Get started

R1 0528

Sold by 3 sellers, timed at 29.5 tok/s, on 7 Design Arena boards, with results on 1 openly licensed board, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/DeepSeek/R1 0528USD per 1M tokens · as OpenRouter routes it
deepseek/deepseek-r1-0528DeepSeek · base listing · DeepSeek tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.50per 1M tokens
Output$2.15per 1M tokens
Cached input$0.35per 1M tokens
Context164k163,840 tokens
What Vitna read · 3 providers, each from its own pricing page, kept as dated recordsin / out per 1M tokens
Googleopen weights$1.35 / $5.40confirmed 22 Nov 2026
DeepInfraopen weights$0.50 / $2.15confirmed 22 Nov 2026
Novita AIopen weights$0.70 / $2.50confirmed 22 Nov 2026

The same weights served by 3 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
AuthorDeepSeek
Listed
Context163,840 tokens
Max output32,768 tokens
Modalitiestext → text
TokenizerDeepSeek
Reasoningalways on
Moderationnot moderated by OpenRouter
Knowledge cutoff2025-03-31
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licencemit
Parameters685B · 684,531,386,000 declared
Model classDeepseekV3ForCausalLM
Downloadnot gated
Published

What sellers charge

3 sellers · 1.14x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.50 at DeepInfra to $0.571 at StreamLake. The $0.50 listed is the cheapest on offer; 1 seller is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

3,391 requests · 3 endpoints · 30-minute window
Throughput29.5 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token1.99sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread18 to 41The 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. DeepInfradeepinfra/fp4 · listed$0.50$2.15$0.35fp433k24 tok/s10689ms896 req99.09%
  2. SiliconFlowsiliconflow/fp8 · listed$0.50$2.18not listedfp8147k18 tok/s161.6s1,034 req99.16%
  3. StreamLakestreamlake$0.571$2.286not listednot declared32k41 tok/s333.07s1,461 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: 2 of the 3 timed routes are slower than it, and the middle route runs at 24 tok/s. The widest median-to-p90 gap is DeepInfra's, 2.4x.

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: SiliconFlow at 82.87% on 10 Nov 2026 and DeepInfra at 97.61% on 19 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

19 parameters · 3 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. response_formatevery seller
  5. structured_outputsevery seller
  6. temperatureevery seller
  7. top_pevery seller
  8. frequency_penalty2 of 3not StreamLake
  9. presence_penalty2 of 3not SiliconFlow
  10. stop2 of 3not SiliconFlow
  11. top_k2 of 3not StreamLake
  12. logit_bias1 of 3not SiliconFlow and StreamLake
  13. logprobs1 of 3not DeepInfra and SiliconFlow
  14. min_p1 of 3not SiliconFlow and StreamLake
  15. repetition_penalty1 of 3not SiliconFlow and StreamLake
  16. seed1 of 3not SiliconFlow and StreamLake
  17. tool_choice1 of 3not DeepInfra and StreamLake
  18. tools1 of 3not DeepInfra and StreamLake
  19. top_logprobs1 of 3not DeepInfra and SiliconFlow

7 of these 19 are accepted by every one of the 3 sellers that publish a list; the other 12 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 $0.913 per million tokens, 3 in to 1 out: cheaper than 157 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 Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. 3D scenes · Models1091 Elowin rate 53.3% · source rank 96the board, 113 ranked
  2. Code · Models1127 Elowin rate 52.6% · source rank 100the board, 120 ranked
  3. Data visualisation · Models1179 Elowin rate 60.9% · source rank 65the board, 110 ranked
  4. Game development · Models1086 Elowin rate 49.3% · source rank 104the board, 120 ranked
  5. SVG · Models1028 Elowin rate 48.7% · source rank 86the board, 83 ranked
  6. UI components · Models1091 Elowin rate 54.9% · source rank 101the board, 116 ranked
  7. Websites · Models1140 Elowin rate 52.7% · source rank 99the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed R1 0528 on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

1 of 6 boards · 4 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.04 of 22 tasks · effort unstated

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 this run DeepSeek-R1-0528, with no effort setting written on it. 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.

1 of the 6 openly licensed boards Vitna mirrors carries a result for R1 0528, each printed as its publisher published it and none added to another. MTEB, LiveBench, 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: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.