Get started

GPT-4o-mini

Timed at 45.6 tok/s and scored 11.4 on the Coding Index.

retrieved sha256 · 0bb53a77713f

Models/OpenAI/GPT-4o-miniUSD per 1M tokens · as OpenRouter routes it
openai/gpt-4o-miniOpenAI · base listing · GPT tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.15per 1M tokens
Output$0.60per 1M tokens
Cached input$0.075per 1M tokens
Context128k128,000 tokens
What Vitna read · the provider's own pricing page, kept as a dated recordin / out per 1M tokens
OpenAIthe maker$0.15 / $0.60confirmed 22 Nov 2026

The maker's own list price, read from developers.openai.com. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.

What the list says · the fields OpenRouter publishes for this id9 fields
AuthorOpenAI
Listed
Context128,000 tokens
Max output16,384 tokens
Modalitiestext, image, file → text
TokenizerGPT
Moderationmoderated by OpenRouter
Knowledge cutoff2023-10-31
Other listingbatch variant

Measured speed

179,498 requests · 3 endpoints · 30-minute window
Throughput45.6 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token610msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread43 to 117The 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 · listed$0.15$0.60$0.075not declared16k78 tok/s40894ms10,821 req100%
  2. Azureazure · listed$0.15$0.60$0.075not declared16k117 tok/s82469ms1,138 req100%
  3. OpenAIopenai · listed$0.15$0.60$0.075not declared16k43 tok/s30593ms167,539 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 78 tok/s. The widest median-to-p90 gap is Azure's, 1.95x.

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 . Every one of the 3 sellers with a reading was at 99% or better on each of the 23 days held, 23 Oct 2026 to 21 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

17 parameters · 2 sellers
  1. frequency_penaltyevery seller
  2. logit_biasevery seller
  3. logprobsevery seller
  4. presence_penaltyevery seller
  5. response_formatevery seller
  6. seedevery seller
  7. stopevery seller
  8. structured_outputsevery seller
  9. temperatureevery seller
  10. top_logprobsevery seller
  11. top_pevery seller
  12. web_search_optionsevery seller
  13. max_completion_tokens1 of 2not OpenAI
  14. max_tokens1 of 2not Azure
  15. prediction1 of 2not Azure
  16. tool_choice1 of 2not Azure
  17. tools1 of 2not Azure

12 of these 17 are accepted by every one of the 2 sellers that publish a list; the other 5 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 $0.262 per million tokens, 3 in to 1 out: cheaper than 251 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
Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Index11.4Position 110 of 118, above 7% of the models scored.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.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
Index123.8120.5 to 126.8
Position179 of 258above 31% of the models placed
Results behind it19benchmark results
As Epoch names itGPT-4o minireleased 18 Jul 2024

Position 179 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

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for GPT-4o-mini under a name that matches its listing, and names are matched to the catalog exactly and never guessed. 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.