GLM 4.7 Flash: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Cloudflarecloudflare | No data | — | — | 99.13%◆ (best) | 98.66% | — | — | — | 131K | $0.061 / $0.400 |
| No data | — | — | — | 99.83%◆ (best) | — | — | — | 203K | $0.060 / $0.400◆ (best) | |
| No data | — | — | 68.93% | 67.78% | — | — | — | 200K | $0.070 / $0.400 | |
| No data | — | — | 98.11% | 97.89% | — | — | — | 128K | $0.060 / $0.400◆ (best) |
- No data24h —
- 7d
- 99.13%◆ (best)
- 30d
- 98.66%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.061 / $0.400
cloudflare - No data24h —
- 7d
- —
- 30d
- 99.83%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 203K
- $/Mtok
- $0.060 / $0.400◆ (best)
deepinfra/bf16bf16 - No data24h —
- 7d
- 68.93%
- 30d
- 67.78%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 200K
- $/Mtok
- $0.070 / $0.400
novita/bf16bf16 - No data24h —
- 7d
- 98.11%
- 30d
- 97.89%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 128K
- $/Mtok
- $0.060 / $0.400◆ (best)
venice/fp8fp8
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.