---
title: Cerebras
slug: cerebras
url: "https://toolweight.com/tools/cerebras"
homepage: "https://cerebras.ai"
categories: llm-apis
last_verified: 2026-11-07
dataset_version: 0738be72
license: CC-BY-4.0
---

# Cerebras

> Wafer-scale inference, the fastest tokens per second available

- Serves open-weight models from wafer-scale engines
- Consistently posts the highest single-stream throughput here, often several thousand tok/s where GPUs manage a few hundred
- A latency instrument, not a general platform: a short model list
- An architecture decision you make deliberately

## Identity

|  |  |
| --- | --- |
| Name | Cerebras |
| Company | Cerebras |
| One-liner | Wafer-scale inference, the fastest tokens per second available |
| Site | https://cerebras.ai |
| Docs | https://inference-docs.cerebras.ai |
| Founded | 2016 |
| Funding | Late-stage private |
| Open source | No |
| Compared in | 1 |

## Where it is compared

### [LLM APIs](https://toolweight.com/compare/llm-apis)
Ranked **#17 of 18** on default weights.
| Field | Value | Confidence | Verified | Source | Note | Permalink |
| --- | --- | --- | --- | --- | --- | --- |
| Flagship model | Curated open-weight models (Qwen3, GLM, Llama, GPT-OSS) | Vendor-claimed | 2026-01-15 | https://inference-docs.cerebras.ai/models/overview | - | https://toolweight.com/compare/llm-apis#cerebras--flagship_model |
| Context window | 131,072 tokens | Vendor-claimed | 2026-11-07 | https://inference-docs.cerebras.ai/models/openai-oss.md | Per-model; paid tier GPT OSS 120B. | https://toolweight.com/compare/llm-apis#cerebras--context_window |
| Max output | 40,000 tokens | Vendor-claimed | 2026-11-07 | https://inference-docs.cerebras.ai/models/openai-oss.md | Per-model; paid tier GPT OSS 120B. | https://toolweight.com/compare/llm-apis#cerebras--max_output |
| Image input | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--vision |
| Audio in/out | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--audio_io |
| Open weights | ● | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--open_weights |
| OpenAI-compat API | ● | Vendor-claimed | 2026-01-15 | https://inference-docs.cerebras.ai/resources/openai | - | https://toolweight.com/compare/llm-apis#cerebras--openai_compatible |
| TTFT p50 | 200ms | Community-reported | 2026-01-15 | - | Community-measured on short prompts; not measured by toolweight. | https://toolweight.com/compare/llm-apis#cerebras--ttft_p50 |
| Output tok/s | 2,000 tok/s | Community-reported | 2026-01-15 | - | Order-of-magnitude figure, third-party benchmarks routinely report 1,500-3,000 tok/s on large MoE models where GPU hosts manage a few hundred. | https://toolweight.com/compare/llm-apis#cerebras--throughput_tps |
| $/M input | $0.35/M tok | Vendor-claimed | 2026-11-07 | https://inference-docs.cerebras.ai/models/openai-oss.md | GPT OSS 120B Developer pricing; per-model rates vary. | https://toolweight.com/compare/llm-apis#cerebras--price_in |
| $/M output | $0.75/M tok | Vendor-claimed | 2026-11-07 | https://inference-docs.cerebras.ai/models/openai-oss.md | - | https://toolweight.com/compare/llm-apis#cerebras--price_out |
| $/M cache read | $0.35/M tok | Vendor-claimed | 2026-11-07 | https://inference-docs.cerebras.ai/capabilities/prompt-caching.md | - | https://toolweight.com/compare/llm-apis#cerebras--cached_input |
| Batch discount | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#cerebras--batch_discount |
| Tool use | ◐ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--tool_use |
| Schema output | ◐ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--structured_output |
| Effort control | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--reasoning_effort |
| Computer use | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--computer_use |
| MCP support | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--mcp_support |
| Cache TTL | Automatic, no code changes; guaranteed TTL of 5 minutes, may persist up to 1 hour depending on load | Vendor-claimed | 2026-11-07 | https://inference-docs.cerebras.ai/capabilities/prompt-caching | - | https://toolweight.com/compare/llm-apis#cerebras--prompt_cache_ttl |
| Continuity policy | Same fragility as Groq, from the same cause: a small curated menu sized to available wafer-scale capacity, with models added and removed as demand shifts. No published notice window. The models themselves are open-weight, so a removal costs you a re-benchmark and a host change rather than a rewrite. | Community-reported | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--continuity_policy |
| Notice period | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#cerebras--deprecation_notice |
| Pinnable versions | ◐ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--pinned_snapshots |
| Zero retention | ● | Vendor-claimed | 2026-11-07 | https://cerebras-inference.help.usepylon.com/articles/1811589793-does-cerebras-retain-my-data | - | https://toolweight.com/compare/llm-apis#cerebras--zero_retention |
| Trains on your data | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--trains_on_data |
| AU region | ○ | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#cerebras--au_region |
| API since | 2024 | Inferred | - | - | - | https://toolweight.com/compare/llm-apis#cerebras--launch_year |
| Positioning | Wafer-scale inference, the highest tokens per second available | Inferred | - | - | - | https://toolweight.com/compare/llm-apis#cerebras--positioning |

**Verdict.** The fastest single-stream generation you can buy, by a qualitative margin; the catch is Groq's: short menu, no continuity guarantees.

## Alternatives

- [Qwen](https://toolweight.com/tools/alibaba-qwen), Alibaba's model family, huge open-weight range, closed flagship
- [Amazon Bedrock](https://toolweight.com/tools/amazon-bedrock), Multi-vendor model access inside your existing AWS account
- [Anthropic](https://toolweight.com/tools/anthropic), Claude models, built around long agentic runs and tool use
- [Cohere](https://toolweight.com/tools/cohere), Enterprise-focused models built for RAG and private deployment
- [DeepSeek](https://toolweight.com/tools/deepseek), Frontier-adjacent models at a small fraction of Western prices
- [Fireworks AI](https://toolweight.com/tools/fireworks-ai), Fast open-weight inference with strong structured-output support
- [Google Gemini](https://toolweight.com/tools/google-gemini), Gemini via AI Studio for prototyping or Vertex AI for production
- [Groq](https://toolweight.com/tools/groq), Custom LPU silicon serving open-weight models at extreme speed
- [Meta Llama](https://toolweight.com/tools/meta-llama), Open-weight Llama models, hosted almost everywhere but Meta
- [Mistral AI](https://toolweight.com/tools/mistral-ai), European lab with an open-weight lineage and EU-resident hosting
- [Moonshot AI](https://toolweight.com/tools/moonshot-ai), Kimi models, open-weight agentic performance at low cost
- [OpenAI](https://toolweight.com/tools/openai), GPT models plus audio, images and embeddings on one bill

## Logo & brand colours

SVG files: https://toolweight.com/teams/cerebras/logo.svg and https://toolweight.com/teams/cerebras/mono.svg. JSON: https://toolweight.com/api/v1/brands/cerebras.

| Hex | oklch |
| --- | --- |
| #f15a29 | oklch(66.1% 0.195 37.4) |
| #000000 | oklch(0.0% 0.000 0.0) |

## Licence and attribution

Data from Toolweight (https://toolweight.com), licensed CC-BY-4.0.

- Licence: [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
- Canonical HTML: https://toolweight.com/tools/cerebras
- Machine-readable: https://toolweight.com/tools/cerebras.md · https://toolweight.com/api/v1 · https://toolweight.com/mcp
- Toolweight takes no affiliate revenue and sells no placements.