Live survey286 models · 13 providers · 17,592 auditsAudited Using Git Worktrees · SAFE →What changedHow we verifyllms.txt

Model comparison · Updated 10 Oct 2026

Llama 3.1 70B Instruct vs Codestral 2508

Codestral 2508 is about 1.3× cheaper on input ($0.30 against $0.40 per 1M tokens), though Llama 3.1 70B Instruct is cheaper on output. Codestral 2508 has the larger context window (256K against 131K tokens). For a support chatbot at 10,000 chats a day, the standard-tier bill is about $216 a month for Llama 3.1 70B Instruct and $216 for Codestral 2508.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Llama 3.1 70B Instruct vs Codestral 2508”. Retrieved 10 Oct 2026. https://modelsatlas.com/compare/meta/llama-3-1-70b-instruct/vs/mistralai/codestral

Model A

Llama 3.1 70B Instruct

by Meta · weights not marked open · GRIDD3

Input / 1M
$0.40
observed We measured
Source
Our catalogue
Retrieved
17 Aug 2026
Output / 1M$0.40
Context131K
vs

Model B

Codestral 2508

by Mistral AI · weights not marked open · GRIDD3

Input / 1M
$0.30
observed We measured
Source
Our catalogue
Retrieved
17 Aug 2026
Output / 1M$0.90
Context256K

Key numbers

Standard tier · highlighted = better

Llama 3.1 70B Instruct
Codestral 2508
Input / 1M tokens
$0.40
$0.30
Output / 1M tokens
$0.40
$0.90
Batch input / output
Not listed
$0.15 / $0.45
Context window
131,072
256,000
Input types
Not disclosed
Not disclosed
Weights
Not marked open
Not marked open
Tiers listed
standard
batch, standard
Prices checked
2026-08-17
2026-10-10

What it costs for real workloads

Monthly, standard tier, 30 days

Support chatbot10k chats/day · 1.5k in, 300 out
$216/mo
$216/mo
RAG over documents2k queries/day · 12k in, 500 out
$300/mo
$243/mo
Coding agent300 tasks/day · 60k in, 8k out
$245/mo
$227/mo

Llama 3.1 70B Instruct   Codestral 2508 · Derived from the standard-tier prices above, input and output tokens per request as stated, 30 days. Excludes caching discounts and batch. Try your own numbers.

On the atlas

Price band (A–H) × context band (1–6)

Same square. Llama 3.1 70B Instruct and Codestral 2508 share D3.

Same square as Llama 3.1 70B Instruct: Command A+ ($0.30), MiniMax M2 ($0.30), MiniMax M2.1 ($0.30). Open D3

AFreeB<$0.10C$0.10–0.30D$0.30–1E$1–3F$3–10G$10–30H$30+1<32K232–128K3128–256K4256K–1M51M6>1MINPUT PRICE PER 1M TOKENS →CONTEXT WINDOW ↑ · position within a square follows the real valueMistral Medium 3 · D3Mistral Medium 3.1 · D3Nano Banana 2 (Gemini 3.1 Flash Image) · D3DeepSeek V3 · D3Command A+ · D3Muse Glimmer 30B · D3MiniMax M2 · D3MiniMax M2.1 · D3Llama 3.1 70B InstructLlama 3.1 70B InstructCodestral 2508Codestral 2508
Llama 3.1 70B InstructCodestral 2508Nearest neighboursOpen weights
View the map as a table (1 squares)
SquarePrice bandContext bandModels
GRIDD3$0.30–1128–256KLlama 3.1 70B Instruct, Codestral 2508, Mistral Medium 3, Mistral Medium 3.1, Nano Banana 2 (Gemini 3.1 Flash Image), DeepSeek V3, Command A+, Muse Glimmer 30B, MiniMax M2, MiniMax M2.1

Capabilities side by side

Only what our records list

Llama 3.1 70B Instruct
Codestral 2508
Vision input
Not disclosed
Not disclosed
Audio input
Not disclosed
Not disclosed
Open weights
Not marked open
Not marked open
Batch tier
Not listed
Supported
Free tier
Not listed
Not listed
Thinking tier
Not listed
Not listed

Neither record lists input types, so we do not claim any.

Which should you choose?

Editorial

Choose Llama 3.1 70B Instruct if…

  • output dominates your bill: $0.40 per 1M output against $0.90

Choose Codestral 2508 if…

  • you pay by the token: it costs $0.30 per 1M input against $0.40
  • your prompts are long: it takes 256,000 tokens against 131,072
  • work can wait: it lists a batch tier and the other does not

Each reason is a fact from the tables above. Picking between them is our judgement, and we do not benchmark quality: price and context are what we can measure, so test both on your own prompts before you commit.

Questions

Is Llama 3.1 70B Instruct better than Codestral 2508?
We do not benchmark quality, so we cannot say. On the recorded numbers: Codestral 2508 is about 1.3× cheaper on input ($0.30 against $0.40 per 1M tokens), though Llama 3.1 70B Instruct is cheaper on output. Codestral 2508 has the larger context window (256K against 131K tokens). For a support chatbot at 10,000 chats a day, the standard-tier bill is about $216 a month for Llama 3.1 70B Instruct and $216 for Codestral 2508. Which is better for you depends on your task; test both on your own prompts.
Which is cheaper, Llama 3.1 70B Instruct or Codestral 2508?
Codestral 2508: $0.30 against $0.40 per 1M input tokens, and $0.90 against $0.40 per 1M output, on standard pricing.
How much does each cost per 1M tokens?
Llama 3.1 70B Instruct: $0.40 input and $0.40 output. Codestral 2508: $0.30 input and $0.90 output. Standard tier, USD.
Which has the larger context window?
Codestral 2508, with 256,000 tokens. Llama 3.1 70B Instruct has 131,072 tokens.
Do both offer batch pricing?
Llama 3.1 70B Instruct lists no batch tier. Codestral 2508 lists a batch tier, at 50% of its standard price.
Can both read images or audio?
Input types recorded for Llama 3.1 70B Instruct: none recorded. For Codestral 2508: none recorded. Where a record lists none we say so rather than guess; check each vendor's documentation before relying on a capability.
Is either model open-weight?
Llama 3.1 70B Instruct: not marked open-weight in our records. Codestral 2508: not marked open-weight in our records.
What would each cost for a support chatbot?
At 10,000 chats a day, 1,500 input and 300 output tokens each, 30 days, standard tier: about $216 a month for Llama 3.1 70B Instruct and $216 for Codestral 2508. This is our calculation from the listed prices, not a quote.

About the two models

Llama 3.1 70B Instruct

By Meta. $0.40 input and $0.40 output per 1M tokens, 131K context, atlas square D3. Tiers listed: standard.

Full specs & pricing →

Codestral 2508

By Mistral AI. $0.30 input and $0.90 output per 1M tokens, 256K context, atlas square D3. Tiers listed: batch, standard.

Full specs & pricing →

Compare Llama 3.1 70B Instruct with…

Compare Codestral 2508 with…

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.