Get started

GPT-5.4 Mini (batch)

Sold by 4 sellers, timed at 108 tok/s, scored 56.1 on the Coding Index, and with results on 1 openly licensed board.

retrieved sha256 · 0bb53a77713f

Models/OpenAI/GPT-5.4 Mini (batch)USD per 1M tokens · as OpenRouter routes it
openai/gpt-5.4-mini:batchOpenAI · batch variant · GPT tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.375per 1M tokens
Output$2.25per 1M tokens
Cached input$0.0375per 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 id12 fields
AuthorOpenAI
Listed
Canonical idopenai/gpt-5.4-mini-20260317
Context400,000 tokens
Max output128,000 tokens
Modalitiesfile, image, text → text
TokenizerGPT
Reasoningoptional, off by default · effort xhigh, high, medium, low, none, medium by default
Moderationmoderated by OpenRouter
Variantbatch
Knowledge cutoff2025-08-31
Other listingbase listing

What sellers charge

4 sellers · 4x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.375 at OpenAI to $1.50 at OpenAI. The $0.375 listed is the cheapest on offer; 3 sellers are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

29,058 requests · 5 endpoints · 30-minute window
Throughput108 tok/sMedian output rate, weighted across the 5 endpoints serving it by the requests each answered.the speed board
First token814msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread75 to 138The 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

5 priced · 5 timed · cheapest first
  1. OpenAIopenai/flex · listed$0.375$2.25$0.0375not declared128knot matchednonenonenot matched100%
  2. Azureazure$0.75$4.50$0.075not declared128k75 tok/s361.27s1,847 req100%
  3. Azureazure$0.75$4.50$0.075not declared128k138 tok/s54.4719ms5 req100%
  4. OpenAIopenai$0.75$4.50$0.075not declared128knot matchednonenonenot matched100%
  5. OpenAIopenai/fast$1.50$9.00$0.15not declared128knot matchednonenonenot matched100%
  6. OpenAInot matchednot matchednot matchednot matchedno offer100 tok/s50862ms24 reqno offer
  7. OpenAInot matchednot matchednot matchednot matchedno offer119 tok/s56581ms30 reqno offer
  8. OpenAInot matchednot matchednot matchednot matchedno offer110 tok/s54783ms27,152 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: 2 of the 5 timed routes are slower than it, and the middle route runs at 110 tok/s. The widest median-to-p90 gap is Azure's, 2.54x.

OpenAI publishes 3 offers and had 3 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 . 3 of the 5 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 85.71% on 4 Nov 2026, OpenAI (openai) at 97.77% on 10 Nov 2026, and OpenAI (openai/flex) at 98.87% on 23 Oct 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 · 4 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_tokens3 of 4not Azure
  11. max_completion_tokens1 of 4not OpenAI (openai), OpenAI (openai/fast), and OpenAI (openai/flex)

9 of these 11 are accepted by every one of the 4 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 $0.844 per million tokens, 3 in to 1 out: cheaper than 174 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 Index56.1Position 44 of 118, above 62% of the models scored.the coding leaderboard
Agentic Index17.9Position 47 of 94, above 50% 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
Index149.4147.7 to 151.1
Position75 of 258above 71% of the models placed
Results behind it15benchmark results
As Epoch names itGPT-5.4 Minireleased 17 Mar 2026

Position 75 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 · 23 results
LiveBench · publisher-run, Apache-2.023 of 23 tasks · 71 runs scored on each task · at xhigh 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-5.4-mini-xhigh. Read from livebench.ai ↗, which dates its own data . LiveBench, Apache-2.0. Results produced by the LiveBench maintainers on questions refreshed monthly.

1 of the 6 openly licensed boards Vitna mirrors carries a result for GPT-5.4 Mini (batch), each printed as its publisher published it and none added to another. Epoch AI Benchmarking Hub, 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.