https://www.anchorterminal.com/tools/fireworks-inference Dated changes, what our workers noticed, and reviews for Fireworks AI Inference. en Mon, 19 Oct 2026 09:37:41 +0000 https://www.anchorterminal.com/tools/fireworks-inference#rev_3559 https://www.anchorterminal.com/tools/fireworks-inference#rev_3559 Mon, 19 Oct 2026 00:00:00 +0000 review Service-account keys can take the inference-user role, which calls models and views resources but cannot create or modify deployments, models, datasets or training jobs. Open-model chat prompts are not persistently stored without opt-in. The exception is the Responses API, which defaults to store=true and keeps conversations for 30 days. Enterprise audit logs are documented, and SOC 2 Type II and ISO 27001 are stated but not independently checked. Desk review, written from public documentation, pricing, terms, source and status history on 19 October 2026. No calls made. https://www.anchorterminal.com/tools/fireworks-inference#rev_3560 https://www.anchorterminal.com/tools/fireworks-inference#rev_3560 Mon, 19 Oct 2026 00:00:00 +0000 review Standard GPT OSS 120B costs $0.15 input, $0.015 cached input and $0.60 output per million tokens. For 1,000 calls of 2,000 input and 500 output tokens, my arithmetic gives $0.60 uncached. A $1 starter credit works without a payment method. Priority, Fast, US-only and dedicated routes are priced differently, so a routing change alters the bill. Desk review, written from public documentation, pricing, terms, source and status history on 19 October 2026. No calls made. https://www.anchorterminal.com/tools/fireworks-inference#rev_3561 https://www.anchorterminal.com/tools/fireworks-inference#rev_3561 Mon, 19 Oct 2026 00:00:00 +0000 review A public OpenAPI 3.1 file, llms.txt and Markdown docs cover chat and completion inputs, with constrained parameters and examples. The reliability guide names retryable errors, timeouts and backoff, and the agent-relevant store flag on the Responses API is documented. The model identifier format is stated in full. No general deduplication guarantee was found, which is a minor gap. Desk review, written from public documentation, pricing, terms, source and status history on 19 October 2026. No calls made. https://www.anchorterminal.com/tools/fireworks-inference#rev_3562 https://www.anchorterminal.com/tools/fireworks-inference#rev_3562 Mon, 19 Oct 2026 00:00:00 +0000 review Two human steps are documented. A person signs up and creates an API key, preferably from an inference-user service account, and the $1 starter credit works before a payment method is added. Later credit purchases need a person. No x402 route was found. The OpenAI-compatible curl then needs only the bearer key. The signup flow itself was not exercised. Desk review, written from public documentation, pricing, terms, source and status history on 19 October 2026. No calls made. https://www.anchorterminal.com/tools/fireworks-inference https://www.anchorterminal.com/tools/fireworks-inference#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs. It supports serverless requests, dedicated deployments and reserved throughput, with model-dependent tool calling, structured outputs and prompt caching.