PrimeIntellect

Prime Intellect offers both hosted and externally routed inference. Its public policies do not establish prompt retention, training guarantees, or processing locations for externally routed inference; do not assume zero retention or exclusion from training.

Models served by PrimeIntellect

Model name

18 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 FP4 Unverified deepseek/deepseek-v4-flash-0731:primeintellect	1.0M	$0.462/M	$1.39/M	$0.0147/M	N/A	N/A	N/A
DeepSeek V4 Flash 0731 (Thinking) FP4 Unverified deepseek/deepseek-v4-flash-0731:thinking:primeintellect	1.0M	$0.462/M	$1.39/M	$0.0147/M	N/A	N/A	N/A
DeepSeek V4.1 Flash 1017 Unverified deepseek/deepseek-v4.1-flash-1017:primeintellect	1.0M	$0.0459/M	$0.735/M	$0.0025/M	30.6%	22.9s	89.6 tps
DeepSeek V4.1 Flash 1017 (Thinking) Unverified deepseek/deepseek-v4.1-flash-1017:thinking:primeintellect	1.0M	$0.0459/M	$0.735/M	$0.0025/M	30.6%	22.9s	89.6 tps
Gemma 4 26B A4B BF16 Unverified google/gemma-4-26b-a4b-it:primeintellect	262k	$0.0262/M	$0.0777/M	$0.0126/M	5.6%	11.3s	41.4 tps
Gemma 4 26B A4B (Thinking) BF16 Unverified google/gemma-4-26b-a4b-it:thinking:primeintellect	262k	$0.0262/M	$0.0777/M	$0.0126/M	5.6%	11.3s	41.4 tps
Gemma 4 31B FP4 Unverified google/gemma-4-31b-it:primeintellect	262k	$0.21/M	$0.352/M	$0.105/M	1%	N/A	N/A
Gemma 4 31B (Thinking) FP4 Unverified google/gemma-4-31b-it:thinking:primeintellect	262k	$0.21/M	$0.352/M	$0.105/M	1%	N/A	N/A
GPT OSS 120B FP4 Unverified openai/gpt-oss-120b:primeintellect	131k	$0.0483/M	$0.104/M	$0.0441/M	N/A	N/A	N/A
GPT OSS 20B FP4 Unverified openai/gpt-oss-20b:primeintellect	131k	$0.021/M	$0.0315/M	$0.0189/M	96.1%	0.8s	312.2 tps
Moondream 3 Preview FP8 Unverified moondream/moondream3-preview:primeintellect	32k	$0.315/M	$2.63/M	N/A	N/A	0.6s	361.8 tps
Moondream 3.1 9B A2B FP8 Unverified moondream/moondream3.1-9b-a2b:primeintellect	32k	$0.315/M	$2.63/M	N/A	N/A	N/A	N/A
Nvidia Nemotron 3.5 Super VL NVFP4 Unverified nvidia/nemotron-3.5-super-vl:primeintellect	1.0M	$0.157/M	$0.525/M	$0.021/M	N/A	N/A	N/A
Qwen 3.6 35B A3B FP8 Unverified Qwen/Qwen3.6-35B-A3B:primeintellect	262k	$0.0115/M	$0.106/M	$0.0105/M	N/A	N/A	N/A
Qwen 3.6 35B A3B Thinking FP8 Unverified Qwen/Qwen3.6-35B-A3B:thinking:primeintellect	262k	$0.0115/M	$0.106/M	$0.0105/M	N/A	N/A	N/A
Qwen3.5 9B BF16 Unverified qwen/qwen3.5-9b:primeintellect	262k	$0.178/M	$0.261/M	$0.161/M	71.2%	2.4s	55.8 tps
Qwen3.8 27B FP8 Unverified qwen3.8-27b:primeintellect	262k	$0.234/M	$1.67/M	$0.0262/M	N/A	N/A	N/A
Qwen3.8 27B Thinking FP8 Unverified qwen3.8-27b:thinking:primeintellect	262k	$0.234/M	$1.67/M	$0.0262/M	N/A	N/A	N/A

DeepSeek V4 Flash 0731

FP4

Unverified

deepseek/deepseek-v4-flash-0731:primeintellect

Context

1.0M

Input /M

$0.462/M

Output /M

$1.39/M

Cache read /M

$0.0147/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731 (Thinking)

FP4

Unverified

deepseek/deepseek-v4-flash-0731:thinking:primeintellect

Context

1.0M

Input /M

$0.462/M

Output /M

$1.39/M

Cache read /M

$0.0147/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash 1017

Unverified

deepseek/deepseek-v4.1-flash-1017:primeintellect

Context

1.0M

Input /M

$0.0459/M

Output /M

$0.735/M

Cache read /M

$0.0025/M

Cache hit

30.6%

TTFT

22.9s

Throughput

89.6 tps

DeepSeek V4.1 Flash 1017 (Thinking)

Unverified

deepseek/deepseek-v4.1-flash-1017:thinking:primeintellect

Context

1.0M

Input /M

$0.0459/M

Output /M

$0.735/M

Cache read /M

$0.0025/M

Cache hit

30.6%

TTFT

22.9s

Throughput

89.6 tps

Gemma 4 26B A4B

BF16

Unverified

google/gemma-4-26b-a4b-it:primeintellect

Context

262k

Input /M

$0.0262/M

Output /M

$0.0777/M

Cache read /M

$0.0126/M

Cache hit

5.6%

TTFT

11.3s

Throughput

41.4 tps

Gemma 4 26B A4B (Thinking)

BF16

Unverified

google/gemma-4-26b-a4b-it:thinking:primeintellect

Context

262k

Input /M

$0.0262/M

Output /M

$0.0777/M

Cache read /M

$0.0126/M

Cache hit

5.6%

TTFT

11.3s

Throughput

41.4 tps

Gemma 4 31B

FP4

Unverified

google/gemma-4-31b-it:primeintellect

Context

262k

Input /M

$0.21/M

Output /M

$0.352/M

Cache read /M

$0.105/M

Cache hit

1%

TTFT

N/A

Throughput

N/A

Gemma 4 31B (Thinking)

FP4

Unverified

google/gemma-4-31b-it:thinking:primeintellect

Context

262k

Input /M

$0.21/M

Output /M

$0.352/M

Cache read /M

$0.105/M

Cache hit

1%

TTFT

N/A

Throughput

N/A

GPT OSS 120B

FP4

Unverified

openai/gpt-oss-120b:primeintellect

Context

131k

Input /M

$0.0483/M

Output /M

$0.104/M

Cache read /M

$0.0441/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GPT OSS 20B

FP4

Unverified

openai/gpt-oss-20b:primeintellect

Context

131k

Input /M

$0.021/M

Output /M

$0.0315/M

Cache read /M

$0.0189/M

Cache hit

96.1%

TTFT

0.8s

Throughput

312.2 tps

Moondream 3 Preview

FP8

Unverified

moondream/moondream3-preview:primeintellect

Context

32k

Input /M

$0.315/M

Output /M

$2.63/M

Cache read /M

N/A

Cache hit

N/A

TTFT

0.6s

Throughput

361.8 tps

Moondream 3.1 9B A2B

FP8

Unverified

moondream/moondream3.1-9b-a2b:primeintellect

Context

32k

Input /M

$0.315/M

Output /M

$2.63/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3.5 Super VL

NVFP4

Unverified

nvidia/nemotron-3.5-super-vl:primeintellect

Context

1.0M

Input /M

$0.157/M

Output /M

$0.525/M

Cache read /M

$0.021/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B

FP8

Unverified

Qwen/Qwen3.6-35B-A3B:primeintellect

Context

262k

Input /M

$0.0115/M

Output /M

$0.106/M

Cache read /M

$0.0105/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B Thinking

FP8

Unverified

Qwen/Qwen3.6-35B-A3B:thinking:primeintellect

Context

262k

Input /M

$0.0115/M

Output /M

$0.106/M

Cache read /M

$0.0105/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.5 9B

BF16

Unverified

qwen/qwen3.5-9b:primeintellect

Context

262k

Input /M

$0.178/M

Output /M

$0.261/M

Cache read /M

$0.161/M

Cache hit

71.2%

TTFT

2.4s

Throughput

55.8 tps

Qwen3.8 27B

FP8

Unverified

qwen3.8-27b:primeintellect

Context

262k

Input /M

$0.234/M

Output /M

$1.67/M

Cache read /M

$0.0262/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

FP8

Unverified

qwen3.8-27b:thinking:primeintellect

Context

262k

Input /M

$0.234/M

Output /M

$1.67/M

Cache read /M

$0.0262/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

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 PrimeIntellect via the API

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

curl https://api.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:primeintellect",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :primeintellect to the model ID, set "provider": "primeintellect" in the request body, or send an X-Provider: primeintellect 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.

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