Ministral 3 14BChat
Mistral's largest Ministral 3 model, pairing strong small-model quality with symmetric low token pricing.
1 rail262K ctx$0.002typical$0.35 → $0.35 /MTok
Models
Codestral 2508
Mistral's low-latency coding model for chat generation, function calling, and repository-scale context.
- Modalities
- texttext
- Price
- $0.45 / $1.08/M tok
- Context
- 256K
- Max output
- 66K
- Providers
- 1
Playground
Providers
| Provider | Context | Price · in / out |
|---|---|---|
| mmistralNo trainingNo training on your data. Zero-retention available | 256K | $0.45 / $1.08/MTok |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.003/req
- Input
- $0.45/M tok
- Cached input
- $0.18/M tok
- Output
- $1.08/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
codestral-2508
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "codestral-2508",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Codestral 2508?
Mistral's low-latency coding model for chat generation, function calling, and repository-scale context.
How much does Codestral 2508 cost?
Codestral 2508 costs $0.45/M input tokens and $1.08/M output tokens.
What inputs and outputs does Codestral 2508 support?
Codestral 2508 accepts text and returns text.
How do I call Codestral 2508?
POST /api/v1/chat/completions with `"model": "codestral-2508"`.
What other Mistral AI models are on NinjaChat?
Ministral 3 14B, Ministral 3 3B, Ministral 3 8B.
