impulse

Ling 3.0 Flash

Open weights

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.

API id Ling-3.0-flashReleased 23 Jul 2026 (Jul 2026)
Input / 1M
$0.06
at DeepInfra
Output / 1M
$0.18
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
2
2 listings
Released
Jul 2026
23 Jul 2026

Pricing

List prices at DeepInfra, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.06$0.18
Cached input
80% off input
$0.012

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$27.18
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$23.76
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$42.48
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$187
Use your own numbers

Where to run it

2 hosts serve Ling 3.0 Flash. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
Ling-3.0-flash
$0.06 / $0.18
Novita AIInference
ling-3.0-flash
$0.06 / $0.18

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Features
Prompt caching
Open weights
License: MIT
Runs in about 306 GB of GPU memory

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than DeepInfra.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Ling-3.0-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Ling 3.0 Flash cost?

On DeepInfra, Ling 3.0 Flash costs $0.06 per million input tokens and $0.18 per million output tokens. Cached input costs $0.012 per million tokens.

Which APIs offer Ling 3.0 Flash?

Ling 3.0 Flash runs on 2 APIs: DeepInfra and Novita AI.

What is Ling 3.0 Flash's context window?

131K tokens, with up to 131K tokens in one reply.

Is Ling 3.0 Flash being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Ling 3.0 Flash?

Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash Fast on Refuseless (17% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Ling 3.0 Flash released?

Independent released it on 23 Jul 2026.

What is Ling 3.0 Flash's API model id?

Use Ling-3.0-flash with DeepInfra. Other hosts use their own ids: ling-3.0-flash on Novita AI.

Sources

Raw catalog entry for Ling-3.0-flash on DeepInfra
{
  "max_output_tokens": 131072,
  "max_input_tokens": 131072,
  "input_cost_per_token": 6e-8,
  "output_cost_per_token": 1.8e-7,
  "cache_read_input_token_cost": 1.2e-8,
  "supports_prompt_caching": true,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "supports_vision": false,
  "source": "https://deepinfra.com/pricing"
}