Mistral/Codestral
Mistral/Codestral is available via Vercel AI Gateway with a 256K context window and up to 4,000 output tokens. Pricing: $0.3000/1M input tokens, $0.9000/1M output tokens.
Mistral/Codestral Pricing & Specifications
What is Mistral/Codestral?
Mistral/Codestral is a large language model by Vercel AI Gateway with a 256K context window and up to 4,000 output tokens. It costs $0.30 per 1M input tokens and $0.90 per 1M output tokens. Mistral/Codestral is available via Vercel AI Gateway with a 256K context window and up to 4,000 output tokens. Pricing: $0.3000/1M input tokens, $0.9000/1M output tokens.
Capabilities
text function calling
Mistral/Codestral Cost Examples
Short prompt (500 tokens)
$0.000150
Medium prompt (2K tokens)
$0.00060
Long output (4K tokens)
$0.00360
Count tokens for Mistral/Codestral
Paste your prompt to see exact token counts and API cost estimates.
Open Token CounterSimilar Models to Mistral/Codestral
Frequently Asked Questions
How much does Mistral/Codestral cost per token? +
Mistral/Codestral costs $0.30 per 1M input tokens and $0.90 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.000750.
What is the context window for Mistral/Codestral? +
Mistral/Codestral supports a context window of 256,000 tokens (256K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Mistral/Codestral? +
Mistral/Codestral can generate up to 4,000 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Mistral/Codestral good for coding tasks? +
Yes, Mistral/Codestral supports capabilities well-suited for coding tasks including code generation, debugging, and refactoring.