Claude Haiku 4.5
anthropic/claude-haiku-4-5POST /v1/chat/completionsAnthropic's fastest and most cost-effective model. 200K context rather than the 1M of the larger models.
Extended reasoningVisionTool callingStructured outputStreamingPrompt caching
Input / 1M
$1.00
via Anthropic
Output / 1M
$5.00
via Anthropic
Cached input / 1M
$0.1000
on a cache hit
Context
200K
max out 64K
Providers
2
failover available
2 providers serve this model
Multigrid picks between them on every request using your policy. Each price is what that route costs us, and we add no spread of our own to it.
| Provider | Upstream model id | In / 1M | Out / 1M | Billing |
|---|---|---|---|---|
| AnthropicCheapest | claude-haiku-4-5-20251001 | $1.00 | $5.00 | Credit |
| DeepInfra | anthropic/claude-haiku-4-5 | $1.00 | $5.00 | Credit |
No performance data published yet
Time to first token, throughput and uptime are measurements, and Multigrid has not served enough traffic through Claude Haiku 4.5 to publish honest ones. When it has, they will appear here per provider, taken from real requests. Nothing on this page is estimated: prices, context window and capabilities all come from the provider’s own documentation.Call it
Same request shape as every other model in the catalogue.
example.ts
const res = await client.chat.completions.create({
model: "anthropic/claude-haiku-4-5",
messages: [{ role: "user", content: "Hello" }],
reasoning: { effort: "medium" },
route: {
// pin, exclude or order the providers below
providers: ["anthropic", "deepinfra"],
sort: "price",
},
});Send Claude Haiku 4.5 a real request
Signing up takes no card and commits you to nothing — you start at a zero balance, so nothing can be charged until you decide to add credit. The playground opens on Claude Haiku 4.5 and prices every answer as it arrives, at the rate shown above — what the route costs us, with nothing of ours added. Already have an account? The second button skips the form.