Sail Research

GLB

19 models available

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by Sail Research

29 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 Standard FP4	1.0M	$0.16/M	$0.31/M	$0.04/M	N/A	1s	36 tps
DeepSeek V4 Flash 0731 (Thinking) Standard FP4	1.0M	$0.16/M	$0.31/M	$0.04/M	N/A	1s	36 tps
DeepSeek V4 Pro 0813 Standard FP4	1.0M	$0.47/M	$0.84/M	$0.07/M	6.1%	0.9s	41 tps
DeepSeek V4 Pro 0813 (Thinking) Standard FP4	1.0M	$0.47/M	$0.84/M	$0.07/M	86.8%	0.9s	41 tps
DeepSeek V4.1 Flash Standard FP4	1.0M	$0.09/M	$0.26/M	$0.0063/M	55.6%	0.5s	50 tps
DeepSeek V4.1 Flash (Thinking) Standard FP4	1.0M	$0.09/M	$0.26/M	$0.0063/M	46.3%	0.5s	50 tps
DeepSeek V4.1 Flash 1017 Standard FP4	1.0M	$0.11/M	$0.16/M	$0.0071/M	98.3%	0.8s	49 tps
DeepSeek V4.1 Flash 1017 (Thinking) Standard FP4	1.0M	$0.11/M	$0.16/M	$0.0071/M	98.3%	0.8s	49 tps
Gemma 4 31B ASAP FP4	262k	$0.15/M	$0.42/M	$0.07/M	N/A	N/A	N/A
Gemma 4 31B Standard FP4	262k	$0.07/M	$0.42/M	$0.05/M	85.5%	6.5s	31.5 tps
Gemma 4 31B (Thinking) ASAP FP4	262k	$0.15/M	$0.42/M	$0.07/M	N/A	N/A	N/A
Gemma 4 31B (Thinking) Standard FP4	262k	$0.07/M	$0.42/M	$0.05/M	85.5%	6.5s	31.5 tps
GLM 5.2 ASAP FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	N/A	N/A
GLM 5.2 Priority FP8	1.0M	$0.73/M	$3.15/M	$0.19/M	N/A	N/A	N/A
GLM 5.2 Standard FP8	1.0M	$0.53/M	$2.63/M	$0.13/M	N/A	1.9s	16 tps
GLM 5.2 (Thinking) ASAP FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	N/A	N/A
GLM 5.2 (Thinking) Priority FP8	1.0M	$0.73/M	$3.15/M	$0.19/M	N/A	N/A	N/A
GLM 5.2 (Thinking) Standard FP8	1.0M	$0.53/M	$2.63/M	$0.13/M	N/A	1.9s	16 tps
GLM 5.3 Standard FP8	1.0M	$0.53/M	$2.10/M	$0.08/M	43.4%	1s	60 tps
GLM 5.3 (Thinking) Standard FP8	1.0M	$0.53/M	$2.10/M	$0.08/M	48.9%	1s	60 tps
GLM 5.3 Flash Standard FP4	1.0M	$0.08/M	$0.26/M	$0.03/M	N/A	1.4s	20 tps
GPT OSS 120B ASAP	128k	$0.06/M	$0.42/M	$0.03/M	N/A	N/A	N/A
GPT OSS 120B Priority	128k	$0.04/M	$0.31/M	$0.02/M	N/A	N/A	N/A
GPT OSS 120B Standard FP4	131k	$0.06/M	$0.42/M	$0.03/M	N/A	0.7s	113 tps
Kimi K2.6 ASAP FP8	256k	$1.05/M	$4.20/M	$0.21/M	N/A	N/A	N/A
Kimi K2.6 Priority FP8	256k	$0.47/M	$3.15/M	$0.21/M	N/A	N/A	N/A
Kimi K2.6 Thinking ASAP FP8	256k	$1.05/M	$4.20/M	$0.21/M	N/A	N/A	N/A
Kimi K2.6 Thinking Priority FP8	256k	$0.47/M	$3.15/M	$0.21/M	N/A	N/A	N/A
Kimi K3 Standard FP4	1.0M	$0.24/M	$11.55/M	$0.12/M	17.7%	1s	65 tps

DeepSeek V4 Flash 0731

Standard

FP4

Context: 1.0M
Input /M: $0.16/M
Output /M: $0.31/M
Cache read /M: $0.04/M
Cache hit: N/A
TTFT: 1s
Throughput: 36 tps

DeepSeek V4 Flash 0731 (Thinking)

Standard

FP4

Context: 1.0M
Input /M: $0.16/M
Output /M: $0.31/M
Cache read /M: $0.04/M
Cache hit: N/A
TTFT: 1s
Throughput: 36 tps

DeepSeek V4 Pro 0813

Standard

FP4

Context: 1.0M
Input /M: $0.47/M
Output /M: $0.84/M
Cache read /M: $0.07/M
Cache hit: 6.1%
TTFT: 0.9s
Throughput: 41 tps

DeepSeek V4 Pro 0813 (Thinking)

Standard

FP4

Context: 1.0M
Input /M: $0.47/M
Output /M: $0.84/M
Cache read /M: $0.07/M
Cache hit: 86.8%
TTFT: 0.9s
Throughput: 41 tps

DeepSeek V4.1 Flash

Standard

FP4

Context: 1.0M
Input /M: $0.09/M
Output /M: $0.26/M
Cache read /M: $0.0063/M
Cache hit: 55.6%
TTFT: 0.5s
Throughput: 50 tps

DeepSeek V4.1 Flash (Thinking)

Standard

FP4

Context: 1.0M
Input /M: $0.09/M
Output /M: $0.26/M
Cache read /M: $0.0063/M
Cache hit: 46.3%
TTFT: 0.5s
Throughput: 50 tps

DeepSeek V4.1 Flash 1017

Standard

FP4

Context: 1.0M
Input /M: $0.11/M
Output /M: $0.16/M
Cache read /M: $0.0071/M
Cache hit: 98.3%
TTFT: 0.8s
Throughput: 49 tps

DeepSeek V4.1 Flash 1017 (Thinking)

Standard

FP4

Context: 1.0M
Input /M: $0.11/M
Output /M: $0.16/M
Cache read /M: $0.0071/M
Cache hit: 98.3%
TTFT: 0.8s
Throughput: 49 tps

Gemma 4 31B

ASAP

FP4

Context: 262k
Input /M: $0.15/M
Output /M: $0.42/M
Cache read /M: $0.07/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Gemma 4 31B

Standard

FP4

Context: 262k
Input /M: $0.07/M
Output /M: $0.42/M
Cache read /M: $0.05/M
Cache hit: 85.5%
TTFT: 6.5s
Throughput: 31.5 tps

Gemma 4 31B (Thinking)

ASAP

FP4

Context: 262k
Input /M: $0.15/M
Output /M: $0.42/M
Cache read /M: $0.07/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Gemma 4 31B (Thinking)

Standard

FP4

Context: 262k
Input /M: $0.07/M
Output /M: $0.42/M
Cache read /M: $0.05/M
Cache hit: 85.5%
TTFT: 6.5s
Throughput: 31.5 tps

GLM 5.2

ASAP

FP8

Context: 1.0M
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.27/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.2

Priority

FP8

Context: 1.0M
Input /M: $0.73/M
Output /M: $3.15/M
Cache read /M: $0.19/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.2

Standard

FP8

Context: 1.0M
Input /M: $0.53/M
Output /M: $2.63/M
Cache read /M: $0.13/M
Cache hit: N/A
TTFT: 1.9s
Throughput: 16 tps

GLM 5.2 (Thinking)

ASAP

FP8

Context: 1.0M
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.27/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.2 (Thinking)

Priority

FP8

Context: 1.0M
Input /M: $0.73/M
Output /M: $3.15/M
Cache read /M: $0.19/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GLM 5.2 (Thinking)

Standard

FP8

Context: 1.0M
Input /M: $0.53/M
Output /M: $2.63/M
Cache read /M: $0.13/M
Cache hit: N/A
TTFT: 1.9s
Throughput: 16 tps

GLM 5.3

Standard

FP8

Context: 1.0M
Input /M: $0.53/M
Output /M: $2.10/M
Cache read /M: $0.08/M
Cache hit: 43.4%
TTFT: 1s
Throughput: 60 tps

GLM 5.3 (Thinking)

Standard

FP8

Context: 1.0M
Input /M: $0.53/M
Output /M: $2.10/M
Cache read /M: $0.08/M
Cache hit: 48.9%
TTFT: 1s
Throughput: 60 tps

GLM 5.3 Flash

Standard

FP4

Context: 1.0M
Input /M: $0.08/M
Output /M: $0.26/M
Cache read /M: $0.03/M
Cache hit: N/A
TTFT: 1.4s
Throughput: 20 tps

GPT OSS 120B

ASAP

Context: 128k
Input /M: $0.06/M
Output /M: $0.42/M
Cache read /M: $0.03/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GPT OSS 120B

Priority

Context: 128k
Input /M: $0.04/M
Output /M: $0.31/M
Cache read /M: $0.02/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

GPT OSS 120B

Standard

FP4

Context: 131k
Input /M: $0.06/M
Output /M: $0.42/M
Cache read /M: $0.03/M
Cache hit: N/A
TTFT: 0.7s
Throughput: 113 tps

Kimi K2.6

ASAP

FP8

Context: 256k
Input /M: $1.05/M
Output /M: $4.20/M
Cache read /M: $0.21/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Kimi K2.6

Priority

FP8

Context: 256k
Input /M: $0.47/M
Output /M: $3.15/M
Cache read /M: $0.21/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Kimi K2.6 Thinking

ASAP

FP8

Context: 256k
Input /M: $1.05/M
Output /M: $4.20/M
Cache read /M: $0.21/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Kimi K2.6 Thinking

Priority

FP8

Context: 256k
Input /M: $0.47/M
Output /M: $3.15/M
Cache read /M: $0.21/M
Cache hit: N/A
TTFT: N/A
Throughput: N/A

Kimi K3

Standard

FP4

Context: 1.0M
Input /M: $0.24/M
Output /M: $11.55/M
Cache read /M: $0.12/M
Cache hit: 17.7%
TTFT: 1s
Throughput: 65 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Sail Research via the API

Call a model served by Sail Research using its displayed model ID, including the provider suffix when selection is supported.

cURL

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash-0731:sailresearch-standard",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :sailresearch-standard to the model ID, set "provider": "sailresearch-standard" in the request body, or send an X-Provider: sailresearch-standard header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

Sail Research offers multiple service lanes, each pinned with its own id: sailresearch-standard (Standard), sailresearch-asap (ASAP), sailresearch-priority (Priority). The table shows which lane serves each row.

See the API documentation for provider preferences, price-aware routing, and error behavior.

Sail Research terms of use Sail Research privacy policy

Model

Context

Input /M

Output /M

Cache read /M

Cache hit

TTFT

Throughput

DeepSeek V4 Flash 0731

Standard

FP4

1.0M

$0.16/M

$0.31/M

$0.04/M

N/A

36 tps

DeepSeek V4 Flash 0731 (Thinking)

Standard

FP4

1.0M

$0.16/M

$0.31/M

$0.04/M

N/A

36 tps

DeepSeek V4 Pro 0813

Standard

FP4

1.0M

$0.47/M

$0.84/M

$0.07/M

6.1%

0.9s

41 tps

DeepSeek V4 Pro 0813 (Thinking)

Standard

FP4

1.0M

$0.47/M

$0.84/M

$0.07/M

86.8%

0.9s

41 tps

DeepSeek V4.1 Flash

Standard

FP4

1.0M

$0.09/M

$0.26/M

$0.0063/M

55.6%

0.5s

50 tps

DeepSeek V4.1 Flash (Thinking)

Standard

FP4

1.0M

$0.09/M

$0.26/M

$0.0063/M

46.3%

0.5s

50 tps

DeepSeek V4.1 Flash 1017

Standard

FP4

1.0M

$0.11/M

$0.16/M

$0.0071/M

98.3%

0.8s

49 tps

DeepSeek V4.1 Flash 1017 (Thinking)

Standard

FP4

1.0M

$0.11/M

$0.16/M

$0.0071/M

98.3%

0.8s

49 tps

Gemma 4 31B

ASAP

FP4

262k

$0.15/M

$0.42/M

$0.07/M

N/A

Gemma 4 31B

Standard

FP4

262k

$0.07/M

$0.42/M

$0.05/M

85.5%

6.5s

31.5 tps

Gemma 4 31B (Thinking)

ASAP

FP4

262k

$0.15/M

$0.42/M

$0.07/M

N/A

Gemma 4 31B (Thinking)

Standard

FP4

262k

$0.07/M

$0.42/M

$0.05/M

85.5%

6.5s

31.5 tps

GLM 5.2

ASAP

FP8

1.0M

$1.47/M

$4.62/M

$0.27/M

N/A

GLM 5.2

Priority

FP8

1.0M

$0.73/M

$3.15/M

$0.19/M

N/A

GLM 5.2

Standard

FP8

1.0M

$0.53/M

$2.63/M

$0.13/M

N/A

1.9s

16 tps

GLM 5.2 (Thinking)

ASAP

FP8

1.0M

$1.47/M

$4.62/M

$0.27/M

N/A

GLM 5.2 (Thinking)

Priority

FP8

1.0M

$0.73/M

$3.15/M

$0.19/M

N/A

GLM 5.2 (Thinking)

Standard

FP8

1.0M

$0.53/M

$2.63/M

$0.13/M

N/A

1.9s

16 tps

GLM 5.3

Standard

FP8

1.0M

$0.53/M

$2.10/M

$0.08/M

43.4%

60 tps

GLM 5.3 (Thinking)

Standard

FP8

1.0M

$0.53/M

$2.10/M

$0.08/M

48.9%

60 tps

GLM 5.3 Flash

Standard

FP4

1.0M

$0.08/M

$0.26/M

$0.03/M

N/A

1.4s

20 tps

GPT OSS 120B

ASAP

128k

$0.06/M

$0.42/M

$0.03/M

N/A

GPT OSS 120B

Priority

128k

$0.04/M

$0.31/M

$0.02/M

N/A

GPT OSS 120B

Standard

FP4

131k

$0.06/M

$0.42/M

$0.03/M

N/A

0.7s

113 tps

Kimi K2.6

ASAP

FP8

256k

$1.05/M

$4.20/M

$0.21/M

N/A

Kimi K2.6

Priority

FP8

256k

$0.47/M

$3.15/M

$0.21/M

N/A

Kimi K2.6 Thinking

ASAP

FP8

256k

$1.05/M

$4.20/M

$0.21/M

N/A

Kimi K2.6 Thinking

Priority

FP8

256k

$0.47/M

$3.15/M

$0.21/M

N/A

Kimi K3

Standard

FP4

1.0M

$0.24/M

$11.55/M

$0.12/M

17.7%

65 tps

Using Sail Research via the API

Call a model served by Sail Research using its displayed model ID, including the provider suffix when selection is supported.

cURL

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash-0731:sailresearch-standard",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.