Auth Rate Limits And Cost
DeepSeek API · DeepSeek
Foundation Model & API — DeepSeek
Evaluates DeepSeek's Auth, Rate Limits & Cost across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
About DeepSeek
DeepSeek is an AI company shipping frontier open-weight models (DeepSeek-V3, DeepSeek-R1) and an OpenAI-compatible API with a separate reasoner model (deepseek-reasoner), automatic disk-based context caching, function calling, JSON output, and very low token pricing. The models are released under an MIT license alongside the hosted API.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | An integrator ships the DeepSeek API key in client-side JavaScript so the browser can call api.deepseek.com directly. | Send the key only server-side as Authorization: Bearer <DEEPSEEK_API_KEY>; never expose it in client code or a public bundle. Proxy browser requests through a backend that holds the key. | Pass / FailAi Platformcritical |
| 02 | A team asks for DeepSeek's fixed RPM/TPM limit to provision a fleet, and hardcodes a numeric cap they found in a blog post. | Treat rate limiting as dynamic — DeepSeek does not publish a fixed hard RPM/TPM and adjusts under load. Build adaptive concurrency that responds to 429s rather than provisioning against a fixed numeric cap [REQUIRES-VERIFICATION for any stated limit]. | Pass / FailAi Platformhigh |
| 03 | Under burst load the API returns HTTP 429; the client retries immediately in a tight loop, amplifying the overload. | On 429, back off with exponential delay and jitter (honor any Retry-After if present), cap retries, and reduce concurrency. Do not hot-loop retries — that worsens the throttle. | Pass / FailAi Platformhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Deepseek
- Ai Platform
- Auth Rate Limits And Cost
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Auth Rate Limits And Cost eval for DeepSeek DeepSeek API test?+
Evaluates DeepSeek's Auth, Rate Limits & Cost across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
How is the Auth Rate Limits And Cost eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Auth Rate Limits And Cost pack for DeepSeek DeepSeek API contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Auth Rate Limits And Cost pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.