CoreWeave

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 CoreWeave

Model name

30 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V3.1 FP8 deepseek-ai/DeepSeek-V3.1:coreweave	161k	$0.58/M	$1.73/M	$0.58/M	0.2s	84 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:coreweave	262k	$0.14/M	$0.29/M	$0.07/M	0.4s	111 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:coreweave	262k	$0.14/M	$0.29/M	$0.07/M	0.4s	111 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:coreweave	1.0M	$1.38/M	$4.16/M	$0.05/M	0.5s	96 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:coreweave	1.0M	$1.38/M	$4.16/M	$0.05/M	0.5s	96 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:coreweave	1.0M	$0.16/M	$0.68/M	$0.0021/M	0.5s	198 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:coreweave	1.0M	$0.16/M	$0.68/M	$0.0021/M	0.5s	198 tps
Gemma 4 26B A4B BF16 google/gemma-4-26b-a4b-it:coreweave	262k	$0.10/M	$0.31/M	$0.05/M	0.3s	75 tps
Gemma 4 26B A4B (Thinking) BF16 google/gemma-4-26b-a4b-it:thinking:coreweave	262k	$0.10/M	$0.31/M	$0.05/M	0.3s	75 tps
Gemma 4 31B FP4 google/gemma-4-31b-it:coreweave	262k	$0.10/M	$0.36/M	$0.10/M	0.7s	52 tps
Gemma 4 31B (Thinking) FP4 google/gemma-4-31b-it:thinking:coreweave	262k	$0.10/M	$0.36/M	$0.10/M	0.7s	52 tps
GLM 5.2 FP4 z-ai/glm-5.2:coreweave	1.0M	$0.65/M	$2.54/M	$0.15/M	0.3s	203 tps
GLM 5.2 (Thinking) FP4 z-ai/glm-5.2:thinking:coreweave	1.0M	$0.65/M	$2.54/M	$0.15/M	0.3s	203 tps
GLM 5.3 FP8 z-ai/glm-5.3:coreweave	1.0M	$1.26/M	$4.20/M	$0.20/M	0.6s	85.5 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:coreweave	1.0M	$1.26/M	$4.20/M	$0.20/M	0.6s	85.5 tps
GLM 5.3 Flash NVFP4 z-ai/glm-5.3-flash:coreweave	1.0M	$0.16/M	$0.53/M	$0.02/M	0.6s	116 tps
GPT OSS 120B FP4 openai/gpt-oss-120b:coreweave	131k	$0.03/M	$0.18/M	$0.03/M	0.3s	91 tps
GPT OSS 20B FP4 openai/gpt-oss-20b:coreweave	131k	$0.03/M	$0.14/M	$0.03/M	0.1s	109 tps
Granite 4.2 8B BF16 ibm-granite/granite-4.2-8b:coreweave	131k	$0.10/M	$0.16/M	$0.05/M	0.2s	125 tps
Kimi K2.6 FP4 moonshotai/kimi-k2.6:coreweave	262k	$0.68/M	$3.58/M	$0.16/M	0.6s	65 tps
Kimi K2.6 Thinking FP4 moonshotai/kimi-k2.6:thinking:coreweave	262k	$0.68/M	$3.58/M	$0.16/M	0.6s	65 tps
Kimi K2.7 Code INT4 moonshotai/kimi-k2.7-code:coreweave	262k	$0.75/M	$3.68/M	$0.16/M	0.4s	67 tps
Llama 3.1 8B BF16 meta-llama/llama-3.1-8b-instruct:coreweave	131k	$0.23/M	$0.23/M	$0.23/M	0.3s	138 tps
Llama 3.3 70B Instruct FP16 meta-llama/llama-3.3-70b-instruct:coreweave	128k	$0.75/M	$0.75/M	$0.75/M	0.1s	88 tps
MiniMax M3 FP4 minimax/minimax-m3:coreweave	262k	$0.24/M	$1.01/M	$0.05/M	0.5s	109 tps
MiniMax M3 Thinking FP4 minimax/minimax-m3:thinking:coreweave	262k	$0.24/M	$1.01/M	$0.05/M	0.5s	109 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:coreweave	262k	$0.26/M	$1.31/M	$0.26/M	0.3s	85 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:coreweave	262k	$0.26/M	$1.31/M	$0.26/M	0.3s	85 tps
Qwen3.8 27B FP8 qwen3.8-27b:coreweave	262k	$0.42/M	$3.15/M	$0.16/M	0.6s	35 tps
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:coreweave	262k	$0.42/M	$3.15/M	$0.16/M	0.6s	35 tps

DeepSeek V3.1

FP8

deepseek-ai/DeepSeek-V3.1:coreweave

Context

161k

Input /M

$0.58/M

Output /M

$1.73/M

Cache read /M

$0.58/M

TTFT

0.2s

Throughput

84 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:coreweave

Context

262k

Input /M

$0.14/M

Output /M

$0.29/M

Cache read /M

$0.07/M

TTFT

0.4s

Throughput

111 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

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

Context

262k

Input /M

$0.14/M

Output /M

$0.29/M

Cache read /M

$0.07/M

TTFT

0.4s

Throughput

111 tps

DeepSeek V4 Pro 0813

FP8

deepseek/deepseek-v4-pro-0813:coreweave

Context

1.0M

Input /M

$1.38/M

Output /M

$4.16/M

Cache read /M

$0.05/M

TTFT

0.5s

Throughput

96 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

deepseek/deepseek-v4-pro-0813:thinking:coreweave

Context

1.0M

Input /M

$1.38/M

Output /M

$4.16/M

Cache read /M

$0.05/M

TTFT

0.5s

Throughput

96 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:coreweave

Context

1.0M

Input /M

$0.16/M

Output /M

$0.68/M

Cache read /M

$0.0021/M

TTFT

0.5s

Throughput

198 tps

DeepSeek V4.1 Flash (Thinking)

FP8

deepseek/deepseek-v4.1-flash:thinking:coreweave

Context

1.0M

Input /M

$0.16/M

Output /M

$0.68/M

Cache read /M

$0.0021/M

TTFT

0.5s

Throughput

198 tps

Gemma 4 26B A4B

BF16

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

Context

262k

Input /M

$0.10/M

Output /M

$0.31/M

Cache read /M

$0.05/M

TTFT

0.3s

Throughput

75 tps

Gemma 4 26B A4B (Thinking)

BF16

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

Context

262k

Input /M

$0.10/M

Output /M

$0.31/M

Cache read /M

$0.05/M

TTFT

0.3s

Throughput

75 tps

Gemma 4 31B

FP4

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

Context

262k

Input /M

$0.10/M

Output /M

$0.36/M

Cache read /M

$0.10/M

TTFT

0.7s

Throughput

52 tps

Gemma 4 31B (Thinking)

FP4

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

Context

262k

Input /M

$0.10/M

Output /M

$0.36/M

Cache read /M

$0.10/M

TTFT

0.7s

Throughput

52 tps

GLM 5.2

FP4

z-ai/glm-5.2:coreweave

Context

1.0M

Input /M

$0.65/M

Output /M

$2.54/M

Cache read /M

$0.15/M

TTFT

0.3s

Throughput

203 tps

GLM 5.2 (Thinking)

FP4

z-ai/glm-5.2:thinking:coreweave

Context

1.0M

Input /M

$0.65/M

Output /M

$2.54/M

Cache read /M

$0.15/M

TTFT

0.3s

Throughput

203 tps

GLM 5.3

FP8

z-ai/glm-5.3:coreweave

Context

1.0M

Input /M

$1.26/M

Output /M

$4.20/M

Cache read /M

$0.20/M

TTFT

0.6s

Throughput

85.5 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:coreweave

Context

1.0M

Input /M

$1.26/M

Output /M

$4.20/M

Cache read /M

$0.20/M

TTFT

0.6s

Throughput

85.5 tps

GLM 5.3 Flash

NVFP4

z-ai/glm-5.3-flash:coreweave

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.02/M

TTFT

0.6s

Throughput

116 tps

GPT OSS 120B

FP4

openai/gpt-oss-120b:coreweave

Context

131k

Input /M

$0.03/M

Output /M

$0.18/M

Cache read /M

$0.03/M

TTFT

0.3s

Throughput

91 tps

GPT OSS 20B

FP4

openai/gpt-oss-20b:coreweave

Context

131k

Input /M

$0.03/M

Output /M

$0.14/M

Cache read /M

$0.03/M

TTFT

0.1s

Throughput

109 tps

Granite 4.2 8B

BF16

ibm-granite/granite-4.2-8b:coreweave

Context

131k

Input /M

$0.10/M

Output /M

$0.16/M

Cache read /M

$0.05/M

TTFT

0.2s

Throughput

125 tps

Kimi K2.6

FP4

moonshotai/kimi-k2.6:coreweave

Context

262k

Input /M

$0.68/M

Output /M

$3.58/M

Cache read /M

$0.16/M

TTFT

0.6s

Throughput

65 tps

Kimi K2.6 Thinking

FP4

moonshotai/kimi-k2.6:thinking:coreweave

Context

262k

Input /M

$0.68/M

Output /M

$3.58/M

Cache read /M

$0.16/M

TTFT

0.6s

Throughput

65 tps

Kimi K2.7 Code

INT4

moonshotai/kimi-k2.7-code:coreweave

Context

262k

Input /M

$0.75/M

Output /M

$3.68/M

Cache read /M

$0.16/M

TTFT

0.4s

Throughput

67 tps

Llama 3.1 8B

BF16

meta-llama/llama-3.1-8b-instruct:coreweave

Context

131k

Input /M

$0.23/M

Output /M

$0.23/M

Cache read /M

$0.23/M

TTFT

0.3s

Throughput

138 tps

Llama 3.3 70B Instruct

FP16

meta-llama/llama-3.3-70b-instruct:coreweave

Context

128k

Input /M

$0.75/M

Output /M

$0.75/M

Cache read /M

$0.75/M

TTFT

0.1s

Throughput

88 tps

MiniMax M3

FP4

minimax/minimax-m3:coreweave

Context

262k

Input /M

$0.24/M

Output /M

$1.01/M

Cache read /M

$0.05/M

TTFT

0.5s

Throughput

109 tps

MiniMax M3 Thinking

FP4

minimax/minimax-m3:thinking:coreweave

Context

262k

Input /M

$0.24/M

Output /M

$1.01/M

Cache read /M

$0.05/M

TTFT

0.5s

Throughput

109 tps

Qwen 3.6 35B A3B

FP8

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

Context

262k

Input /M

$0.26/M

Output /M

$1.31/M

Cache read /M

$0.26/M

TTFT

0.3s

Throughput

85 tps

Qwen 3.6 35B A3B Thinking

FP8

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

Context

262k

Input /M

$0.26/M

Output /M

$1.31/M

Cache read /M

$0.26/M

TTFT

0.3s

Throughput

85 tps

Qwen3.8 27B

FP8

qwen3.8-27b:coreweave

Context

262k

Input /M

$0.42/M

Output /M

$3.15/M

Cache read /M

$0.16/M

TTFT

0.6s

Throughput

35 tps

Qwen3.8 27B Thinking

FP8

qwen3.8-27b:thinking:coreweave

Context

262k

Input /M

$0.42/M

Output /M

$3.15/M

Cache read /M

$0.16/M

TTFT

0.6s

Throughput

35 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 CoreWeave via the API

Call a model served by CoreWeave 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-V3.1:coreweave",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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