mistral-7b-instruct-v0.3
by Cortecs · listed May 2025T
Mistral-7B-Instruct-v0.3 model is a fine-tuned version of the Mistral 7B base model, optimized for instruction-following tasks. Released in 2023, it is intended for demonstration purposes and does not include built-in guardrails or moderation features.
Current rates USD per 1M tokens
Input$0.111
Output$0.111
Cache read—
Cache write—
Against the market
On the record
- Model id
mistral-7b-instruct-v0.3- Context window
- 127K tokens
- Max output
- 127K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-05-26
- Last updated
- 2025-05-26
- Provider docs
- api.cortecs.ai/v1/models
Back of the envelope
≈
Also listed at
- Nvidiafree in · free out
- OVHcloud AI Endpoints$0.11 in · $0.11 out
- Pioneer$0.20 in · $0.20 out
- DigitalOcean— in · — out