LimitWatch: Fireworks AI changes

Fireworks AI: Small rate-limit tier threshold raised from <600B to <800B total parameters; ceilings unchanged.

Sun, 18 Oct 2026 00:00:00 +0000

Before: Small tier: fewer than 600B parameters | After: Small tier: fewer than 800B; Medium: 800B to <1.6T | Source: https://docs.fireworks.ai/updates/changelog

Fireworks AI: Adaptive rate-limit ceilings for Small serverless models doubled.

Wed, 07 Oct 2026 00:00:00 +0000

Before: Total Prompt TPM 108M; Uncached 27M; Generated 1.08M (per 2026-10-02 entry) | After: Total Prompt TPM 216M; Uncached 54M; Generated 2.16M | Source: https://docs.fireworks.ai/updates/changelog

Fireworks AI: Adaptive rate-limit ceilings for Small serverless models increased.

Fri, 02 Oct 2026 00:00:00 +0000

Before: Not stated in entry | After: Total Prompt TPM 108M; Uncached Prompt TPM 27M; Generated TPM 1.08M | Source: https://docs.fireworks.ai/updates/changelog

Fireworks AI: Serverless price for DeepSeek V4.1 Flash increased (uncached input / cached input / output per 1M).

Thu, 01 Oct 2026 00:00:00 +0000

Before: Standard $0.22/$0.007/$0.66; Priority $0.275/$0.00875/$0.825 | After: Standard $0.30/$0.006/$1.20; Priority $0.375/$0.0075/$1.50 | Source: https://docs.fireworks.ai/updates/changelog

Fireworks AI: Serverless adaptive rate-limit ceilings now vary by model size tier.

Tue, 01 Sep 2026 00:00:00 +0000

Before: Not stated | After: Small models higher ceilings, medium intermediate, large lower | Source: https://docs.fireworks.ai/updates/changelog