Model detail
DeepSeek-V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.
Model specs
- Model ID
-
deepseek-v3.1
- Context length
- 163.84K
- Max output
- 128K
- I/O modalities
- Released
- 2025-08
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Pricing
Flat rate, unit: /1M Tokens
Input
$0.5600 /1M Tokens
Completion
$1.6800 /1M Tokens
Cache read
$0.0700 /1M Tokens
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Large hybrid reasoning model (671B parameters, 37B active)
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
What should you check before using it?
163,840 context, 128,000 output tokens
DeepSeek model that supports reasoning, tool calling and structured output. Knowledge cutoff: 2025-08. Released 2025-08-21.
Why use it through MixRoute?
DeepSeek-V3.1 runs tools and structured output here
Tool calling and structured output run on that route as well. MixRoute serves DeepSeek-V3.1 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID deepseek-v3.1 and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
DeepSeek-V3.1 supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
DeepSeek-V3.1 can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
DeepSeek-V3.1 supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
DeepSeek-V3.1 supports prompt caching under supported routing conditions.
OpenAI SDK
Call DeepSeek-V3.1 through MixRoute's OpenAI-compatible endpoint.
base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.
08
Token cost estimator
Live estimate from this page's pricing, not an actual bill
Share of the same prefix read repeatedly, up to 100%
09
FAQ
Reasoning tokens are billed as output on DeepSeek-V3.1, at $1.6800 per 1,000,000 token. They are generated before the visible answer and count toward both latency and spend, so a higher reasoning setting costs more even when the final answer is short.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.