Anthropic: Claude Haiku Latest
anthropic/claude-haiku-latestThis model always redirects to the latest model in the Claude Haiku family.
Providers
10 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.10 | $0.50 | $0.01 | 1.85s | 156 tps | 100% | |
| $0.10 | $0.50 | $0.01 | 1.39s | 136 tps | 100% | |
| $0.10 | $0.50 | $0.01 | 0.88s | 147 tps | 100% | |
| $0.11 | $0.55 | $0.01 | 0.50s | 133 tps | 100% | |
| $0.11 | $0.55 | $0.01 | 0.53s | 159 tps | 100% | |
| $0.11 | $0.55 | $0.01 | 0.66s | 145 tps | 100% | |
| $0.11 | $0.55 | $0.01 | 1.32s | 190 tps | 100% | |
| $0.11 | $0.55 | $0.01 | 2.23s | 131 tps | 100% | |
| $0.10 | $0.50 | $0.01 | 2.63s | 117 tps | 99.92% | |
| $0.10 | $0.50 | $0.01 | 1.30s | 163 tps | 99.9% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Claude Haiku Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Claude Haiku Latest costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
Share of requests that at least one provider served successfully.
Apps
Tools that most often run Claude Haiku Latest, by tokens this week.
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Explore
Other models your pass can call.


