NeosantaraAI provides a compatibility layer that enables you to use the OpenAI SDK to test the NeosantaraAI API. With a few code changes, you can quickly evaluate NeosantaraAI model capabilities.
strict
parameter for function calling is ignored, which means the tool use JSON is not guaranteed to follow the supplied schema.Field | Support status |
---|---|
model | Use NeosantaraAI model names |
max_tokens | Fully supported |
max_completion_tokens | Ignored (use max_tokens instead) |
stream | Fully supported |
stream_options | Ignored |
top_p | Fully supported |
parallel_tool_calls | Supported via tools array |
stop | Fully supported |
temperature | Fully supported |
n | Must be exactly 1 |
logprobs | Ignored |
metadata | Ignored |
response_format | Fully supported (text , json_object ) |
prediction | Ignored |
presence_penalty | Fully supported |
frequency_penalty | Fully supported |
seed | Ignored |
service_tier | Ignored |
audio | Ignored |
logit_bias | Ignored |
store | Ignored |
user | Ignored |
modalities | Ignored |
top_logprobs | Ignored |
reasoning_effort | Ignored (use /v1/reasoning endpoint instead) |
tools
/ functions
fieldsShow fields
tools[n].function
fieldsField | Support status |
---|---|
name | Fully supported |
description | Fully supported |
parameters | Fully supported |
strict | Ignored |
messages
array fieldsShow fields
messages[n].role == "developer"
Field | Support status |
---|---|
content | Not applicable (ignored) |
name | Ignored |
Header | Support Status |
---|---|
x-ratelimit-limit-requests | Fully supported |
x-ratelimit-limit-tokens | Fully supported |
x-ratelimit-remaining-requests | Fully supported |
x-ratelimit-remaining-tokens | Fully supported |
x-ratelimit-reset-requests | Fully supported |
x-ratelimit-reset-tokens | Fully supported |
retry-after | Not supported |
request-id | Not supported |
openai-version | Not supported |
authorization | Fully supported |
openai-processing-ms | Not supported |