Model detail
DeepSeek v4 flash
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
Model specs
- Model ID
-
deepseek-v4-flash-0731
- Context length
- 1M
- Max output
- 384K
- I/O modalities
- Released
- 2026-07
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Pricing
Flat rate, unit: /1M Tokens
Input
$0.4400 /1M Tokens
Completion
$1.3200 /1M Tokens
Cache read
$0.0440 /1M Tokens
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
What should you check before using it?
1,000,000 context, 384,000 output tokens
DeepSeek model that supports reasoning. Knowledge cutoff: 2025-05. Released 2026-07-31.
Why use it through MixRoute?
DeepSeek v4 flash keeps its 1,000,000-token context on one route
The full 1,000,000-token context stays reachable on the same route. MixRoute serves DeepSeek v4 flash on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID deepseek-v4-flash-0731 and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Tool calling
DeepSeek v4 flash supports function and tool calls.
tools definition; the response returns tool_calls to execute and feed results back.
Structured output
DeepSeek v4 flash can produce JSON-formatted output on demand.
response_format: { type: "json_schema" } forces valid JSON output.
Streaming
DeepSeek v4 flash supports streamed responses.
stream: true streams tokens incrementally, so chat UIs render as they arrive.
Prompt caching
DeepSeek v4 flash supports prompt caching under supported routing conditions.
OpenAI SDK
Call DeepSeek v4 flash 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
DeepSeek v4 flash is a reasoning model. Reasoning effort can be tuned per request. Lower effort settings cut reasoning tokens and cost for routine work; reserve higher settings for problems that need deeper search. Measure quality at two or three settings before fixing one in production.
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.