Mistral 7B Models by MistralAI
7 models2023–2024Up to 32k ctxFrom $0.05/1M input
Details
ResearcherMistralAI
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models7
Released2023–2024
Max context32k
Capabilities
Function Calling2 of 7 models
About
Mistral AI's 7B open-weight language model family, including base and instruction-tuned revisions.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
5 in view2 retired
Mistral 7B v0.3Current
Use when the workload needs 32k context, 7B parameters, and function calling.
2024-0532k context7B parametersfunction calling
Mistral 7B Instruct v0.3Current
Use when the workload needs 32k context, 7B parameters, and function calling.
2024-0532k context7B parametersfunction calling
Mistral 7B v0.2Current
Use when the workload needs 32k context and 7B parameters.
2023-1232k context7B parameters
Mistral 7B Instruct v0.2Current
Use when the workload needs 32k context and 7B parameters.
2023-1232k context7B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Mistral 7B v0.3 | Use when the workload needs 32k context, 7B parameters, and function calling. | 2024-05 | 32k context7B parametersfunction calling | Current |
| Mistral 7B Instruct v0.3 | Use when the workload needs 32k context, 7B parameters, and function calling. | 2024-05 | 32k context7B parametersfunction calling | Current |
| Mistral 7B v0.2 | Use when the workload needs 32k context and 7B parameters. | 2023-12 | 32k context7B parameters | Current |
| Mistral 7B Instruct v0.2 | Use when the workload needs 32k context and 7B parameters. | 2023-12 | 32k context7B parameters | Current |
| Mistral 7B Instruct | Use when the workload needs 7.3B parameters. | 2023-10 | 7.3B parameters | Current |
Release Timeline
4 release groups2024-05
2 current
Mistral 7B Instruct v0.3
Current32k context7B parametersfunction calling
Mistral 7B v0.3
Current32k context7B parametersfunction calling
2023-12
2 current
Mistral 7B Instruct v0.2
Current32k context7B parameters
Mistral 7B v0.2
Current32k context7B parameters
2023-10
1 current
Mistral 7B Instruct
Current7.3B parameters
2023-09
2 retired
Mistral 7B Instruct v0.1
Archived8k context7B parameters
Mistral 7B v0.1
Archived8k context7B parameters
Specifications(7 models)
| Model | Released | Context | Parameters | Fn Calling |
|---|---|---|---|---|
| Mistral 7B v0.3 | 2024-05 | 32k | 7B | Yes |
| Mistral 7B Instruct v0.3 | 2024-05 | 32k | 7B | Yes |
| Mistral 7B v0.2 | 2023-12 | 32k | 7B | No |
| Mistral 7B Instruct v0.2 | 2023-12 | 32k | 7B | No |
| Mistral 7B Instruct | 2023-10 | — | 7.3B | No |
Available From(18 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Mistral 7B Instruct v0.2 | DeepInfra | $0.05 | $0.15 | Serverless |
| Mistral 7B Instruct v0.2 | OctoML (Deprecated) | $0.15 | $0.2 | Serverless |
| Mistral 7B Instruct v0.2 | AWS Bedrock | $0.15 | $0.2 | Serverless |
| Mistral 7B Instruct | AWS Bedrock | $0.15 | $0.2 | Serverless |
| Mistral 7B Instruct | GCP Vertex AI | $0.15 | $0.2 | Serverless |
| Mistral 7B Instruct v0.2 | Fireworks AI | $0.2 | $0.2 | Serverless |
| Mistral 7B Instruct v0.3 | Fireworks AI | $0.2 | $0.2 | Serverless |
| Mistral 7B Instruct v0.2 | Together AI | $0.2 | $0.2 | Serverless |
| Mistral 7B Instruct v0.2 | Replicate API | $0.25 | $0.25 | Serverless |
Frequently Asked Questions
- What is Mistral 7B used for?
- Mistral 7B is used for agent workflows and tool use, coding, and math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.
- How does Mistral 7B compare to Ministral?
- Mistral 7B by MistralAI is strongest where you need agent workflows and tool use, while Ministral by MistralAI is the closest related family to check for vision and multimodal work. Mistral 7B has 7 listed variants and reaches up to 32k context, while Ministral reaches up to 32k context, so compare the specs and pricing tables before choosing a production model.
- Which Mistral 7B model should I use?
- For the lowest listed input price, start with Mistral 7B v0.1 through DeepInfra at $0.05/1M input tokens. For the most capable/latest local choice, evaluate Mistral 7B v0.3 with 32k context and function calling.
