openai/gpt-6-astra
estimated usage cost
$35.00
1,000 requests × (1,000 uncached input × $10.00 + 500 output × $50.00) / 1,000,000 = $35.00
base rates: up to 272,000 input tokens per request, inclusive.
GPT-6 Astra vs Inkling
rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.
| specification | GPT-6 Astra openai/gpt-6-astra | Inkling thinkingmachines/inkling |
|---|---|---|
| input · usd / 1m tok | $10.00 | $1.87 |
| output · usd / 1m tok | $50.00 | $4.68 |
| context window | 1.05mtokens | 65.54ktokens |
| modalities · in → out | takes text and image in, gives text out | takes text and image in, gives text out |
pricing
| base api rates · usd per 1m tokens | GPT-6 Astra openai/gpt-6-astra | Inkling thinkingmachines/inkling |
|---|---|---|
| input | $10.00over 272k · $20.00 | $1.87 |
| output | $50.00over 272k · $75.00 | $4.68 |
| cache read | $1.00over 272k · $2.00 | $0.374 |
| cache write · default ttl | $12.50over 272k · $25.00 | not published |
brackets are by input tokens per request: a request over a threshold is billed at that bracket's rates for all of its tokens. cache creation can have a separate charge. the estimate below prices one workload at these rates on every model.
specifications
| as published | GPT-6 Astra openai/gpt-6-astra | Inkling thinkingmachines/inkling |
|---|---|---|
| creator | OpenAI | Thinking Machines |
| model type | Text generation | Text generation |
| context window | 1,050,000tokens | 65,536tokens |
| input | takes text and image in, gives text out | takes text and image in, gives text out |
| output | text | text |
| tool calling | not verified | not verified |
| released | sep 3, 2026 | jul 15, 2026 |
| endpoint | /v1/chat/completions | /v1/chat/completions |
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
benchmarks
| primary configuration | GPT-6 Astra openai/gpt-6-astra | Inkling thinkingmachines/inkling xhigh |
|---|---|---|
| intelligence index · gateway rank | 52.7#5 of 113 | 25.0#65 of 113 |
| coding index | 76.9#4 of 66 | 52.1#44 of 66 |
| agentic index | 51.0#7 of 54 | 22.5#34 of 54 |
| omniscience | not measured | 2.0#36 of 90 |
| gpqa | not measured | 87.2%#36 of 82 |
| humanity’s last exam | not measured | 31.9%#46 of 93 |
| aa-lcr | not measured | 77.3% |
| mmmu-pro | not measured | 73.5% |
| scicode | not measured | 47.0% |
| tau banking | not measured | 29.1% |
| analystagent | not measured | 23.8% |
| gdp.pdf all-pass | not measured | 12.8% |
| multilingual lcr | not measured | 6.1% |
| critpt | not measured | 5.4% |
| automationbench partial | not measured | 5.0% |
| harvey lab | not measured | 0.0% |
GPT-6 Astra source ↗Inkling source ↗
each column describes the tested configuration named under the model; performance and costs can differ on impossibl. a score one model was not measured on is left blank rather than scored zero. indices are ranked against every model on the gateway with one. last checked 2026-10-21.
estimate your cost
one token workload, priced on every model at the published rates, in usd. change the numbers to match yours.
thinkingmachines/inkling
estimated usage cost
$4.21
1,000 requests × (1,000 uncached input × $1.87 + 500 output × $4.68) / 1,000,000 = $4.21
base rates; no context pricing tiers are published.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
summary
GPT-6 Astra and Inkling are available through the Impossibl API. they share the /v1/chat/completions endpoint; the model identifier selects the model for a request.
GPT-6 Astra is created by OpenAI. It has a 1,050,000-token context window. Base API pricing (USD): $10.00 per million input tokens; $50.00 per million output tokens. Above 272,000 input tokens per request, context-tier rates apply to the whole request.
Inkling is created by Thinking Machines. It has a 65,536-token context window. Base API pricing (USD): $1.87 per million input tokens; $4.68 per million output tokens.
this page compares GPT-6 Astra vs Inkling as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.
view the source catalog ↗comparison as markdown ↗report a correction →