MegaNova

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 MegaNova

Model name

15 models

Model	Context	Input /M	Output /M	Cache read /M	Cache write /M	TTFT	Throughput
DeepSeek R1-0528 deepseek-ai/DeepSeek-R1-0528:meganova	164k	$0.525/M	$2.26/M	$0.42/M	N/A	N/A	N/A
DeepSeek V3.1 FP16 deepseek-ai/DeepSeek-V3.1:meganova	128k	$0.223/M	$0.709/M	N/A	N/A	N/A	N/A
GLM 4.6 z-ai/glm-4.6:meganova	203k	$0.472/M	$2.00/M	N/A	N/A	N/A	N/A
GLM 4.6 (Thinking) z-ai/glm-4.6:thinking:meganova	203k	$0.472/M	$2.00/M	N/A	N/A	N/A	N/A
GLM 4.7 FP8 z-ai/glm-4.7:meganova	200k	$0.263/M	$1.05/M	N/A	N/A	N/A	N/A
GLM 4.7 (Thinking) FP8 z-ai/glm-4.7:thinking:meganova	200k	$0.263/M	$1.05/M	N/A	N/A	N/A	N/A
GLM 5.2 FP8 z-ai/glm-5.2:meganova	1.0M	$1.05/M	$3.15/M	$0.189/M	Free	N/A	N/A
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:meganova	1.0M	$1.05/M	$3.15/M	$0.189/M	Free	N/A	N/A
Kimi K2.5 moonshotai/kimi-k2.5:meganova	262k	$0.472/M	$2.36/M	$0.0735/M	N/A	N/A	N/A
Kimi K2.5 Thinking moonshotai/kimi-k2.5:thinking:meganova	262k	$0.472/M	$2.36/M	$0.0735/M	N/A	N/A	N/A
Kimi K2.7 Code moonshotai/kimi-k2.7-code:meganova	262k	$0.787/M	$3.68/M	$0.157/M	Free	N/A	N/A
Manta Flash 1.0 meganova-ai/manta-flash-1.0	16k	$0.02/M	$0.16/M	N/A	N/A	N/A	N/A
Manta Mini 1.0 meganova-ai/manta-mini-1.0	8k	$0.02/M	$0.16/M	N/A	N/A	N/A	N/A
Manta Pro 1.0 meganova-ai/manta-pro-1.0	33k	$0.06/M	$0.50/M	N/A	N/A	N/A	N/A
Qwen3 235B A22B qwen/qwen3-235b-a22b:meganova	262k	$0.0945/M	$0.105/M	N/A	N/A	N/A	N/A

DeepSeek R1-0528

deepseek-ai/DeepSeek-R1-0528:meganova

Context

164k

Input /M

$0.525/M

Output /M

$2.26/M

Cache read /M

$0.42/M

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V3.1

FP16

deepseek-ai/DeepSeek-V3.1:meganova

Context

128k

Input /M

$0.223/M

Output /M

$0.709/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

GLM 4.6

z-ai/glm-4.6:meganova

Context

203k

Input /M

$0.472/M

Output /M

$2.00/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

GLM 4.6 (Thinking)

z-ai/glm-4.6:thinking:meganova

Context

203k

Input /M

$0.472/M

Output /M

$2.00/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

GLM 4.7

FP8

z-ai/glm-4.7:meganova

Context

200k

Input /M

$0.263/M

Output /M

$1.05/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

GLM 4.7 (Thinking)

FP8

z-ai/glm-4.7:thinking:meganova

Context

200k

Input /M

$0.263/M

Output /M

$1.05/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

GLM 5.2

FP8

z-ai/glm-5.2:meganova

Context

1.0M

Input /M

$1.05/M

Output /M

$3.15/M

Cache read /M

$0.189/M

Cache write /M

Free

TTFT

N/A

Throughput

N/A

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:meganova

Context

1.0M

Input /M

$1.05/M

Output /M

$3.15/M

Cache read /M

$0.189/M

Cache write /M

Free

TTFT

N/A

Throughput

N/A

Kimi K2.5

moonshotai/kimi-k2.5:meganova

Context

262k

Input /M

$0.472/M

Output /M

$2.36/M

Cache read /M

$0.0735/M

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

Kimi K2.5 Thinking

moonshotai/kimi-k2.5:thinking:meganova

Context

262k

Input /M

$0.472/M

Output /M

$2.36/M

Cache read /M

$0.0735/M

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

Kimi K2.7 Code

moonshotai/kimi-k2.7-code:meganova

Context

262k

Input /M

$0.787/M

Output /M

$3.68/M

Cache read /M

$0.157/M

Cache write /M

Free

TTFT

N/A

Throughput

N/A

Manta Flash 1.0

meganova-ai/manta-flash-1.0

Context

16k

Input /M

$0.02/M

Output /M

$0.16/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

Manta Mini 1.0

meganova-ai/manta-mini-1.0

Context

8k

Input /M

$0.02/M

Output /M

$0.16/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

Manta Pro 1.0

meganova-ai/manta-pro-1.0

Context

33k

Input /M

$0.06/M

Output /M

$0.50/M

Cache read /M

N/A

Cache write /M

N/A

TTFT

N/A

Throughput

N/A

Qwen3 235B A22B

qwen/qwen3-235b-a22b:meganova

Context

262k

Input /M

$0.0945/M

Output /M

$0.105/M

Cache read /M

N/A

Cache write /M

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 MegaNova via the API

Call a model served by MegaNova 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-ai/DeepSeek-R1-0528:meganova",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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