Codestral API Pricing — $0.30/M input, $0.90/M output
Code-specialised model for fast, low-cost completions.
Speed
Tokens / sec
118
TTFT
270 ms
Rank
#13 of 31
$ / M ÷ t/s
$0.0038
Measured with 5 runs on a fixed prompt — see the full methodology.
Cost at scale
| Tokens / month | Est. cost (blended 3:1) |
|---|---|
| 100,000 | $0.04 |
| 1,000,000 | $0.45 |
| 10,000,000 | $4.50 |
| 100,000,000 | $45.00 |
How Codestral compares
Ministral 8B — $0.15/MMistral Small 3.1 — $0.26/MMistral Medium 3 — $0.80/MMistral Large 3 — $3.00/MGPT-OSS 120B (Cerebras) — $0.45/MGPT-5.6 Luna — $0.45/MGPT-5.4 Nano — $0.46/M
FAQ
Is Codestral cheaper than GPT-OSS 120B (Cerebras)?
Codestral costs $0.45/M blended tokens, GPT-OSS 120B (Cerebras) costs $0.45/M — GPT-OSS 120B (Cerebras) is cheaper.
How much does 1 million tokens cost with Codestral?
At a 3:1 input:output ratio, 1 million blended tokens costs approximately $0.45. Pure input costs $0.30/M; pure output costs $0.90/M.
Who provides Codestral?
Codestral is served by Mistral. Pricing was last verified on 2026-06-14 against https://mistral.ai/pricing.