Mistral: Devstral 2 2512

mistralai/devstral-2512

Modalities: text+file->text
In / out price: $0.4 / $2
Context: 262K
Released: Dec 9, 2025
Knowledge cutoff: —

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

ToolsStructured outputLong context

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
presence_penalty
Presence penalty
Lowers the chance of any token that has already appeared.
response_format
Response format
For example json_object or json_schema, to constrain the shape.
seed
Seed
A fixed seed helps reproduce sampling. It does not guarantee byte-identical output.
stop
Stop
Stop when these strings are produced. A string or an array of strings.
structured_outputs
Structured outputs
Generate a parseable structure that follows a JSON Schema.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.Default 0.3
tool_choice
Tool choice
Whether to call a tool: auto, none, or a named function.
tools
Tools
Function definitions the model may call via tool_calls.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.

Models Mistral

Mistral: Devstral 2 2512

mistralai/devstral-2512

Try this model

Modalities: text+file->text
In / out price: $0.4 / $2
Context: 262K
Released: Dec 9, 2025
Knowledge cutoff: —

ToolsStructured outputLong context

Supported parameters

frequency_penalty
Frequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
presence_penalty
Presence penalty
Lowers the chance of any token that has already appeared.
response_format
Response format
For example json_object or json_schema, to constrain the shape.
seed
Seed
A fixed seed helps reproduce sampling. It does not guarantee byte-identical output.
stop
Stop
Stop when these strings are produced. A string or an array of strings.
structured_outputs
Structured outputs
Generate a parseable structure that follows a JSON Schema.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.Default 0.3
tool_choice
Tool choice
Whether to call a tool: auto, none, or a named function.
tools
Tools
Function definitions the model may call via tool_calls.
top_p
Top-p
Sample only from tokens whose cumulative probability reaches top_p.