Skip to main content

Mistral Nemo 2407

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.

Input / output price
$0.029 / $0.03 per 1M
Context
131K tokens
Released
Jul 18, 2024
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "mistral-nemo-instruct-2407".

Read docs

Providers

4 providers, cheapest first, priced per 1M tokens after gateway discounts.

ProviderInputOutput
DeepInfradeepinfra/mistral-nemo-instruct-2407
$0.029/M$0.03/M
Parasailparasail/mistral-nemo-instruct-2407
$0.03/M$0.03/M
IO.netionet/mistral-nemo-instruct-2407
$0.05675/M$0.06/M
Featherlessfeatherless/mistral-nemo-instruct-2407
$0.2175/M$0.2475/M

Pricing

Averaged across 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.08 per 1M
Average output
$0.09 per 1M
Average cache read
$0.16 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.2175/MFeatherlessLowest$0.029/MDeepInfra

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

14tokens/sacross providers

Faster than 27% of the other 599 models on the gateway

Time to first token

Lower is better

0.4sacross providers

Faster than 96% of the other 150 models on the gateway

Response latency

Lower is better

1.1sacross providers

Faster than 66% of the other 780 models on the gateway

Benchmarks

1 published score from 1 source, each linked to where it was published.

Published scores

BenchmarkScore
MMLUhuggingface.co68%

Apps

Use Mistral Nemo 2407 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Mistral Nemo 2407 FAQ

Short answers, built from the data on this page.

Mistral Nemo 2407 is a model from Mistral, released on Jul 18, 2024. 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.

On the Respan gateway, input starts at $0.029 per 1M tokens on DeepInfra, and output starts at $0.03 per 1M tokens on DeepInfra and Parasail, after gateway discounts. Averaged across its 4 providers, it costs $0.08 per 1M input tokens and $0.09 per 1M output tokens.

Mistral Nemo 2407 is available through 4 providers: DeepInfra, Parasail, IO.net, and Featherless.

Mistral Nemo 2407 accepts up to 131K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "mistral-nemo-instruct-2407". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Mistral Nemo 2407 has 1 published benchmark score, including MMLU 68%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.