Get started

GPT-6 Astra

Sold by 6 sellers, timed at 43.2 tok/s, scored 56.9 on the Intelligence Index, and with results on 2 openly licensed boards.

retrieved sha256 · 0bb53a77713f

Models/OpenAI/GPT-6 AstraUSD per 1M tokens · as OpenRouter routes it
openai/gpt-6-astraOpenAI · base listing · GPT tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$10.00per 1M tokens
Output$50.00per 1M tokens
Cached input$1.00per 1M tokens
Context1.05M1,050,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states2 meters
Cache write$12.50per 1M tokens
Web search$0.01per search
Over the base window · the rate the list gives once a prompt is longer than a thresholdin / out per 1M tokens
Prompts over 272K tokens$20.00 / $75.00cached $2.00
What Vitna read · 2 providers, each from its own pricing page, kept as dated recordsin / out per 1M tokens
OpenAIthe maker$10.00 / $50.00confirmed 22 Nov 2026
Azureresold$10.00 / $50.00confirmed 22 Nov 2026

The same model sold by 2 providers, each at its own list price. OpenRouter's rate is its routed rate across whichever of them it uses, and it need not match any one of them.

What the list says · the fields OpenRouter publishes for this id10 fields
AuthorOpenAI
Listed
Canonical idopenai/gpt-6-astra-20260903
Context1,050,000 tokens
Max output128,000 tokens
Modalitiesfile, image, text → text
TokenizerGPT
Reasoningalways on · effort max, xhigh, high, medium, low, medium by default
Moderationmoderated by OpenRouter
Other listingbatch variant

What sellers charge

6 sellers · 12x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $5.00 at OpenAI to $60.00 at OpenAI. 1 seller undercuts the $10.00 listed; 2 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

5,794 requests · 8 endpoints · 30-minute window
Throughput43.2 tok/sMedian output rate, weighted across the 8 endpoints serving it by the requests each answered.the speed board
First token5.25sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread41 to 189.5The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

8 priced · 8 timed · cheapest first
  1. OpenAIopenai/flex$5.00$25.00$0.50not declared128knot matchednonenonenot matched100%
  2. Amazon Bedrockamazon-bedrock/global · listed$10.00$50.00$1.00not declared128k46 tok/s221.53s43 req99.18%
  3. Amazon Bedrockamazon-bedrock/global · listed$10.00$50.00$1.00not declared128k42 tok/s18.71.24s2 req99.18%
  4. Azureazure · listed$10.00$50.00$1.00not declared128k41 tok/s287.78s1,837 req100%
  5. Azureazure · listed$10.00$50.00$1.00not declared128k41 tok/s243.57s50 req100%
  6. OpenAIopenai · listed$10.00$50.00$1.00not declared128knot matchednonenonenot matched100%
  7. OpenAIopenai/fast$20.00$100.00$2.00not declared128knot matchednonenonenot matched100%
  8. OpenAIopenai/ultrafast$60.00$300.00$6.00not declared128knot matchednonenonenot matchedno reading
  9. OpenAInot matchednot matchednot matchednot matchedno offer61 tok/s311.12s30 reqno offer
  10. OpenAInot matchednot matchednot matchednot matchedno offer49 tok/s23.85.44s105 reqno offer
  11. OpenAInot matchednot matchednot matchednot matchedno offer190 tok/s132978ms1 reqno offer
  12. OpenAInot matchednot matchednot matchednot matchedno offer44 tok/s264.1s3,726 reqno offer

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 3 of the 8 timed routes are slower than it, and the middle route runs at 45 tok/s. The widest median-to-p90 gap is Amazon Bedrock's, 2.25x.

OpenAI publishes 4 offers and had 4 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 6 of the 8 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Azure (azure/us) at 53.83% on 7 Nov 2026, Azure (azure) at 80.11% on 6 Nov 2026, Amazon Bedrock (amazon-bedrock/global) at 86.53% on 2 Nov 2026, OpenAI (openai/flex) at 93.50% on 7 Nov 2026, and 2 more. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

11 parameters · 6 sellers
  1. include_reasoningevery seller
  2. reasoningevery seller
  3. reasoning_effortevery seller
  4. response_formatevery seller
  5. structured_outputsevery seller
  6. tool_choiceevery seller
  7. toolsevery seller
  8. verbosityevery seller
  9. max_tokens5 of 6not Azure
  10. seed5 of 6not Amazon Bedrock
  11. max_completion_tokens1 of 6only Azure

8 of these 11 are accepted by every one of the 6 sellers that publish a list; the other 3 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $20.00 per million tokens, 3 in to 1 out: cheaper than 7 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Index56.9Position 4 of 58, above 93% of the models scored.the intelligence leaderboard
Coding Index76.9Position 4 of 118, above 97% of the models scored.the coding leaderboard
Agentic Index51.0Position 7 of 94, above 93% of the models scored.the agentic leaderboard

Not ranked in any Design Arena category.

Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index169.2166.4 to 172.5
Position4 of 258above 99% of the models placed
Results behind it26benchmark results
As Epoch names itGPT-6 Astrareleased 3 Sep 2026

Position 4 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.

Benchmark results

2 of 6 boards · 43 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.014 of 22 tasks

Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names these runs gpt-6-astra_max, gpt-6-astra_xhigh, gpt-6-astra_high, gpt-6-astra_medium, gpt-6-astra_low and gpt-6-astra_none, and the effort beside each score says which run it is. A run missing from a task's rows has no published result there, which is not a score of zero. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.

LiveBench · publisher-run, Apache-2.023 of 23 tasks · 71 runs scored on each task · at max effort

Percent correct on the task the row names, higher is better. All 23 published columns; there is no average to carry, because the site computes its headline in the browser from a weighting this does not reimplement. LiveBench names this run gpt-6-astra-max. Read from livebench.ai ↗, which dates its own data . LiveBench, Apache-2.0. Results produced by the LiveBench maintainers on questions refreshed monthly.

2 of the 6 openly licensed boards Vitna mirrors carry a result for GPT-6 Astra, each printed as its publisher published it and none added to another. MTEB, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.