4.00 input, $0.20 cached input, $5.00 cache writes and $15.00 output[1][2].
  • Batch and Flex cost half of Standard, Fast mode twice, and Ultrafast six times[2].
  • Reasoning tokens bill as output, so reasoning_effort can materially affect cost[4].
  • Against its siblings: same input and output price as GPT-6 Sol with half the cached-input rate, and one fifth of GPT-6 Astra[1].
  • On reAPI (checked October 28, 2026): $2.00 input and $10.00 output per 1M tokens, the same as OpenAI's Standard rate, billed from one credit balance[5].

GPT-6.1 Sol pricing for every token type

OpenAI prices GPT-6.1 Sol by token type and by prompt length. Short context means up to 272K input tokens; above that, the long-context rates apply to the whole request[1].

Per 1M tokens (Standard)Up to 272K inputOver 272K input
Input$2.00$4.00
Cached input$0.10$0.20
Cache write, 30-minute lifetime$2.50$5.00
Cache write, 12-hour lifetime$5.00$10.00
Output$10.00$15.00

Source: OpenAI API pricing, Standard tier[1].

The model page gives the rules behind the table. Cached input tokens are "priced at 5% of the uncached input token rate", cache writes "are billed at 1.25x the uncached input token rate", and "prompts with more than 272K input tokens are priced at 2x input and cache rates and 1.5x output for the full request"[2]. The 5% read rate is unusual. OpenAI's caching guide says reads cost "0.1× the ordinary input rate on most of these models and 0.05× on GPT-6.1 Sol and GPT-6.1 Terra"[6].

Batch, Flex, Fast and Ultrafast for GPT-6.1 Sol

Standard is one of five prices. The model page states: "Fast mode prices are 2x Standard. Batch and Flex prices are 50% lower than Standard", "Ultrafast mode prices are 6x Standard", and "Regional processing adds a 10% premium where available"[2].

Per 1M tokens, up to 272K inputInputCached input30-min writeOutput
Batch / Flex$1.00$0.05$1.25$5.00
Standard$2.00$0.10$2.50$10.00
Fast$4.00$0.20$5.00$20.00
Ultrafast$12.00$0.60$15.00$60.00

Source: OpenAI API pricing, Batch, Flex, Fast and Ultrafast tables[1].

Ultrafast arrived on October 8, 2026, in the Responses API, used by setting service_tier: "ultrafast"[3]. It is a speed tier, and at $60 per million output tokens it costs more than GPT-6 Astra's Standard output rate of $50[1]. At the other end, GPT-6.1 Sol in Batch costs exactly what GPT-6.1 Terra costs at Standard, $1.00 input and $5.00 output.

How a GPT-6.1 Sol request is priced

Every response reports token counts in usage. The bill for one Standard request below 272K input tokens is:

cost = (uncached_input × $2.00
      + cached_input × $0.10
      + cache_write × $2.50
      + output × $10.00) / 1,000,000

Three things move the result.

Cache. Tokens read from the prompt cache bill at 5% of the input rate. The first request that writes a prefix pays 1.25× for those tokens with the default 30-minute lifetime, or 2.5× for the 12-hour lifetime available in the Responses API[6]. So a cached prefix costs more once and much less every time after.

reAPI's check on October 28, 2026 shows both sides. A 2,683-token prompt was charged $0.006906 the first time, when 2,680 of its tokens were written to the cache, and $0.000494 when sent again, when the same 2,680 tokens were read from it[7]. The arithmetic matches the table: (3 × $2 + 20 × $10 + 2,680 × $2.50) / 1M on the first call and (3 × $2 + 22 × $10 + 2,680 × $0.10) / 1M on the second, with 20 and 22 output tokens.

Reasoning. OpenAI's reasoning guide says reasoning tokens occupy the context window and "are billed as output tokens"[4]. GPT-6.1 Sol supports low, medium (default), high, xhigh and max, with no none setting[2]. Every reasoning token costs the output rate of $10 per million.

Prompt length. Cross 272K input tokens and every token type in the request moves to the long-context column, not only the tokens above the line[2].

GPT-6.1 Sol pricing calculator: five worked examples

All five use OpenAI's Standard rates from the tables above. The token counts are illustrative assumptions, chosen to show how each lever moves the total.

ScenarioTokensArithmeticCost
A. Short code review2,000 in, 500 out2,000 × $2 + 500 × $10$0.009
B. Same prefix, cached20,000 in (18,000 cached), 800 out2,000 × $2 + 18,000 × $0.10 + 800 × $10$0.0138
C. Same as B, no cache20,000 in, 800 out20,000 × $2 + 800 × $10$0.048
D. Reasoning at high effort1,000 in, 300 visible + 2,000 reasoning out1,000 × $2 + 2,300 × $10$0.025
E. Long contract review300,000 in, 4,000 out300,000 × $4 + 4,000 × $15$1.26

Each product is per 1M tokens, so divide by 1,000,000. Scenario A at a million requests a day is $9,000. Scenario B costs less than a third of C, because the cached share bills at 5% of the input rate. In scenario D, reasoning tokens are 80% of the bill even though the visible answer is 300 tokens. Scenario E shows the long-context switch: the same 304,000 tokens at short-context rates would cost $0.64, so crossing 272K roughly doubles the request.

How GPT-6.1 Sol pricing compares with other GPT models

Model (Standard, per 1M)InputCached inputOutput
GPT-6 Luna$0.10$0.01$0.50
GPT-6.1 Terra$1.00$0.05$5.00
GPT-6.1 Sol$2.00$0.10$10.00
GPT-6 Sol$2.00$0.20$10.00
GPT-5.6 Sol$4.00$0.40$20.00
GPT-6 Astra$10.00$1.00$50.00

Source: OpenAI API pricing, Standard tier[1].

Against GPT-6 Sol, the previous Sol model, only the cached-input rate changes, and it halves. OpenAI's GPT-6 Sol page now points readers to "the newer Sol model"[8]. Against GPT-6 Astra, input and output are one fifth and cached input one tenth. GPT-5.6 Sol cost twice as much for input and output and four times as much for cached input. GPT-6.1 Terra is half of GPT-6.1 Sol on every line[1]. The price gap does not tell you which model answers better; GPT-6.1 Sol vs GPT-6 Astra and GPT-6.1 Terra vs 6.1 Sol cover those choices.

Paying for GPT-6.1 Sol through reAPI

reAPI serves GPT-6.1 Sol on its Chat Completions endpoint with the model id gpt-6.1-sol, billed per token from your reAPI credit balance[7]. On October 28, 2026 the reAPI rates were:

Per 1M tokens on reAPIUp to 272K inputOver 272K input
Input$2.00$4.00
Cached input$0.10$0.20
Cache write$2.50$5.00
Output$10.00$15.00

Source: reAPI model page, checked October 28, 2026[5].

These are OpenAI's Standard rates, with the long-context line at the same 272K input tokens. On reAPI the reasoning levels offered are low to xhigh: in the October 28 check, max returned an error on this endpoint and was not charged[7]. The output cap is enforced, so max_completion_tokens limits the output part of a request's cost; it counts reasoning tokens as well as the visible answer. The GPT-6.1 Sol model page always shows the current rates and has a playground that sends billed requests.

FAQ

gpt 6.1 sol pricing after 272k context

Once a prompt has more than 272K input tokens, the whole request is priced at the long-context rates: $4.00 input, $0.20 cached input, $5.00 cache writes and $15.00 output per 1M tokens at Standard[1]. That is 2× input and cache rates and 1.5× output, applied to every token in the request[2].

gpt 6.1 sol price vs gpt 6 sol

Input and output are the same, $2.00 and $10.00 per 1M tokens. Cached input is $0.10 for GPT-6.1 Sol and $0.20 for GPT-6 Sol, so cache-heavy workloads cost less on the newer model[1].

gpt sol cost per million tokens

GPT-6.1 Sol costs $2.00 per million input tokens, $0.10 per million cached input tokens and $10.00 per million output tokens at Standard, below 272K input tokens[1]. Batch and Flex halve those rates[2].

is gpt 6.1 sol free

Not through the API. OpenAI's pricing page lists only paid per-token rates for GPT-6.1 Sol, and reAPI bills it per token from a credit balance[1][5].

gpt 6.1 sol pricing calculator

Multiply each token count in usage by its rate and divide by 1,000,000: uncached input × $2.00, cached input × $0.10, cache writes × $2.50 and output × $10.00 at Standard, or the long-context column when the prompt is over 272K tokens[1]. The five examples above show the arithmetic.

is gpt 6.1 sol cheap

It is the mid-priced model in OpenAI's GPT-6 line: one fifth of GPT-6 Astra, twice GPT-6.1 Terra and twenty times GPT-6 Luna for input and output[1]. Whether that is cheap depends on whether a lower-priced model holds your accuracy on your own tasks.

Keeping GPT-6.1 Sol costs predictable

A GPT-6.1 Sol bill moves with uncached input, cache writes and reads, and output tokens, reasoning included. Start at the default medium and raise effort only where the answers improve. Keep a stable prefix at the start of every conversation so repeat calls read from cache at 5% of the input rate, set max_completion_tokens high enough for reasoning plus the longest answer you need, and split documents that would push a prompt past 272K tokens. Work that can wait drops GPT-6.1 Sol pricing by half in Batch. For current per-token rates and a playground, open the GPT-6.1 Sol model page.

References

  1. OpenAI. API pricing. Retrieved October 2026 from developers.openai.com/api/docs/pricing
  2. OpenAI. GPT-6.1 Sol model page. Retrieved October 2026 from developers.openai.com/api/docs/models/gpt-6.1-sol
  3. OpenAI. API changelog, September 29 and October 8, 2026. Retrieved October 2026 from developers.openai.com/api/docs/changelog
  4. OpenAI. Reasoning models. Retrieved October 2026 from developers.openai.com/api/docs/guides/reasoning
  5. reAPI. GPT-6.1 Sol model page. Retrieved October 2026 from reapi.ai/models/gpt-6-1-sol
  6. OpenAI. Prompt caching. Retrieved October 2026 from developers.openai.com/api/docs/guides/prompt-caching
  7. reAPI. GPT-6.1 Sol API docs. Retrieved October 2026 from reapi.ai/docs/gpt-6-1-sol
  8. OpenAI. GPT-6 Sol model page. Retrieved October 2026 from developers.openai.com/api/docs/models/gpt-6-sol
All resources