Mistral API pricing

68 Mistral models: text, embeddings, text to speech, speech to text, document ocr, from price book 2026-10-22.

Billing rules Veqen applies

  • Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
  • Audio models: per second of audio or per character of text, or per token where the model bills tokens.

Also recognized as: mistral_ai, mistralai (framework, gateway and OpenTelemetry names).

Reconcile your bill

Mistral doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.

Prices come from Mistral's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.

Text 49 models

ModelInputOutputCached inputBatch inputContextStatus
labs-leanstral-1-5-1$0.00$0.00——262.1K
devstral-small-latest$0.10$0.30$0.01—256K
ministral-3-3b-2512$0.10$0.10$0.01—131.1K
ministral-3b-2512$0.10$0.10$0.01—131.1K
ministral-3b-latest$0.10$0.10$0.01—131.1K
mistral-small$0.10$0.30$0.01—32K
voxtral-small-2507$0.10$0.40$0.01—32.8K
voxtral-small-latest$0.10$0.40$0.01—32.8K
magistral-small-latest$0.15$0.60$0.015—262.1K
ministral-3-8b-2512$0.15$0.15$0.015—262.1K
ministral-8b-2512$0.15$0.15$0.015—262.1K
ministral-8b-latest$0.15$0.15$0.015—262.1K
mistral-small-2603$0.15$0.60$0.015—262.1K
mistral-small-latest$0.15$0.60$0.015—262.1K
mistral-vibe-cli-fast$0.15$0.60$0.015—262.1K
ministral-14b-2512$0.20$0.20$0.02—262.1K
ministral-14b-latest$0.20$0.20$0.02—262.1K
ministral-3-14b-2512$0.20$0.20$0.02—262.1K
codestral-mamba-latest$0.25$0.25$0.025—256K
mistral-tiny$0.25$0.25$0.025—32K
codestral-2508$0.30$0.90$0.03—128K
codestral-latest$0.30$0.90$0.03—128K
mistral-code-fim-latest$0.30$0.90$0.03—128K
mistral-code-latest$0.30$0.90$0.03—128K
open-mistral-nemo$0.30$0.30$0.03—128K
devstral-latest$0.40$2.00$0.04—256K
devstral-medium-latest$0.40$2.00$0.04—256K
mistral-code-agent-latest$0.40$2.00$0.04—256K
mistral-large-2512$0.50$1.50$0.05—262.1K
mistral-large-3$0.50$1.50$0.05—262.1K
mistral-large-latest$0.50$1.50$0.05—262.1K
mistral-large-4$0.68$2.09$0.068—1M
mistral-large-4-0$0.68$2.09$0.068—1M
glm-5-2$1.40$4.40$0.14—1M
zai-glm-5$1.40$4.40$0.14—1M
zai-glm-5-3$1.40$4.40$0.14—1M
zai-glm-latest$1.40$4.40$0.14—1M
magistral-medium-latest$1.50$7.50$0.15—262.1K
mistral-medium$1.50$7.50$0.15—262.1K
mistral-medium-2604$1.50$7.50$0.15—262.1K
mistral-medium-3$1.50$7.50$0.15—262.1K
mistral-medium-3-5$1.50$7.50$0.15—262.1K
mistral-medium-3.5$1.50$7.50$0.15—262.1K
mistral-medium-latest$1.50$7.50$0.15—262.1K
mistral-vibe-cli-latest$1.50$7.50$0.15—262.1K
mistral-vibe-cli-with-tools$1.50$7.50$0.15—262.1K
pixtral-large-latest$2.00$6.00$0.20—128K
labs-leanstral-1-5$0.00$0.00——262.1KRetired 2026-09-30
zai-glm-5-2$1.40$4.40$0.14—1MRetires 2026-10-31

Embeddings 4 models

ModelPriceStatus
mistral-embed$0.10 per 1M tokens
mistral-embed-2312$0.10 per 1M tokens
codestral-embed$0.15 per 1M tokens
codestral-embed-2505$0.15 per 1M tokens

Text to speech 2 models

ModelPriceStatus
voxtral-mini-tts-2603$16.00 per 1M characters
voxtral-mini-tts-latest$16.00 per 1M characters

Speech to text 6 models

ModelPriceStatus
voxtral-mini-2602$0.003 per minute
voxtral-mini-latest$0.003 per minute
voxtral-mini-realtime-2602$0.006 per minute
voxtral-mini-realtime-latest$0.006 per minute
voxtral-mini-transcribe-realtime-2602$0.006 per minute
voxtral-mini-transcribe-realtime-latest$0.006 per minute

Document OCR 7 models

ModelPriceStatus
mistral-ocr-2512$2.00 per 1K pages
mistral-ocr-3$2.00 per 1K pages
mistral-ocr-3-0$2.00 per 1K pages
mistral-ocr-4$4.00 per 1K pages
mistral-ocr-4-1$4.00 per 1K pages
mistral-ocr-latest$4.00 per 1K pages
mistral-ocr-4-0$4.00 per 1K pagesRetired 2026-09-30