GET

/v1/schemas/cohere/chat/v2%2Fchat

kind inputactivity chathash 25a19e9f…extracted Aug 15, 2026version currentsource upstream spec ↗

Request body

21 properties · 2 required · 28 $defs
propertytypedescriptionconstraints
model*stringThe name of a compatible [Cohere model](https://docs.cohere.com/v2/docs/models).
messages*ChatMessageV2[]A list of chat messages in chronological order, representing a conversation between the user and the model.
streambooleanDefaults to `false`.
toolsToolV2[]A list of tools (functions) available to the model. The model response may contain 'tool_calls' to the specified tools.
strict_toolsbooleanWhen set to `true`, tool calls in the Assistant message will be forced to follow the tool definition strictly. Learn more in the [Structured Outputs (Tools) guide](https://docs.cohere.com/docs/structured-outputs-json#structured-outputs-tools).
documentsstring | Document[]A list of relevant documents that the model can cite to generate a more accurate reply. Each document is either a string or document object with content and metadata.
citation_optionsCitationOptionsOptions for controlling citation generation.
response_formatobject | objectConfiguration for forcing the model output to adhere to the specified format. Supported on [Command R](https://docs.cohere.com/v2/docs/command-r), [Command R+](https://docs.cohere.com/v2/docs/command-r-plus) and newer models.
safety_modeenumUsed to select the [safety instruction](https://docs.cohere.com/v2/docs/safety-modes) inserted into the prompt. Defaults to `CONTEXTUAL`. When `OFF` is specified, the safety instruction will be omitted.CONTEXTUAL | STRICT | OFF
max_tokensintegerThe maximum number of output tokens the model will generate in the response. If not set, `max_tokens` defaults to the model's maximum output token limit. You can find the maximum output token limits for each model in the [model documentation](https://docs.cohe…
stop_sequencesstring[]A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence.
temperaturenumberDefaults to `0.3`.0 ≤ n ≤ 1 · format: float
seedintegerIf specified, the backend will make a best effort to sample tokens deterministically, such that repeated requests with the same seed and parameters should return the same result. However, determinism cannot be totally guaranteed.0 ≤ n ≤ 18446744073709552000
frequency_penaltynumberDefaults to `0.0`, min value of `0.0`, max value of `1.0`. Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the…format: float
presence_penaltynumberDefaults to `0.0`, min value of `0.0`, max value of `1.0`. Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact freque…format: float
kintegerEnsures that only the top `k` most likely tokens are considered for generation at each step. When `k` is set to `0`, k-sampling is disabled. Defaults to `0`, min value of `0`, max value of `500`.0 ≤ n ≤ 500 · default: 0
pnumberEnsures that only the most likely tokens, with total probability mass of `p`, are considered for generation at each step. If both `k` and `p` are enabled, `p` acts after `k`. Defaults to `0.75`. min value of `0.01`, max value of `0.99`.0.01 ≤ n ≤ 0.99 · format: float · default: 0.75
logprobsbooleanDefaults to `false`. When set to `true`, the log probabilities of the generated tokens will be included in the response.
tool_choiceenumUsed to control whether or not the model will be forced to use a tool when answering. When `REQUIRED` is specified, the model will be forced to use at least one of the user-defined tools, and the `tools` parameter must be passed in the request. When `NONE` is …REQUIRED | NONE
thinkingThinkingConfiguration for [reasoning features](https://docs.cohere.com/docs/reasoning).
priorityintegerControls how early the request is handled. Lower numbers indicate higher priority (default: 0, the highest). When the system is under load, higher-priority requests are processed first and are the least likely to be dropped.0 ≤ n ≤ 999 · default: 0

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"cohere","endpointId":"v2/chat","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}