anthropic/claude-fable-5-1
estimated usage cost
$35.00
1,000 requests × (1,000 uncached input × $10.00 + 500 output × $50.00) / 1,000,000 = $35.00
base rates; no context pricing tiers are published.
Claude Fable 5.1 vs Llama 3.3 70B Instruct
rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.
| specification | Claude Fable 5.1 anthropic/claude-fable-5-1 | Llama 3.3 70B Instruct meta/llama-3.3-70b |
|---|---|---|
| input · usd / 1m tok | $10.00 | $0.71 |
| output · usd / 1m tok | $50.00 | $0.71 |
| context window | 1mtokens | 128ktokens |
| modalities · in → out | takes text and image in, gives text out | takes text in, gives text out |
pricing
| base api rates · usd per 1m tokens | Claude Fable 5.1 anthropic/claude-fable-5-1 | Llama 3.3 70B Instruct meta/llama-3.3-70b |
|---|---|---|
| input | $10.00 | $0.71 |
| output | $50.00 | $0.71 |
| cache read | $0.25 | not published |
| cache write · default ttl | $12.50 | not published |
| cache write · 1h ttl | $20.00 | not published |
the estimate below prices one workload at these rates on every model.
specifications
| as published | Claude Fable 5.1 anthropic/claude-fable-5-1 | Llama 3.3 70B Instruct meta/llama-3.3-70b |
|---|---|---|
| creator | Anthropic | Meta |
| model type | Text generation | Text generation |
| context window | 1,000,000tokens | 128,000tokens |
| input | takes text and image in, gives text out | takes text in, gives text out |
| output | text | text |
| tool calling | not verified | not verified |
| released | sep 1, 2026 | dec 6, 2024 |
| endpoint | /v1/chat/completions | /v1/chat/completions |
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
benchmarks
| primary configuration | Claude Fable 5.1 anthropic/claude-fable-5-1 default fallback | Llama 3.3 70B Instruct meta/llama-3.3-70b |
|---|---|---|
| intelligence index · gateway rank | 53.4#1 of 90 | 7.7#85 of 90 |
| coding index | 81.6#1 of 60 | 11.9#57 of 60 |
| agentic index | 58.0#1 of 49 | not measured |
| omniscience | 43.5#1 of 86 | -54.2#81 of 86 |
| gpqa | 93.7%#7 of 88 | 49.8%#85 of 88 |
| humanity’s last exam | 59.1%#1 of 89 | 3.6%#87 of 89 |
| terminal-bench v2.1 | 91.4%#1 of 57 | 4.9%#55 of 57 |
| harvey lab | 93.0% | not measured |
| aa-lcr | 85.3% | 15.7% |
| multilingual lcr | 71.1% | not measured |
| scicode | 63.1% | not measured |
| automationbench partial | 59.4% | not measured |
| analystagent | 57.5% | not measured |
| terminal-bench v4.0 | 52.0% | not measured |
| tau banking | 47.2% | not measured |
| critpt | 29.7% | 0.0% |
| gdp.pdf all-pass | 26.2% | not measured |
| ifbench | not measured | 47.1% |
| livecodebench | not measured | 28.8% |
| tau2 | not measured | 26.6% |
| aime 2025 | not measured | 7.7% |
| terminal-bench hard | not measured | 3.0% |
| itbench | not measured | 0.6% |
Claude Fable 5.1 source ↗Llama 3.3 70B Instruct source ↗
each column describes the tested configuration named under the model; performance and costs can differ on impossibl. a score one model was not measured on is left blank rather than scored zero. indices are ranked against every model on the gateway with one. last checked 2026-09-11.
estimate your cost
one token workload, priced on every model at the published rates, in usd. change the numbers to match yours.
meta/llama-3.3-70b
estimated usage cost
$1.065
1,000 requests × (1,000 uncached input × $0.71 + 500 output × $0.71) / 1,000,000 = $1.065
base rates; no context pricing tiers are published.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
summary
Claude Fable 5.1 and Llama 3.3 70B Instruct are available through the Impossibl API. they share the /v1/chat/completions endpoint; the model identifier selects the model for a request.
Claude Fable 5.1 is created by Anthropic. It has a 1,000,000-token context window. Base API pricing (USD): $10.00 per million input tokens; $50.00 per million output tokens.
Llama 3.3 70B Instruct is created by Meta. It has a 128,000-token context window. Base API pricing (USD): $0.71 per million input tokens; $0.71 per million output tokens.
Claude Fable 5.1 →Llama 3.3 70B Instruct →
this page compares Claude Fable 5.1 vs Llama 3.3 70B Instruct as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.
view the source catalog ↗comparison as markdown ↗report a correction →