Home/Models
Models/Mistral

Mistral Nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.

The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.

It supports function calling and is released under the Apache 2.0 license.

mistral/mistral-nemo
Organization
Mistral
Family
mistral-nemo
Providers
4
Context
128,000
Output limit
128,000
Knowledge
2024-07
Release
2024-07-01
Updated
2024-07-01
Weights
Open
Input
text
Output
text
Capabilities
Tools, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

9 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
Chutes
unsloth/Mistral-Nemo-Instruct-2407-TEE
131,072131,072$0.0245 / $0.0978NoNo—
View
Kilo Gateway
mistralai/mistral-nemo
131,07216,384$0.15 / $0.15NoYesYes
View
DeepInfravia OpenRouter
mistralai/mistral-nemo
fp8		131,07216,384$0.019 / $0.03NoYesYes
View
DekaLLMvia OpenRouter
mistralai/mistral-nemo
fp8		131,072104,857$0.018 / $0.03NoNoYes
View
Io Netvia OpenRouter
mistralai/mistral-nemo
fp16		128,000102,400$0.03212 / $0.1168NoYesNo
View
Mistralvia OpenRouter
mistralai/mistral-nemo
unknown		131,072104,857$0.15 / $0.15NoYesYes
View
Novitavia OpenRouter
mistralai/mistral-nemo
fp8		60,28816,000$0.04 / $0.17NoNoYes
View
Parasailvia OpenRouter
mistralai/mistral-nemo
fp8		131,072104,857$0.03 / $0.03NoNoYes
View
Pioneer
mistralai/Mistral-Nemo-Instruct-2407
128,000128,000$0.02 / $0.03NoYes—
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.018Per 1M input tokens
Output from$0.03Per 1M output tokens
Available offers9Across 4 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 6 lowest-priced configurations
InputOutput
DekaLLMdekallm/fp8
$0.018$0.03
DeepInfradeepinfra/fp8
$0.019$0.03
Parasailparasail/fp8
$0.03$0.03
Io Netio-net/fp16
$0.03212$0.1168
Novitanovita/fp8
$0.04$0.17
Mistralmistral/eu
$0.15$0.15
mistralai/mistral-nemoObserved
Input
$0.019
Output
$0.03
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
DeepInfradeepinfra/fp8$0.019$0.03——
DekaLLMdekallm/fp8$0.018$0.03——
Io Netio-net/fp16$0.03212$0.1168$0.02117—
Mistralmistral/eu$0.15$0.15$0.015—
Novitanovita/fp8$0.04$0.17——
Parasailparasail/fp8$0.03$0.03——

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
DeepInfradeepinfra/fp8
1,143–3,863.27 ms
DekaLLMdekallm/fp8
513–2,928.81 ms
Io Netio-net/fp16
273–823 ms
Mistralmistral/eu
255–508.68 ms
Novitanovita/fp8
778–10,564.91 ms
Parasailparasail/fp8
382–1,042.94 ms
All latency percentiles 6 endpoints
EndpointP50P75P90P99
DeepInfradeepinfra/fp81,143 ms2,037 ms2,675.7 ms3,863.27 ms
DekaLLMdekallm/fp8513 ms776 ms1,194 ms2,928.81 ms
Io Netio-net/fp16273 ms339 ms390 ms823 ms
Mistralmistral/eu255 ms304 ms446 ms508.68 ms
Novitanovita/fp8778 ms1,060 ms1,721.7 ms10,564.91 ms
Parasailparasail/fp8382 ms562 ms657.2 ms1,042.94 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
DeepInfradeepinfra/fp8
19–29 t/s
DekaLLMdekallm/fp8
23–69 t/s
Io Netio-net/fp16
54–64 t/s
Mistralmistral/eu
102–127.2 t/s
Novitanovita/fp8
57–85 t/s
Parasailparasail/fp8
134–195 t/s
All throughput percentiles 6 endpoints
EndpointP50P75P90P99
DeepInfradeepinfra/fp819 t/s21 t/s23 t/s29 t/s
DekaLLMdekallm/fp823 t/s33 t/s49 t/s69 t/s
Io Netio-net/fp1654 t/s58 t/s61 t/s64 t/s
Mistralmistral/eu102 t/s109 t/s115.8 t/s127.2 t/s
Novitanovita/fp857 t/s66 t/s75 t/s85 t/s
Parasailparasail/fp8134 t/s158 t/s175 t/s195 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 6 endpoints
Endpoint5 minutes30 minutes24 hours
DeepInfradeepinfra/fp8
DekaLLMdekallm/fp8
Io Netio-net/fp16
Mistralmistral/eu
Novitanovita/fp8
Parasailparasail/fp8

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondMistral: Mistral Nemo
32.997%
tau bench verified airlineMistral: Mistral Nemo
23.299%
EvaluationConfigurationSourceResultsDetails
gpqa diamondMistral: Mistral Nemomistralai/mistral-nemoOpenRouter32.997%
Details
tau bench verified airlineMistral: Mistral Nemomistralai/mistral-nemoOpenRouter23.299%
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentmistralai/mistral-nemo1 turn
$0.000021
Details
Hermes Agentmistralai/mistral-nemo2–9 turns
$0.000653
Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days
Daily token usage1,688,195,403,091 reported tokens · 47 days with observations
Jul 6, 2026Oct 3, 2026
Daily observations · 47 days
Date (UTC)Reported tokensReported routes
Sep 27, 202652,090,497,1501
Sep 26, 202648,093,288,3591
Sep 20, 202651,855,258,4211
Sep 19, 202649,736,225,0381
Sep 14, 202640,777,972,7441
Sep 13, 202651,818,753,7481
Sep 12, 202643,085,521,7851
Sep 6, 202634,796,142,8611
Sep 5, 202634,998,000,2251
Aug 24, 202633,037,408,8321
Aug 23, 202627,091,228,6631
Aug 22, 202632,168,888,5421
Aug 21, 202631,509,432,5961
Aug 20, 202627,871,726,4971
Aug 19, 202629,556,597,3131
Aug 18, 202630,447,304,2071
Aug 17, 202631,410,939,9371
Aug 16, 202632,367,529,9481
Aug 15, 202631,276,846,1381
Aug 14, 202626,669,907,1701
Aug 13, 202624,563,749,5281
Aug 9, 202615,761,233,5281
Aug 8, 202620,961,391,3641
Aug 2, 202620,533,922,9311
Aug 1, 202616,406,265,7991
Jul 28, 202641,622,946,7931
Jul 27, 202642,616,203,5071
Jul 26, 202640,313,609,7421
Jul 25, 202639,576,275,8031
Jul 24, 202632,360,429,5771
Jul 23, 202631,573,036,2121
Jul 22, 202633,324,741,3011
Jul 21, 202646,922,971,4741
Jul 20, 202633,111,385,6001
Jul 19, 202637,205,621,8081
Jul 18, 202644,375,182,1971
Jul 17, 202639,476,077,1861
Jul 16, 202638,924,224,4521
Jul 15, 202639,248,417,9161
Jul 14, 202640,727,639,1821
Jul 13, 202639,076,045,0471
Jul 12, 202640,216,671,0711
Jul 11, 202640,362,997,8481
Jul 10, 202638,467,415,7401
Jul 9, 202635,673,025,2681
Jul 8, 202635,398,173,4081
Jul 7, 202638,736,278,6351

Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
mistralai/mistral-nemoObserved
Context
131,072
Maximum output
16,384
Tokenizer
Mistral
Input
text
Output
text
Moderation
No
Knowledge cutoff
2024-04-30
Added to OpenRouter
2024-07-19
Base URLhttps://openrouter.ai/api/v1
Model IDmistralai/mistral-nemo
Version IDmistralai/mistral-nemo
Weights IDmistralai/Mistral-Nemo-Instruct-2407

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Default parameters

temperature
0.3

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Mistral Nemo cost?

Listed rates start at $0.018 per million input tokens and $0.03 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Mistral Nemo?

There are 9 cataloged offers across 4 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 128,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗
Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 2c0f690855ed
  • · efb946c871d7