Context Window

Compare

Codestral Mamba Latest vs Sonar Reasoning Pro

This page is context-first: how much text each model can take in one request. Full specs adds capabilities and limits; the pricing matrix below is only about $/million tokens from hosts that list both models.

Mistral

Model

Codestral Mamba Latest

Context window

256K

256,000 tokens · ~192K words

Model page
Perplexity

Model

Sonar Reasoning Pro

Image input

Context window

128K

128,000 tokens · ~96K words

Model page

Context window · side by side

Bar length is relative to the larger of the two windows (100% = max of this pair). This is not pricing.

Codestral Mamba Latest256K
Sonar Reasoning Pro128K

Codestral Mamba Latest has about 2× the context window of the other in this pair.

Token calculator →Memory savings →

Codestral Mamba Latest has 100% more context capacity (256K vs 128K tokens). Codestral Mamba Latest is 87% cheaper on input.

Quick verdicts

Short takeaways — validate with your own workloads.

  • Long document processing

    Use Codestral Mamba Latest. Its 256K context fits entire documents without chunking (vs 128K).

  • RAG / high-volume retrieval

    Use Codestral Mamba Latest. Input tokens are 87% cheaper — critical when sending large retrieved contexts.

Full specs

Context, output, capabilities, and dates. Green highlights the favorable value where we compute a winner.

SpecCodestral Mamba LatestSonar Reasoning Pro
Context window256,000 tokens (256K)128,000 tokens (128K)
Max output tokens256,000 tokens (256K)N/A
Speed tierBalancedDeep
VisionNoYes
Function callingNoNo
Extended thinkingNoYes
Prompt cachingNoNo
Batch APINoNo
Release dateN/AMar 2025

Pricing matrix

Dollar rates only: hosts that list both models, per 1M tokens. For how much text fits, use the context section above — not this table.

ProviderCodestral Mamba Latest inCodestral Mamba Latest outSonar Reasoning Pro inSonar Reasoning Pro out
Mistral$0.250/M$0.250/M——
Perplexity——$2.00/M$8.00/M

Frequently asked questions

Codestral Mamba Latest has a larger context window: 256K tokens vs 128K. For long documents, large codebases, or extended agent sessions, the larger context window reduces the need to chunk inputs or summarize history.

Powered by Mem0

Use a smaller model.
Get better results.

Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.

Calculate your savingsLearn about Mem0

Example: a multi-turn chat session

Without Mem0~128K tokens sent
Full history
Repeated info
Old context
With Mem0~20K tokens sent
Key memories
Current turn

80% less to send — works with any model