Together

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 Together

Model name

26 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:together	1.0M	$0.15/M	$0.29/M	$0.03/M	0.9s	40 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:together	1.0M	$0.15/M	$0.29/M	$0.03/M	0.9s	40 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:together	1.0M	$1.39/M	$4.16/M	$0.14/M	1s	74 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:together	1.0M	$1.39/M	$4.16/M	$0.14/M	1s	74 tps
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:together	1.0M	$0.31/M	$1.26/M	$0.0063/M	0.3s	217 tps
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:together	1.0M	$0.31/M	$1.26/M	$0.0063/M	0.3s	217 tps
GLM 5.2 z-ai/glm-5.2:together	1.0M	$1.47/M	$4.62/M	$0.27/M	0.3s	127 tps
GLM 5.2 (Thinking) z-ai/glm-5.2:thinking:together	1.0M	$1.47/M	$4.62/M	$0.27/M	0.3s	127 tps
GLM 5.3 z-ai/glm-5.3:together	1.0M	$1.47/M	$4.62/M	$0.27/M	0.2s	116 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:together	1.0M	$1.47/M	$4.62/M	$0.27/M	0.2s	116 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:together	1.0M	$0.16/M	$0.53/M	$0.03/M	0.9s	115.5 tps
GPT OSS 120B openai/gpt-oss-120b:together	131k	$0.16/M	$0.63/M	N/A	0.2s	83 tps
Inkling thinkingmachines/inkling:together	524k	$1.05/M	$4.25/M	$0.18/M	0.9s	112 tps
Inkling Small thinkingmachines/Inkling-Small:together	524k	$0.53/M	$1.26/M	$0.11/M	N/A	N/A
Inkling Small Thinking thinkingmachines/Inkling-Small:thinking:together	524k	$0.53/M	$1.26/M	$0.11/M	N/A	N/A
Inkling Thinking thinkingmachines/inkling:thinking:together	524k	$1.05/M	$4.25/M	$0.18/M	0.9s	112 tps
Kimi K3 moonshotai/kimi-k3:together	1.0M	$2.84/M	$14.18/M	$0.28/M	1.2s	42 tps
Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct:together	131k	$1.09/M	$1.09/M	N/A	0.5s	65 tps
MiniMax M3 minimax/minimax-m3:together	524k	$0.31/M	$1.26/M	$0.06/M	0.8s	46 tps
MiniMax M3 Thinking minimax/minimax-m3:thinking:together	524k	$0.31/M	$1.26/M	$0.06/M	0.8s	46 tps
Nvidia Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b:together	512k	$0.63/M	$3.78/M	$0.21/M	N/A	N/A
Nvidia Nemotron 3 Ultra 550B Thinking nvidia/nemotron-3-ultra-550b-a55b:thinking:together	512k	$0.63/M	$3.78/M	$0.21/M	N/A	N/A
Qwen 3.6 Plus qwen-3.6-plus:together	1M	$0.53/M	$3.15/M	N/A	N/A	N/A
Qwen3.5 9B qwen/qwen3.5-9b:together	262k	$0.18/M	$0.26/M	N/A	0.7s	62 tps
Qwen3.8 Max qwen3.8-max:together	1.0M	$2.10/M	$6.30/M	$0.26/M	0.3s	162 tps
Qwen3.8 Max Thinking qwen3.8-max:thinking:together	1.0M	$2.10/M	$6.30/M	$0.26/M	0.3s	162 tps

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731:together

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

0.9s

Throughput

40 tps

DeepSeek V4 Flash 0731 (Thinking)

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

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

0.9s

Throughput

40 tps

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:together

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.14/M

TTFT

1s

Throughput

74 tps

DeepSeek V4 Pro 0813 (Thinking)

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

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.14/M

TTFT

1s

Throughput

74 tps

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash:together

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0063/M

TTFT

0.3s

Throughput

217 tps

DeepSeek V4.1 Flash (Thinking)

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

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0063/M

TTFT

0.3s

Throughput

217 tps

GLM 5.2

z-ai/glm-5.2:together

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

0.3s

Throughput

127 tps

GLM 5.2 (Thinking)

z-ai/glm-5.2:thinking:together

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

0.3s

Throughput

127 tps

GLM 5.3

z-ai/glm-5.3:together

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

0.2s

Throughput

116 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:together

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

TTFT

0.2s

Throughput

116 tps

GLM 5.3 Flash

z-ai/glm-5.3-flash:together

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

TTFT

0.9s

Throughput

115.5 tps

GPT OSS 120B

openai/gpt-oss-120b:together

Context

131k

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

N/A

TTFT

0.2s

Throughput

83 tps

Inkling

thinkingmachines/inkling:together

Context

524k

Input /M

$1.05/M

Output /M

$4.25/M

Cache read /M

$0.18/M

TTFT

0.9s

Throughput

112 tps

Inkling Small

thinkingmachines/Inkling-Small:together

Context

524k

Input /M

$0.53/M

Output /M

$1.26/M

Cache read /M

$0.11/M

TTFT

N/A

Throughput

N/A

Inkling Small Thinking

thinkingmachines/Inkling-Small:thinking:together

Context

524k

Input /M

$0.53/M

Output /M

$1.26/M

Cache read /M

$0.11/M

TTFT

N/A

Throughput

N/A

Inkling Thinking

thinkingmachines/inkling:thinking:together

Context

524k

Input /M

$1.05/M

Output /M

$4.25/M

Cache read /M

$0.18/M

TTFT

0.9s

Throughput

112 tps

Kimi K3

moonshotai/kimi-k3:together

Context

1.0M

Input /M

$2.84/M

Output /M

$14.18/M

Cache read /M

$0.28/M

TTFT

1.2s

Throughput

42 tps

Llama 3.3 70B Instruct

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

Context

131k

Input /M

$1.09/M

Output /M

$1.09/M

Cache read /M

N/A

TTFT

0.5s

Throughput

65 tps

MiniMax M3

minimax/minimax-m3:together

Context

524k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

0.8s

Throughput

46 tps

MiniMax M3 Thinking

minimax/minimax-m3:thinking:together

Context

524k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

0.8s

Throughput

46 tps

Nvidia Nemotron 3 Ultra 550B

nvidia/nemotron-3-ultra-550b-a55b:together

Context

512k

Input /M

$0.63/M

Output /M

$3.78/M

Cache read /M

$0.21/M

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3 Ultra 550B Thinking

nvidia/nemotron-3-ultra-550b-a55b:thinking:together

Context

512k

Input /M

$0.63/M

Output /M

$3.78/M

Cache read /M

$0.21/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 Plus

qwen-3.6-plus:together

Context

1M

Input /M

$0.53/M

Output /M

$3.15/M

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

Qwen3.5 9B

qwen/qwen3.5-9b:together

Context

262k

Input /M

$0.18/M

Output /M

$0.26/M

Cache read /M

N/A

TTFT

0.7s

Throughput

62 tps

Qwen3.8 Max

qwen3.8-max:together

Context

1.0M

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.26/M

TTFT

0.3s

Throughput

162 tps

Qwen3.8 Max Thinking

qwen3.8-max:thinking:together

Context

1.0M

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.26/M

TTFT

0.3s

Throughput

162 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 Together via the API

Call a model served by Together 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:together",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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