impulse

Swe 1.7 Lightning

API id swe-1.7-lightning
Input / 1M
$2.50
at Cognition
Output / 1M
$12.50
at Cognition
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$2.50$12.50
Cached input
60% off input
$1.00

What it costs a month

At Cognition list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,553
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,290
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,490
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$9,000
Use your own numbers

Where to run it

1 host serve Swe 1.7 Lightning. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
swe-1.7-lightning
$2.50 / $12.50

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

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 Cognition.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    4% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    20% less
  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    20% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    40% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    20% less
  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
    40% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    60% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    66% less

Call it

Using Cognition's API.

Python
from litellm import completion

response = completion(
    model="cognition/swe-1.7-lightning",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Swe 1.7 Lightning cost?

On Cognition, Swe 1.7 Lightning costs $2.50 per million input tokens and $12.50 per million output tokens. Cached input costs $1.00 per million tokens.

Which APIs offer Swe 1.7 Lightning?

Swe 1.7 Lightning runs on 1 API: Cognition.

Is Swe 1.7 Lightning being retired?

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

What are cheaper alternatives to Swe 1.7 Lightning?

Models that cost less and keep most of what it can do: GPT-5.3 Codex on OpenAI (4% less), Gemini 4 Carbon on Google AI Studio (20% less) and Kimi K3.1 Pro on Databricks (20% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Swe 1.7 Lightning's API model id?

Use swe-1.7-lightning with Cognition.

Sources

Raw catalog entry for swe-1.7-lightning on Cognition
{
  "input_cost_per_token": 0.0000025,
  "output_cost_per_token": 0.0000125,
  "cache_read_input_token_cost": 0.000001,
  "litellm_provider": "cognition",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "source": "https://docs.devin.ai/desktop/models"
}