impulse

Swe 1.6

API id swe-1.6
Input / 1M
$0.50
at Cognition
Output / 1M
$2.50
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$0.50$2.50
Cached input
60% off input
$0.20

What it costs a month

At Cognition list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$311
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$258
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$498
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,800
Use your own numbers

Where to run it

1 host serve Swe 1.6. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
swe-1.6
$0.50 / $2.50

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

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    15% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    54% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    80% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    80% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    13% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    14% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    21% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    31% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedSwe 1.7Latest$0.50 / $2.50
  2. UndatedSwe 1.6This page$0.50 / $2.50

Call it

Using Cognition's API.

Python
from litellm import completion

response = completion(
    model="cognition/swe-1.6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Swe 1.6 cost?

On Cognition, Swe 1.6 costs $0.50 per million input tokens and $2.50 per million output tokens. Cached input costs $0.20 per million tokens.

Which APIs offer Swe 1.6?

Swe 1.6 runs on 1 API: Cognition.

Is Swe 1.6 being retired?

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

Is there a newer version of Swe 1.6?

Yes. Swe 1.7 is the newest model in this line.

What are cheaper alternatives to Swe 1.6?

Models that cost less and keep most of what it can do: Gemini 3.5 Flash Lite on Google AI Studio (15% less), GPT-5.4 Nano on OpenAI (54% less) and Motif 3 on ai& (13% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Swe 1.6's API model id?

Use swe-1.6 with Cognition.

Sources

Raw catalog entry for swe-1.6 on Cognition
{
  "input_cost_per_token": 5e-7,
  "output_cost_per_token": 0.0000025,
  "cache_read_input_token_cost": 2e-7,
  "litellm_provider": "cognition",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "source": "https://docs.devin.ai/windsurf/plugins/cascade/models"
}