Codestral 2508Chat
Mistral's low-latency coding model for chat generation, function calling, and repository-scale context.
1 rail256K ctx$0.003typical$0.45 → $1.08 /MTok
Models
Ministral 3 8B
Mistral's balanced Ministral 3 model for fast visual understanding, coding, and tool use.
- Modalities
- textimagetext
- Price
- $0.30 / $0.30/M tok
- Context
- 262K
- Max output
- 66K
- Providers
- 1
Playground
Providers
| Provider | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|
| mmistralNo trainingNo training on your data. Zero-retention available | 262K | $0.30 / $0.30/MTok | 422ms | 422ms | 100% |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.002/req
- Input
- $0.30/M tok
- Cached input
- $0.17/M tok
- Output
- $0.30/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
ministral-3-8b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ministral-3-8b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Ministral 3 8B?
Mistral's balanced Ministral 3 model for fast visual understanding, coding, and tool use.
How much does Ministral 3 8B cost?
Ministral 3 8B costs $0.30/M input tokens and $0.30/M output tokens.
What inputs and outputs does Ministral 3 8B support?
Ministral 3 8B accepts text and image and returns text.
How do I call Ministral 3 8B?
POST /api/v1/chat/completions with `"model": "ministral-3-8b"`.
What other Mistral AI models are on NinjaChat?
Codestral 2508, Ministral 3 14B, Ministral 3 3B.
