DeepSeek V4 Flash Vision Exp
Sold by 4 sellers, timed at 59.6 tok/s, scored 65.0 on the Coding Index, and with results on 1 openly licensed board.
retrieved sha256 · 0bb53a77713f
What sellers charge
4 sellers · 2.55x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.17248 at DeepInfra to $0.44 at SiliconFlow. 3 sellers undercut the $0.44 listed; 0 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
1,988 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- DeepInfradeepinfra/fp8/flex · 51% off$0.17248$0.51744$0.005488fp8262knot matchednonenonenot matched0.00%
- DeepInfradeepinfra/fp8 · 51% off$0.2156$0.6468$0.00686fp8262knot matchednonenonenot matched99.02%
- DeepInfradeepinfra/fp8/priority · 51% off$0.3234$0.9702$0.01029fp8262knot matchednonenonenot matched97.59%
- SiliconFlowsiliconflow/fp8 · listed$0.44$1.32$0.028fp8393k92 tok/s331.81s285 req99.88%
- DeepInfranot matchednot matchednot matchednot matchedno offer99 tok/s55.21.38s7 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer54 tok/s20.11.17s1,464 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer54 tok/s211.06s232 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 4 timed routes are slower than it, and the middle route runs at 73 tok/s. The widest median-to-p90 gap is SiliconFlow's, 2.79x.
DeepInfra 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 . 5 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: DeepInfra (deepinfra/fp8/flex) at 0.00% on 16 Nov 2026, DeepInfra (deepinfra/fp8/priority) at 89.38% on 17 Nov 2026, DeepInfra (deepinfra/fp8) at 93.88% on 4 Nov 2026, SiliconFlow at 98.65% on 18 Nov 2026, and 1 more. 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
18 parameters · 4 sellers- frequency_penaltyevery seller
- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_kevery seller
- top_pevery seller
- logit_bias3 of 4not SiliconFlow
- min_p3 of 4not SiliconFlow
- presence_penalty3 of 4not SiliconFlow
- repetition_penalty3 of 4not SiliconFlow
- response_format3 of 4not SiliconFlow
- seed3 of 4not SiliconFlow
- stop3 of 4not SiliconFlow
- structured_outputs3 of 4not SiliconFlow
10 of these 18 are accepted by every one of the 4 sellers that publish a list; the other 8 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 $0.66 per million tokens, 3 in to 1 out: cheaper than 188 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.
Not ranked in any Design Arena category.
Epoch AI has not placed DeepSeek V4 Flash Vision Exp 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 · 23 results| Task | Score |
|---|---|
| AMPS_Hard | 88 |
| code_completion | 67.39 |
| code_generation | 69.01 |
| connections | 99.33 |
| consecutive_events | 90.05 |
| integrals_with_game | 76 |
| javascript | 63.64 |
| logic_with_navigation | 68 |
| math_comp | 97.06 |
| olympiad | 90.17 |
| paraphrase | 72.83 |
| plot_unscrambling | 57.75 |
| python | 75 |
| simplify | 65.07 |
| spatial | 96 |
| story_generation | 73.83 |
| summarize | 72.10 |
| tablejoin | 50.35 |
| tablereformat | 98.04 |
| theory_of_mind | 78.85 |
| typescript | 56.67 |
| typos | 84 |
| zebra_puzzle | 98.75 |
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 deepseek-v4-flash-vision-exp, with no effort setting written on it. 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 DeepSeek V4 Flash Vision Exp, 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.
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.
