impulse

Mistral Nemo Instruct 2407

Open weights
API id Mistral-Nemo-Instruct-2407
Input / 1M
$0.029
at DeepInfra
Output / 1M
$0.03
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
5
5 listings
Released
-
date not published

Pricing

List prices at DeepInfra, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.029$0.03

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$10.95
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$15.00
  • Coding agent1,000 requests a day, 40K in / 2K out$36.60
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$76.80
Use your own numbers

Where to run it

5 hosts serve Mistral Nemo Instruct 2407. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
Mistral-Nemo-Instruct-2407
$0.029 / $0.03
Mistral-Nemo-Instruct-2407
$0.04 / $0.12
+105% vs headline
Mistral-Nemo-Instruct-2407
$0.13 / $0.13
+344% vs headline
Fireworks AIInference
mistral-nemo-instruct-2407
$0.20 / $0.20
+584% vs headline
mistral-nemo-instruct-2407
$0.30 / $0.30
+926% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than DeepInfra.

Smaller Mistral AI models

No cheaper Mistral AI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Mistral-Nemo-Instruct-2407",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mistral Nemo Instruct 2407 cost?

On DeepInfra, Mistral Nemo Instruct 2407 costs $0.029 per million input tokens and $0.03 per million output tokens.

Which APIs offer Mistral Nemo Instruct 2407?

Mistral Nemo Instruct 2407 runs on 5 APIs: DeepInfra, Nebius AI Studio, OVHcloud AI Endpoints, Fireworks AI and GradientAI.

What is Mistral Nemo Instruct 2407's context window?

131K tokens, with up to 131K tokens in one reply.

Is Mistral Nemo Instruct 2407 being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Mistral Nemo Instruct 2407?

Models that cost less and keep most of what it can do: gpt-oss-20b on Darkbloom (3% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Mistral Nemo Instruct 2407's API model id?

Use Mistral-Nemo-Instruct-2407 with DeepInfra. Other hosts use their own ids: mistral-nemo-instruct-2407 on Fireworks AI, mistral-nemo-instruct-2407 on GradientAI.

Sources

Raw catalog entry for Mistral-Nemo-Instruct-2407 on DeepInfra
{
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "input_cost_per_token": 2.9e-8,
  "output_cost_per_token": 3e-8,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": true,
  "supports_function_calling": true,
  "source": "https://deepinfra.com/pricing"
}