DeepSeek V3.2 - ByteSpike

Vendor: DeepSeek Model ID: deepseek-v3-2 Capability: 64K context · tool use · streaming · structured output Pricing: per-token, mid tier (live rate) DeepSeek V3.2 was the last 3-series model and it earned a reputation for code generation that punched above its price tier. Still a fine production model for code-heavy workflows that have already validated against this version. For new work, prefer DeepSeek V4 Pro or the faster V4 Flash.

Request

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "deepseek-v3-2",
    "messages": [{"role": "user", "content": "Write a Python implementation of trie."}]
  }'

Body parameters

Field	Type	Required	Default	Notes
`model`	string	yes	—	`deepseek-v3-2`
`messages`	array	yes	—	—
`max_tokens`	integer	no	model max	Max: 8192.
`temperature`	number	no	1.0	—
`tools`	array	no	—	Function calling supported.
`response_format`	object	no	—	JSON mode.
`stream`	boolean	no	false	SSE streaming.

Response

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "deepseek-v3-2",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "class Trie..."}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 28, "completion_tokens": 412, "total_tokens": 440}
}

Code examples

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model": "deepseek-v3-2", "messages": [{"role": "user", "content": "Implement trie in Python."}]}'

Streaming + caching

"stream": true for SSE. Automatic prompt caching on stable prefixes.

Errors

Code	Trigger	Billed?
400 / 401 / 402 / 422 / 429	Standard	No
5xx	Upstream	No (auto-retry)

When to use

Code-heavy workflows on existing benchmarks.
For new work, prefer DeepSeek V4 Pro.
For lower latency, see DeepSeek V4 Flash.

Limits

Limit	Value
Context window	64K tokens
Max output	8192 tokens
Supports tool use	Yes
Supports vision	No
Supports streaming	Yes
Supports prompt caching	Automatic

Gemini 3.1 Pro DeepSeek V4 Flash

​Request

​Body parameters

​Response

​Code examples

​Streaming + caching

​Errors

​When to use

​Limits