Mistral Nemo
Sold by 6 sellers, timed at 40 tok/s, and not scored by Artificial Analysis.
retrieved sha256 · 0bb53a77713f
The same weights, served by one provider at its own list price, read from deepinfra.com. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.
What sellers charge
6 sellers · 9.06x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.01656 at Io Net to $0.15 at Mistral. 3 sellers undercut the $0.029 listed; 2 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
487,256 requests · 6 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
6 priced · 6 timed · cheapest first- Io Netio-net/fp16 · 28% off$0.01656$0.0216$0.0108fp16102k51 tok/s31704ms19,325 req99.86%
- DekaLLMdekallm/fp8$0.018$0.03not listedfp8105k19 tok/s131.05s2,315 req99.09%
- DeepInfradeepinfra/fp8/flex$0.0232$0.024not listedfp8105knot matchednonenonenot matched97.84%
- DeepInfradeepinfra/fp8 · listed$0.029$0.03not listedfp816knot matchednonenonenot matched100%
- Parasailparasail/fp8$0.03$0.03not listedfp8105k22 tok/s15509ms930 req84.33%
- Mistralmistral/eu$0.15$0.15$0.015not declared105k81 tok/s53447ms18,478 req100%
- DeepInfranot matchednot matchednot matchednot matchedno offer38 tok/s28460ms446,207 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer30 tok/s15461ms1 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: 4 of the 6 timed routes are slower than it, and the middle route runs at 34 tok/s. The widest median-to-p90 gap is DeepInfra's, 2x.
DeepInfra publishes 2 offers and had 2 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 . 4 of the 6 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Parasail at 74.84% on 20 Nov 2026, DekaLLM at 89.65% on 19 Nov 2026, DeepInfra (deepinfra/fp8/flex) at 92.30% on 17 Nov 2026, and Io Net at 97.43% on 10 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 · 6 sellers- frequency_penaltyevery seller
- max_tokensevery seller
- presence_penaltyevery seller
- seedevery seller
- stopevery seller
- temperatureevery seller
- top_pevery seller
- response_format5 of 6not Io Net
- structured_outputs5 of 6not Io Net
- logit_bias4 of 6not Io Net and Mistral
- repetition_penalty4 of 6not DekaLLM and Mistral
- top_k4 of 6not DekaLLM and Mistral
- logprobs3 of 6not DeepInfra (deepinfra/fp8), DeepInfra (deepinfra/fp8/flex), and Mistral
- min_p3 of 6not DekaLLM, Mistral, and Parasail
- tool_choice3 of 6not DeepInfra (deepinfra/fp8/flex), DekaLLM, and Parasail
- tools3 of 6not DeepInfra (deepinfra/fp8/flex), DekaLLM, and Parasail
- top_logprobs3 of 6not DeepInfra (deepinfra/fp8), DeepInfra (deepinfra/fp8/flex), and Mistral
7 of these 17 are accepted by every one of the 6 sellers that publish a list; the other 10 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 $0.029 per million tokens, 3 in to 1 out: cheaper than 339 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 boardNot ranked in any Design Arena category.
Position 198 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 Mistral Nemo 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: 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.
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.
