Cerebras Inference vs Inkling 2 Small

Cerebras Inference 70

Graded as listed, on the hosted API lines. Public component status history at status.cerebras.ai, with components for GPT-OSS-120B, Qwen-3.8-27b and the Developer Console (20). The history feed, read on 1 November 2026, runs back to November 2025, so the whole 90 days from 3 August were read. On 25 September 2026 Cerebras posted that parts of the service might be unavailable from 10:54 UTC, services were back at 13:41 UTC and the incident was resolved at 17:14 UTC, marked major and affecting both public model components. That is about 2 hours 47 minutes with the whole shared catalogue affected, one major. A 15-minute partial degradation of Gemma 4 31B on 27 August is minor, and the 30 August firewall maintenance was announced on 25 August (10). Numeric rate-limit tables, although the trial request limit is 5 a minute on the rate-limits page and 30 a minute on the GPT OSS page, re-read on 1 November (15). SDK error classes and bounded retries with backoff (15). No public shared-inference SLA established (0). Shared inference is generally available (10).

Inkling 2 Small 30

Model reading, for the surface it's called on, Tinker's serverless inference and OpenAI-compatible API. No status page found, per the tinker listing's checks of 1 October and 4 November (0), so no readable incident history (5). The only published limit is the in-flight sample cap of 2,000, per the tinker listing's 1 October check; the OpenAI-compatible page gives no numbers and says higher or more stable throughput needs the waitlist (10). The SDK retries sampling with stable request IDs, per the tinker listing's reading of the SDK repository; the OpenAI-compatible page has no retry guidance (15). No SLA found (0). Serverless inference is 'currently in beta' on the models and pricing page and the OpenAI-compatible API is labelled Beta, read 6 November (0). 0 + 5 + 10 + 15 + 0 + 0 = 30.

Cerebras Inference 93

Public OpenAPI 3.1 (25), llms.txt and Markdown pages (10), documented capability and compatibility limits (16 of 20), typed inputs and constrained parameters (13 of 15), examples and error guidance (14 of 15), and API versions plus dated changelog (15).

Inkling 2 Small 70

Model reading. No OpenAPI file of its own; the OpenAI-compatible chat and completions endpoints and the typed Python SDK are the contract, as the tinker listing reads it (15). llms.txt on the docs host, per the tinker listing's 1 October check (10). The model card states intended use (agentic and tool-use systems, coding assistants, chatbots, RAG), inputs, outputs and limitations, and the launch post its benchmarks (16 of 20). Model IDs, context lengths and the reasoning_effort values (none to xhigh, or 0.0 to 0.99) are documented; the tool-call format and structured output aren't, for this model (8 of 15). A Python example and an HTTP 400 for models without reasoning_effort, with no error page (6 of 15). A dated Tinker changelog and a model deprecations page, per the tinker listing (15). 15 + 10 + 16 + 8 + 6 + 15 = 70.

Cerebras Inference 85

Model API with bounded output and compact request shape (25). Output token controls, streaming and structured outputs (20). Documented error classes and fixes (20). Bounded transient retries but no request-deduplication guarantee established (5 of 20). Defaults and official Python and TypeScript SDKs (15).

Inkling 2 Small 62

Model reading (tool use, structured output, caching, context, batch, SDKs). A 256K served context, max_tokens and a priced cache at $0.03 per million; tool use isn't documented for this model (15 of 25). Output-size controls through max_tokens, reasoning_effort and separate_reasoning (15 of 20). One documented error, the 400 for unsupported reasoning_effort (5 of 20). Stable request IDs make SDK sampling retries safe, per the tinker listing (15 of 20). OpenAI's SDKs work against the endpoint, with Tinker's Python SDK besides, and reasoning defaults to 0.9 (12 of 15). 15 + 15 + 5 + 15 + 12 = 62.

Cerebras Inference 70

Revocable Bearer keys with rotation instructions (20). Paid-project boundaries, but no inference-only key permission found (10 of 20). GPT OSS documentation warns about undeclared tool calls and tells callers to validate them (10 of 15). Request and audit logs in the console (15). Trust centre lists SOC 2 Type II, with reports requiring access (15 of 20).

Inkling 2 Small 57

Platform readings are the tinker listing's. Revocable API keys from the console, with no per-key scopes found (20). Org, team and project permissions with no read-only role (5). The model returns its own completions, no third-party content (10). get_audit_log() for admins (15). security.txt with a reporting address and no stated acknowledgement time (7). For the model reading, Tinker's terms commit not to use Customer Content for training, recorded under transparency. 20 + 5 + 10 + 15 + 7 = 57.

Cerebras Inference 65

Dated changelog entry on 28 October 2026, adding five models to the Dedicated catalogue and documenting image inputs in tool messages and new reasoning controls (30). Seven dated changelog entries in the 90 days from 3 August, on 28 and 31 August, two on 3 September, 22 September, 9 October and 28 October (20). Support responsiveness not established (0). Official Python and TypeScript SDKs, both last released as 1.91.0 on 8 July 2026 (15). Runtime dependency health and CI were not audited (0).

Inkling 2 Small 75

Model reading. Released 5 November 2026 (30). Churn and notice in place of release counts: Inkling, Inkling-Small (30 July) and Inkling 2 Small in about four months, and a deprecations page with dated retirements and a promise to 'aim to give advance notice' by email, with no stated period, per the tinker listing (10 of 20). A public changelog and a support address and Discord, per the tinker listing (10 of 15). Current official SDKs, Tinker's Python SDK and the OpenAI-compatible endpoint (15). SDK and cookbook CI, per the tinker listing (10). 30 + 10 + 10 + 15 + 10 = 75.