Claude Fable 5.1
claude-fable-5-1
- Context
- 1M
- Input
- $10.00
- Output
- $50.00
- Cache read
- $0.25
- Cache write
- 5 min$12.50
- 1 hour$20.00
List prices and published task-bench scores for major model APIs. Each bench is one board, and an empty cell means that board published no score.
Cache reads are 0.1× input, 0.05× on Opus 5.5 and 0.025× on Fable 5.1.
claude-fable-5-1
claude-fable-5
claude-opus-5-5
claude-opus-5
claude-opus-4-8
claude-opus-4-7
claude-opus-4-6
claude-sonnet-5-5
claude-sonnet-5
claude-sonnet-4-6
claude-haiku-4-5
A prompt over 272k input tokens is billed at the long-context rate for every token in the request.
Language
gpt-6-astra
gpt-6-sol
gpt-6-luna
gpt-5.6-sol
gpt-5.6-terra
gpt-5.6-luna
gpt-5.6-cyber
gpt-5.5
No list price is recorded on this sheet.
gpt-5.3-codex
gpt-5
API shutdown 11 December 2026
gpt-4.1
gpt-4.1-mini
gpt-4.1-nano
gpt-4o
gpt-4o-mini
o3
API shutdown 11 December 2026
Voice
gpt-realtime-2.1
gpt-realtime-2.1-mini
gpt-live-1
gpt-realtime-translate
gpt-realtime-whisper
gpt-live-transcribe
gpt-transcribe
gpt-4o-transcribe
gpt-4o-mini-transcribe
Image
gpt-image-2.5
gpt-image-2
Embeddings
text-embedding-3-large
text-embedding-3-small
Tools
web-search
file-search
Gemini 3.8 Flash is on an introductory rate through 31 December 2026.
Language
gemini-3.8-flash
gemini-3.1-pro-preview
gemini-3.5-flash-lite
gemini-3-flash-preview
Voice
gemini-3.1-flash-live-preview
gemini-3.5-live-translate-preview
gemini-3.5-transcribe-live
gemini-3.5-transcribe
gemini-2.5-flash-native-audio
gemini-3.1-flash-tts-preview
gemini-2.5-flash-preview-tts
Embeddings
gemini-embedding-001
Tools
google-search-grounding
A prompt of 200k tokens or more is billed at the higher rate for every token in the request.
Language
grok-4.7
grok-4.6
grok-4.5
grok-4.3
grok-build-0.1
Voice
grok-voice-think-fast-2.0
grok-stt
grok-tts
Image
grok-imagine-image
grok-imagine-image-2.0
grok-imagine-image-quality
grok-imagine-video
grok-imagine-video-1.5
Tools
x-web-search
x-search
code-execution
collections-search
kimi-k2.6
kimi-k2.7-code
kimi-k2.7-code-highspeed
Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday. Other hours are half price.
deepseek-flash
deepseek-v4-pro
qwen3-max
qwen3-max-beijing
qwen3.7-plus
No list price is recorded on this sheet.
Language
mistral-large-3
mistral-medium-3.5
mistral-small-4
Voice
voxtral-mini-transcribe-realtime
voxtral-tts
voxtral-small
minimax-m3
No list price is recorded on this sheet.
One OpenAI-compatible endpoint in front of the providers above. Token rates are passed through. The fee is on buying credits, and on bring-your-own-key usage past a monthly allowance. The listed price for a model is the cheapest endpoint, and routing is price-weighted unless you pin a provider.
Checked 27 September 2026. The table shows the standard list price. Batch and fast tiers are in the JSON.