Get started

GPT-5 (batch)

Timed at 70.5 tok/s, scored 37.8 on the Coding Index, on 8 Design Arena boards, and with results on 1 openly licensed board.

retrieved sha256 · 0bb53a77713f

Models/OpenAI/GPT-5 (batch)USD per 1M tokens · as OpenRouter routes it
openai/gpt-5:batchOpenAI · batch variant · GPT tokenizer
listed until 2026-12-11
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.625per 1M tokens
Output$5.00per 1M tokens
Cached input$0.0625per 1M tokens
Context400k400,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states1 meter
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id13 fields
AuthorOpenAI
Listed
Canonical idopenai/gpt-5-2025-08-07
Context400,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerGPT
Reasoningalways on · effort high, medium, low, minimal, medium by default
Moderationmoderated by OpenRouter
Variantbatch
Knowledge cutoff2024-09-30
Listed until2026-12-11
Other listingbase listing

Measured speed

1,051 requests · 3 endpoints · 30-minute window
Throughput70.5 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token4.34sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread35 to 86The 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

3 priced · 3 timed · cheapest first
  1. Azureazure$1.25$10.00$0.125not declared128k35 tok/s224.69s53 req100%
  2. Azureazure$1.25$10.00$0.125not declared128k86 tok/s455.43s29 req100%
  3. OpenAIopenai/default$1.25$10.00$0.125not declared128k72 tok/s424.29s969 req100%

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: 1 of the 3 timed routes are slower than it, and the middle route runs at 72 tok/s. The widest median-to-p90 gap is Azure's, 1.91x.

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 . 2 of the 3 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/swedencentral) at 97.61% on 2 Nov 2026 and OpenAI at 97.77% on 10 Nov 2026. 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 · 2 sellers
  1. include_reasoningevery seller
  2. reasoningevery seller
  3. reasoning_effortevery seller
  4. response_formatevery seller
  5. seedevery seller
  6. structured_outputsevery seller
  7. tool_choiceevery seller
  8. toolsevery seller
  9. verbosityevery seller
  10. max_completion_tokens1 of 2not OpenAI
  11. max_tokens1 of 2not Azure

9 of these 11 are accepted by every one of the 2 sellers that publish a list; the other 2 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 $1.719 per million tokens, 3 in to 1 out: cheaper than 111 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 Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Index37.8Position 76 of 118, above 36% of the models scored.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. 3D scenes · Models1035 Elowin rate 41.3% · source rank 115the board, 113 ranked
  2. ASCII art · Models1124 Elowin rate 49.0% · source rank 54the board, 67 ranked
  3. Code · Models1156 Elowin rate 54.5% · source rank 83the board, 120 ranked
  4. Data visualisation · Models1218 Elowin rate 60.5% · source rank 52the board, 110 ranked
  5. Game development · Models1174 Elowin rate 59.3% · source rank 68the board, 120 ranked
  6. SVG · Models1178 Elowin rate 64.1% · source rank 40the board, 83 ranked
  7. UI components · Models1168 Elowin rate 57.4% · source rank 73the board, 116 ranked
  8. Websites · Models1175 Elowin rate 53.7% · source rank 81the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index150.0the scale is anchored here
Position72 of 258above 72% of the models placed
Results behind it28benchmark results
As Epoch names itGPT-5released 7 Aug 2025

Position 72 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

1 of 6 boards · 3 results
Aider polyglot · submitted, Apache-2.01 of 1 task · 69 runs scored on the task
TaskEffortScore
polyglot pass ratehigh88
medium86.70
low81.30

Percent of 225 Exercism exercises solved with a second attempt allowed, higher is better. The id carries the edit format, because the publisher says a model alone does not identify a run. Aider polyglot names these runs gpt-5 (high) (diff), gpt-5 (medium) (diff) and gpt-5 (low) (diff), and the effort beside each score says which run it is. Read from raw.githubusercontent.com ↗, which dates its own data . Aider polyglot benchmark, Apache-2.0, by the Aider project. Results are submitted by contributors rather than produced by the publisher.

1 of the 6 openly licensed boards Vitna mirrors carries a result for GPT-5 (batch), each printed as its publisher published it and none added to another. Epoch AI Benchmarking Hub, MTEB, LiveBench, HELM and Vectara hallucination leaderboard 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. 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.