claude-fable-5-1 — API, Pricing & Context Window | Vivgrid
Run Anthropic's claude-fable-5-1 on Vivgrid: the most capable Claude model, with a 1M-token context window, 128K max output, and worldwide geo-distributed acceleration.
claude-fable-5-1 is Anthropic's most capable model and sits above the Opus tier for the most demanding reasoning and long-horizon agentic work. It pairs a 1M-token context window with 128K-token max output and always-on adaptive thinking, so a single request can plan, execute, and verify work that would otherwise need several passes.
On Vivgrid, claude-fable-5-1 is served through the native Messages API (/messages) with geo-distributed acceleration across AMER, EMEA, and APAC. It uses the same unified Vivgrid API key as the rest of the catalog, so switching an agent from claude-opus-5 is a model-string change.
Specifications
| Provider | Anthropic |
| Model ID | claude-fable-5-1 |
| Best for | Coding |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2026-06 |
| Acceleration | ⚡ Geo-Distributed — AMER, EMEA, APAC |
Pricing
Pricing in USD per 1M tokens, matching the provider's rates.
| Input | Cached input | Output |
|---|---|---|
| $10.00 | $0.50 | $50.00 |
Quick start
Call claude-fable-5-1 through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.
curl https://api.vivgrid.com/v1/messages \
-H "Authorization: Bearer $VIVGRID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-fable-5-1",
"max_tokens": 1024,
"messages": [
{ "role": "user", "content": "Say hello in English, Chinese and Spanish." }
],
"stream": true
}'Prompt caching is billed at $12.50 per 1M cache-write tokens on the 5-minute TTL and $20.00 per 1M on the 1-hour TTL, with cached reads at $0.50 — half the cache-read rate of claude-fable-5.
Ideal use cases
- Long-horizon coding agents that run for many turns without supervision
- Whole-repository migrations and refactors inside a single 1M-token pass
- High-stakes reasoning where answer quality outweighs token cost
- Deep research and analysis chaining many tool calls per session
Related models
- claude-fable-5 — the prior Fable release at the same per-token price
- claude-opus-5 — the Opus-tier model at half the price
- gpt-6-astra — OpenAI's frontier gpt-6 coding model