Hugging Face

Zephyr 7B

Type
language model
Context
33K tokens
Max output
16K
API string
anyscale/HuggingFaceH4/zephyr-7b-beta

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
anyscale $0.15 $0.15 31 Jul 2026
Fireworks AI $0.2 $0.2 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in English 1,107.52 1,098–1,117 — —
Arena Score, creative writing 1,102.7 1,087–1,119 — —
Arena Score in Spanish 1,072.75 1,017–1,128 — —
Arena Score, overall 1,069.58 1,061–1,078 — —
Arena Score in Russian 1,061.1 1,023–1,099 — —
Arena Score, programming 1,045.08 1,027–1,063 — —
Arena Score, long queries 1,041.88 1,015–1,069 — —
Arena Score, mathematics 1,040.96 1,024–1,058 — —
Arena Score, multi-turn dialogue 1,037.99 1,020–1,056 — —
Arena Score, instruction following 1,031.99 1,019–1,045 — —
Arena Score in French 1,029.63 981–1,079 — —
Arena Score, hard prompts 1,026.9 1,013–1,041 — —
Arena Score, expert questions 1,005.49 968–1,043 — —