GPT-5.2 (batch)
Sold by 4 sellers, timed at 51.6 tok/s, on 13 Design Arena boards, and not scored by Artificial Analysis.
retrieved sha256 · 0bb53a77713f
What sellers charge
4 sellers · 4x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.875 at OpenAI to $3.50 at OpenAI. The $0.875 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
6,168 requests · 4 endpoints · 30-minute windowOpenRouter'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
4 priced · 4 timed · cheapest first- OpenAIopenai/flex · listed$0.875$7.00$0.0875not declared128knot matchednonenonenot matchedno reading
- Azureazure$1.75$14.00$0.175not declared128k65 tok/s333.93s239 req99.62%
- OpenAIopenai$1.75$14.00$0.175not declared128knot matchednonenonenot matched100%
- OpenAIopenai/fast$3.50$28.00$0.35not declared128knot matchednonenonenot matched100%
- OpenAInot matchednot matchednot matchednot matchedno offer67 tok/s372.59s11 reqno offer
- OpenAInot matchednot matchednot matchednot matchedno offer51 tok/s252.36s5,910 reqno offer
- OpenAInot matchednot matchednot matchednot matchedno offer55.5 tok/s32626ms8 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: 1 of the 4 timed routes are slower than it, and the middle route runs at 60.3 tok/s. The widest median-to-p90 gap is OpenAI's, 2.04x.
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 . 2 of the 4 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: OpenAI (openai) at 97.84% on 10 Nov 2026 and OpenAI (openai/flex) at 98.88% on 4 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 · 4 sellers- include_reasoningevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- seedevery seller
- structured_outputsevery seller
- tool_choiceevery seller
- toolsevery seller
- verbosityevery seller
- max_tokens3 of 4not Azure
- 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 modelsBlended $2.406 per million tokens, 3 in to 1 out: cheaper than 94 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 boardEach 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.
- Android native · Agents1046 Elowin rate 49.1% · source rank 38the board, 41 ranked
- Full stack · Agents1016 Elowin rate 44.2% · source rank 40the board, 44 ranked
- Godot game development · Agents1142 Elowin rate 48.1% · source rank 20the board, 34 ranked
- Mobile apps · Agents1085 Elowin rate 46.8% · source rank 45the board, 49 ranked
- Web apps · Agents1067 Elowin rate 45.5% · source rank 42the board, 47 ranked
- 3D scenes · Models1059 Elowin rate 41.5% · source rank 109the board, 113 ranked
- ASCII art · Models1136 Elowin rate 50.7% · source rank 46the board, 67 ranked
- Code · Models1158 Elowin rate 49.6% · source rank 82the board, 120 ranked
- Data visualisation · Models1202 Elowin rate 56.1% · source rank 57the board, 110 ranked
- Game development · Models1184 Elowin rate 56.0% · source rank 65the board, 120 ranked
- SVG · Models1128 Elowin rate 53.7% · source rank 60the board, 83 ranked
- UI components · Models1179 Elowin rate 51.3% · source rank 71the board, 116 ranked
- Websites · Models1186 Elowin rate 54.4% · source rank 71the board, 126 ranked
Position 52 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 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for GPT-5.2 (batch) 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.
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.
