Best price — Output ($/1M tokens)
Best price — Output ($/1M tokens)
Markets
One row per access path (venue → underlying provider). Prices are each venue's published list price; performance is measured by Artificial Analysis. Your actual bill may vary by routing settings, fallbacks, region / ZDR, long-context tiers, and request features (JSON mode, tools, vision).
- #
- 1
- Provider
- deepseek
- Class
- Official
$ / 1M tokens- Input $ / 1M tokens
- $0.14
- Output $ / 1M tokens
- $0.28
- Cache read $ / 1M tokens
- $0.03
-65.0% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 2
- Provider
- zeroeval → deepseek
- Class
- Reseller
$ / 1M tokens- Input $ / 1M tokens
- $0.28
- Output $ / 1M tokens
- $0.42
- Cache read $ / 1M tokens
- —
-47.6% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 3
- Provider
- openrouter → deepinfra
- Class
- Reseller
$ / 1M tokens- Input $ / 1M tokens
- $0.32
- Output $ / 1M tokens
- $0.89
- Cache read $ / 1M tokens
- —
+11.1% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 4
- Provider
- openrouter → deepseek
- Class
- Reseller
$ / 1M tokens- Input $ / 1M tokens
- $0.26
- Output $ / 1M tokens
- $1.03
- Cache read $ / 1M tokens
- —
+28.4% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 5
- Provider
- openrouter → streamlake
- Class
- Reseller
$ / 1M tokens- Input $ / 1M tokens
- $0.26
- Output $ / 1M tokens
- $1.03
- Cache read $ / 1M tokens
- —
+28.4% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 6
- Provider
- gmi
- Class
- Direct host
Disabled by gmi · stale$ / 1M tokens- Input $ / 1M tokens
- $0.21
- Output $ / 1M tokens
- $0.31
- Cache read $ / 1M tokens
- —
-61.3% vs consensus- TTFT
- 3.6s
- Throughput
- 48.8 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 7
- Provider
- deepinfra
- Class
- Direct host
Disabled by deepinfra · stale$ / 1M tokens- Input $ / 1M tokens
- $0.26
- Output $ / 1M tokens
- $0.38
- Cache read $ / 1M tokens
- —
-52.6% vs consensus- TTFT
- 1.2s
- Throughput
- 30.7 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 8
- Provider
- novita
- Class
- Direct host
Disabled by novita · stale$ / 1M tokens- Input $ / 1M tokens
- $0.27
- Output $ / 1M tokens
- $0.4
- Cache read $ / 1M tokens
- $0.13
-50.1% vs consensus- TTFT
- 1.9sreasoning 2.0s
- Throughput
- 42.1 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 9
- Provider
- siliconflow
- Class
- Direct host
Disabled by siliconflow · stale$ / 1M tokens- Input $ / 1M tokens
- $0.27
- Output $ / 1M tokens
- $0.42
- Cache read $ / 1M tokens
- $0.14
-47.6% vs consensus- TTFT
- 2.4sreasoning 2.1s
- Throughput
- 21.0 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 10
- Provider
- parasail
- Class
- Direct host
Disabled by parasail · stale$ / 1M tokens- Input $ / 1M tokens
- $0.28
- Output $ / 1M tokens
- $0.45
- Cache read $ / 1M tokens
- $0.13
-43.8% vs consensus- TTFT
- 1.9s
- Throughput
- 81.5 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 11
- Provider
- nebius
- Class
- Direct host
Disabled by nebius · stale$ / 1M tokens- Input $ / 1M tokens
- $0.3
- Output $ / 1M tokens
- $0.45
- Cache read $ / 1M tokens
- —
-43.8% vs consensus- TTFT
- 2.0sreasoning 2.4s
- Throughput
- 104.4 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 12
- Provider
- digitalocean
- Class
- Direct host
Disabled by digitalocean · stale$ / 1M tokens- Input $ / 1M tokens
- $0.25
- Output $ / 1M tokens
- $0.8
- Cache read $ / 1M tokens
- $0.15
-0.1% vs consensus- TTFT
- 1.4sreasoning 983ms
- Throughput
- 65.7 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 13
- Provider
- openrouter → novita
- Class
- Reseller
Disabled by openrouter · disabled · fp8$ / 1M tokens- Input $ / 1M tokens
- $0.4
- Output $ / 1M tokens
- $1.3
- Cache read $ / 1M tokens
- —
+62.3% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 14
- Provider
- friendli-ai
- Class
- Direct host
Disabled by friendli-ai · stale$ / 1M tokens- Input $ / 1M tokens
- $0.5
- Output $ / 1M tokens
- $1.5
- Cache read $ / 1M tokens
- —
+87.3% vs consensus- TTFT
- 4.7s
- Throughput
- 55.2 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 15
- Provider
- fireworks
- Class
- Direct host
Disabled by fireworks · stale$ / 1M tokens- Input $ / 1M tokens
- $0.56
- Output $ / 1M tokens
- $1.68
- Cache read $ / 1M tokens
- —
+109.7% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
- #
- 16
- Provider
- Class
- Direct host
Disabled by google · stale$ / 1M tokens- Input $ / 1M tokens
- $0.56
- Output $ / 1M tokens
- $1.68
- Cache read $ / 1M tokens
- $0.06
+109.7% vs consensus- TTFT
- 5.6sreasoning 2.3s
- Throughput
- 17.1 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 17
- Provider
- azure → azure-ai
- Class
- Reseller
Disabled by azure · stale$ / 1M tokens- Input $ / 1M tokens
- $0.58
- Output $ / 1M tokens
- $1.68
- Cache read $ / 1M tokens
- —
+109.7% vs consensus- TTFT
- 1.8s
- Throughput
- 179.1 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 18
- Provider
- eigenai
- Class
- Direct host
Disabled by eigenai · stale$ / 1M tokens- Input $ / 1M tokens
- $0.6
- Output $ / 1M tokens
- $1.85
- Cache read $ / 1M tokens
- —
+131.0% vs consensus- TTFT
- 1.4sreasoning 1.5s
- Throughput
- 136.8 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 19
- Provider
- amazon-bedrock
- Class
- Direct host
Disabled by amazon-bedrock · stale$ / 1M tokens- Input $ / 1M tokens
- $0.62
- Output $ / 1M tokens
- $1.85
- Cache read $ / 1M tokens
- —
+131.0% vs consensus- TTFT
- 1.6sreasoning 1.5s
- Throughput
- 57.7 tps
- Uptime 24h
- —
- Requests 24h
- —
- #
- 20
- Provider
- sambanova
- Class
- Direct host
Disabled by sambanova · stale$ / 1M tokens- Input $ / 1M tokens
- $3
- Output $ / 1M tokens
- $4.5
- Cache read $ / 1M tokens
- —
+461.8% vs consensus- TTFT
- —
- Throughput
- —
- Uptime 24h
- —
- Requests 24h
- —
Source ecosystem
Loading…