Provider directory

Blended $/1M

$6.25

TTFT

480ms

Throughput

90t/s

Reputation

91■

Frontier model quality and the de-facto API standard the whole ecosystem mimics.

Blended $/1M

$9.00

TTFT

520ms

Throughput

78t/s

Reputation

90▲

Long-context reasoning, strong safety posture and enterprise trust.

Blended $/1M

$0.90

TTFT

400ms

Throughput

120t/s

Reputation

88▲

One API and one bill across nearly every provider and model.

Blended $/1M

$0.69

TTFT

120ms

Throughput

480t/s

Reputation

87▲

Category-leading tokens/sec thanks to custom LPU silicon.

Blended $/1M

$0.88

TTFT

340ms

Throughput

130t/s

Reputation

86▲

Huge open-model catalog with fine-tuning and dedicated endpoints.

Blended $/1M

$0.90

TTFT

300ms

Throughput

145t/s

Reputation

85▲

Low-latency serving stack and strong function-calling support.

Blended $/1M

—

TTFT

700ms

Throughput

100t/s

Reputation

85▲

Code-first serverless GPUs; full control of the serving stack.

Blended $/1M

$3.13

TTFT

610ms

Throughput

85t/s

Reputation

84■

Enterprise-grade cloud integration, global regions and compliance breadth.

Blended $/1M

$0.80

TTFT

280ms

Throughput

140t/s

Reputation

84▲

Production dedicated deployments with strong autoscaling.

Blended $/1M

$4.00

TTFT

430ms

Throughput

95t/s

Reputation

83▲

EU-based lab with both open weights and a hosted API.

Blended $/1M

$0.30

TTFT

340ms

Throughput

120t/s

Reputation

83▲

Flat-rate subscription pricing that decouples cost from token volume.

Blended $/1M

$0.70

TTFT

110ms

Throughput

520t/s

Reputation

82▲

Extreme throughput from wafer-scale engines.

Blended $/1M

$1.00

TTFT

650ms

Throughput

80t/s

Reputation

82■

Built-in web-search grounding with citations.

Blended $/1M

$0.38

TTFT

360ms

Throughput

110t/s

Reputation

81■

Aggressive per-token pricing on popular open models.

Blended $/1M

$1.70

TTFT

900ms

Throughput

60t/s

Reputation

80■

Broadest catalog including image, audio and video models.

Blended $/1M

$0.90

TTFT

130ms

Throughput

400t/s

Reputation

79■

High-throughput serving of large open models.

Blended $/1M

$0.50

TTFT

370ms

Throughput

118t/s

Reputation

79▲

EU-hosted inference with a full GPU cloud behind it.

Blended $/1M

$0.50

TTFT

330ms

Throughput

125t/s

Reputation

78■

Developer-friendly platform with tuned serving.

Blended $/1M

$0.35

TTFT

380ms

Throughput

105t/s

Reputation

77▲

Low prices and a broad multimodal catalog.

Blended $/1M

$0.40

TTFT

350ms

Throughput

115t/s

Reputation

76▲

Cheap open-model inference plus raw GPU rental.