Sail Research

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

Model name

26 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 Standard FP4 deepseek/deepseek-v4-flash-0731:sailresearch-standard	1.0M	$0.10/M	$0.31/M	$0.03/M	9.3%	1.6s	36 tps
DeepSeek V4 Flash 0731 (Thinking) Standard FP4 deepseek/deepseek-v4-flash-0731:thinking:sailresearch-standard	1.0M	$0.10/M	$0.31/M	$0.03/M	9.3%	1.6s	36 tps
DeepSeek V4 Pro 0813 Standard FP4 deepseek/deepseek-v4-pro-0813:sailresearch-standard	1.0M	$0.42/M	$4.51/M	$0.03/M	0%	1.2s	82 tps
DeepSeek V4 Pro 0813 (Thinking) Standard FP4 deepseek/deepseek-v4-pro-0813:thinking:sailresearch-standard	1.0M	$0.42/M	$4.51/M	$0.03/M	0%	1.2s	82 tps
DeepSeek V4.1 Flash Standard FP4 deepseek/deepseek-v4.1-flash:sailresearch-standard	1.0M	$0.08/M	$0.42/M	$0.01/M	30.6%	0.8s	60 tps
DeepSeek V4.1 Flash (Thinking) Standard FP4 deepseek/deepseek-v4.1-flash:thinking:sailresearch-standard	1.0M	$0.08/M	$0.42/M	$0.01/M	45%	0.8s	60 tps
Gemma 4 31B ASAP FP4 google/gemma-4-31b-it:sailresearch-asap	262k	$0.15/M	$0.42/M	$0.07/M	N/A	N/A	N/A
Gemma 4 31B Standard FP4 google/gemma-4-31b-it:sailresearch-standard	262k	$0.07/M	$0.42/M	$0.05/M	26.7%	3.9s	33.7 tps
Gemma 4 31B (Thinking) ASAP FP4 google/gemma-4-31b-it:thinking:sailresearch-asap	262k	$0.15/M	$0.42/M	$0.07/M	N/A	N/A	N/A
Gemma 4 31B (Thinking) Standard FP4 google/gemma-4-31b-it:thinking:sailresearch-standard	262k	$0.07/M	$0.42/M	$0.05/M	29.2%	18s	36.4 tps
GLM 5.2 ASAP FP8 z-ai/glm-5.2:sailresearch-asap	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	N/A	N/A
GLM 5.2 Priority FP8 z-ai/glm-5.2:sailresearch-priority	1.0M	$0.73/M	$3.15/M	$0.19/M	N/A	N/A	N/A
GLM 5.2 Standard FP8 z-ai/glm-5.2:sailresearch-standard	1.0M	$0.53/M	$2.63/M	$0.13/M	N/A	1.9s	16 tps
GLM 5.2 (Thinking) ASAP FP8 z-ai/glm-5.2:thinking:sailresearch-asap	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	N/A	N/A
GLM 5.2 (Thinking) Priority FP8 z-ai/glm-5.2:thinking:sailresearch-priority	1.0M	$0.73/M	$3.15/M	$0.19/M	N/A	N/A	N/A
GLM 5.2 (Thinking) Standard FP8 z-ai/glm-5.2:thinking:sailresearch-standard	1.0M	$0.53/M	$2.63/M	$0.13/M	N/A	1.9s	16 tps
GLM 5.3 Standard FP8 z-ai/glm-5.3:sailresearch-standard	1.0M	$0.21/M	$3.57/M	$0.16/M	0%	0.7s	111 tps
GLM 5.3 (Thinking) Standard FP8 z-ai/glm-5.3:thinking:sailresearch-standard	1.0M	$0.21/M	$3.57/M	$0.16/M	48%	0.7s	111 tps
GLM 5.3 Flash Standard FP4 z-ai/glm-5.3-flash:sailresearch-standard	1.0M	$0.05/M	$0.63/M	$0.03/M	56.4%	3.9s	11 tps
GPT OSS 120B ASAP openai/gpt-oss-120b:sailresearch-asap	128k	$0.06/M	$0.42/M	$0.03/M	N/A	N/A	N/A
GPT OSS 120B Priority openai/gpt-oss-120b:sailresearch-priority	128k	$0.04/M	$0.31/M	$0.02/M	N/A	N/A	N/A
Kimi K2.6 ASAP FP8 moonshotai/kimi-k2.6:sailresearch-asap	256k	$1.05/M	$4.20/M	$0.21/M	N/A	N/A	N/A
Kimi K2.6 Priority FP8 moonshotai/kimi-k2.6:sailresearch-priority	256k	$0.47/M	$3.15/M	$0.21/M	N/A	N/A	N/A
Kimi K2.6 Thinking ASAP FP8 moonshotai/kimi-k2.6:thinking:sailresearch-asap	256k	$1.05/M	$4.20/M	$0.21/M	N/A	N/A	N/A
Kimi K2.6 Thinking Priority FP8 moonshotai/kimi-k2.6:thinking:sailresearch-priority	256k	$0.47/M	$3.15/M	$0.21/M	N/A	N/A	N/A
Kimi K3 Standard FP4 moonshotai/kimi-k3:sailresearch-standard	1.0M	$0.88/M	$14.18/M	$0.31/M	N/A	1.5s	55 tps

DeepSeek V4 Flash 0731

Standard

FP4

deepseek/deepseek-v4-flash-0731:sailresearch-standard

Context

1.0M

Input /M

$0.10/M

Output /M

$0.31/M

Cache read /M

$0.03/M

Cache hit

9.3%

TTFT

1.6s

Throughput

36 tps

DeepSeek V4 Flash 0731 (Thinking)

Standard

FP4

deepseek/deepseek-v4-flash-0731:thinking:sailresearch-standard

Context

1.0M

Input /M

$0.10/M

Output /M

$0.31/M

Cache read /M

$0.03/M

Cache hit

9.3%

TTFT

1.6s

Throughput

36 tps

DeepSeek V4 Pro 0813

Standard

FP4

deepseek/deepseek-v4-pro-0813:sailresearch-standard

Context

1.0M

Input /M

$0.42/M

Output /M

$4.51/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

1.2s

Throughput

82 tps

DeepSeek V4 Pro 0813 (Thinking)

Standard

FP4

deepseek/deepseek-v4-pro-0813:thinking:sailresearch-standard

Context

1.0M

Input /M

$0.42/M

Output /M

$4.51/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

1.2s

Throughput

82 tps

DeepSeek V4.1 Flash

Standard

FP4

deepseek/deepseek-v4.1-flash:sailresearch-standard

Context

1.0M

Input /M

$0.08/M

Output /M

$0.42/M

Cache read /M

$0.01/M

Cache hit

30.6%

TTFT

0.8s

Throughput

60 tps

DeepSeek V4.1 Flash (Thinking)

Standard

FP4

deepseek/deepseek-v4.1-flash:thinking:sailresearch-standard

Context

1.0M

Input /M

$0.08/M

Output /M

$0.42/M

Cache read /M

$0.01/M

Cache hit

45%

TTFT

0.8s

Throughput

60 tps

Gemma 4 31B

ASAP

FP4

google/gemma-4-31b-it:sailresearch-asap

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

google/gemma-4-31b-it:sailresearch-standard

Context

262k

Input /M

$0.07/M

Output /M

$0.42/M

Cache read /M

$0.05/M

Cache hit

26.7%

TTFT

3.9s

Throughput

33.7 tps

Gemma 4 31B (Thinking)

ASAP

FP4

google/gemma-4-31b-it:thinking:sailresearch-asap

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

google/gemma-4-31b-it:thinking:sailresearch-standard

Context

262k

Input /M

$0.07/M

Output /M

$0.42/M

Cache read /M

$0.05/M

Cache hit

29.2%

TTFT

18s

Throughput

36.4 tps

GLM 5.2

ASAP

FP8

z-ai/glm-5.2:sailresearch-asap

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

z-ai/glm-5.2:sailresearch-priority

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

z-ai/glm-5.2:sailresearch-standard

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

z-ai/glm-5.2:thinking:sailresearch-asap

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

z-ai/glm-5.2:thinking:sailresearch-priority

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

z-ai/glm-5.2:thinking:sailresearch-standard

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

z-ai/glm-5.3:sailresearch-standard

Context

1.0M

Input /M

$0.21/M

Output /M

$3.57/M

Cache read /M

$0.16/M

Cache hit

0%

TTFT

0.7s

Throughput

111 tps

GLM 5.3 (Thinking)

Standard

FP8

z-ai/glm-5.3:thinking:sailresearch-standard

Context

1.0M

Input /M

$0.21/M

Output /M

$3.57/M

Cache read /M

$0.16/M

Cache hit

48%

TTFT

0.7s

Throughput

111 tps

GLM 5.3 Flash

Standard

FP4

z-ai/glm-5.3-flash:sailresearch-standard

Context

1.0M

Input /M

$0.05/M

Output /M

$0.63/M

Cache read /M

$0.03/M

Cache hit

56.4%

TTFT

3.9s

Throughput

11 tps

GPT OSS 120B

ASAP

openai/gpt-oss-120b:sailresearch-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

openai/gpt-oss-120b:sailresearch-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

Kimi K2.6

ASAP

FP8

moonshotai/kimi-k2.6:sailresearch-asap

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

moonshotai/kimi-k2.6:sailresearch-priority

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

moonshotai/kimi-k2.6:thinking:sailresearch-asap

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

moonshotai/kimi-k2.6:thinking:sailresearch-priority

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

moonshotai/kimi-k3:sailresearch-standard

Context

1.0M

Input /M

$0.88/M

Output /M

$14.18/M

Cache read /M

$0.31/M

Cache hit

N/A

TTFT

1.5s

Throughput

55 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 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.