AI model
anthropic/claude-haiku-4.5
Anthropic: Claude Haiku 4.5 is a 200,000-token model served on Composite at $1.25 per million tokens in and $6.25 per million tokens out. Ranked #150 of 179 models by traffic on Composite over the last 30 days, taking 0% of tokens and 0.01% of requests.
Try in Playground| Model ID | anthropic/claude-haiku-4.5 |
|---|---|
| Provider | cv11 |
| Context window | 200,000 tokens |
| Accepts | text, image, file |
| Returns | text |
| Input price | $1.25 per million tokens |
| Output price | $6.25 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Web search | $0.0125 per result |
| Moderated | Yes - by the provider |
| Cost on a monthly plan | About 13 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 8 (base plus 7 routing variants) |
Make a Composite API key and type anthropic/claude-haiku-4.5 as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#150 of 179
0% of tokens and 0.01% of requests over 30 days.
The same model behind 7 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | anthropic/claude-haiku-4.5-normal |
cv11 | $1.25 per million tokens input · $6.25 per million tokens output |
| Normal + cheapThink | anthropic/claude-haiku-4.5-normal:cheapThink |
cv11 | $1.25 per million tokens input · $6.25 per million tokens output |
| Cheapest provider | anthropic/claude-haiku-4.5:cheapest-provider |
Azure | $1.25 per million tokens input · $6.25 per million tokens output |
| Cheapest provider + cheapThink | anthropic/claude-haiku-4.5:cheapest-provider:cheapThink |
Azure | $1.25 per million tokens input · $6.25 per million tokens output |
| cheapThink | anthropic/claude-haiku-4.5:cheapThink |
cv11 | $1.25 per million tokens input · $6.25 per million tokens output |
| Fast | anthropic/claude-haiku-4.5:fast |
Azure | $1.25 per million tokens input · $6.25 per million tokens output |
| Fast + cheapThink | anthropic/claude-haiku-4.5:fast:cheapThink |
Azure | $1.25 per million tokens input · $6.25 per million tokens output |
$1.25 per million tokens input · $6.25 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 13 plan credits, at the provider's own price.
cv11
Claude models are widely regarded for nuanced, in-character writing and for following detailed system prompts and character cards closely.
With a 200,000-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Supplied by cv11, not written by Composite.
Composite Anthropic Router · Anthropic: Claude Opus 5 (Drafted) · Anthropic: Claude Opus 4.8 (Drafted)