Anthropic-compatible

Keep the Claude SDK. Change the base URL. Pay a fraction.

Tokenify serves the Anthropic Messages API at /v1/messages — same request shape, same streaming events, same error envelope. Your Claude code runs unchanged against DeepSeek V4.

Get an API key for the Anthropic SDK Using Claude Code? Set it up →

Per 1M tokens	Input	Output
Claude Haiku 4.5	$1.000	$5.000
DeepSeek V4 Pro	$0.660	$1.980
DeepSeek V4.1 Flash	$0.150	$0.600
DeepSeek V4.1 Flash off-peak	$0.090	$0.360

To be clear about what this is: Tokenify does not resell Anthropic’s models and is not affiliated with, endorsed by or connected to Anthropic. We implement their publicly documented API format so that code written for it can run against the models we do sell. Claude is a trademark of Anthropic.

Claude Haiku 4.5 price from claude.com, checked 2026-10-01. Tokenify serves DeepSeek models, not Claude.

One line

The same code, a different base URL

Messages, system prompts, content blocks, tool use, streaming and errors are all translated. Nothing in your client changes.

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.tokenify.dev",   # the only line that changes
    api_key=os.environ["TOKENIFY_API_KEY"],
)

message = client.messages.create(
    model="deepseek/deepseek-v4-pro",
    max_tokens=1024,
    system="Be concise.",
    messages=[{"role": "user", "content": "Explain B-trees"}],
)
print(message.content[0].text)

What it costs

Roughly 8× cheaper per blended token

Blended at a 3:1 prompt-to-completion ratio. Anthropic's published list price is shown for comparison; we do not sell it.

Model	Input / 1M	Output / 1M	Cache read / 1M	Context
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash50% off	$0.300$0.150 $0.090 off-peak	$1.200$0.600 $0.360 off-peak	$0.006 $0.003 off-peak	1049K	Use this model
DeepSeek V4 Pro deepseek/deepseek-v4-pro50% off	$1.320$0.660	$3.960$1.980	$0.044	1049K	Use this model
DeepSeek V4 Flash deepseek/deepseek-v4-flash50% off	$0.440$0.220	$1.320$0.660	$0.014	1049K	Use this model
GLM 5.3 Flash z-ai/glm-5.3-flash	$0.150	$0.500	$0.030	1049K	Use this model
GLM 5.2 z-ai/glm-5.250% off	$1.400$0.700	$4.400$2.200	$0.260	1049K	Use this model

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

50% off

Input / 1M: $0.300$0.150
$0.090 off-peak
Output / 1M: $1.200$0.600
$0.360 off-peak
Cache read / 1M: $0.006
$0.003 off-peak
Context: 1049K

Use this model

DeepSeek V4 Pro

deepseek/deepseek-v4-pro

50% off

Input / 1M: $1.320$0.660
Output / 1M: $3.960$1.980
Cache read / 1M: $0.044
Context: 1049K

Use this model

DeepSeek V4 Flash

deepseek/deepseek-v4-flash

50% off

Input / 1M: $0.440$0.220
Output / 1M: $1.320$0.660
Cache read / 1M: $0.014
Context: 1049K

Use this model

GLM 5.3 Flash

z-ai/glm-5.3-flash

Input / 1M: $0.150
Output / 1M: $0.500
Cache read / 1M: $0.030
Context: 1049K

Use this model

GLM 5.2

z-ai/glm-5.2

50% off

Input / 1M: $1.400$0.700
Output / 1M: $4.400$2.200
Cache read / 1M: $0.260
Context: 1049K

Use this model

Struck-through figures are the model vendor’s own published rate; the price beside them is what we charge. Billed per token, no minimum. Cache reads are the exception and carry no discount — they already cost between a third and a twenty-fifth of the input rate, and we pass the supplier’s cache rate through rather than flattening it into one headline number.

Off-peak pricing. DeepSeek V4.1 Flash is billed at two rates. Peak hours are Mon-Fri 09:00-12:00 and 14:00-18:00 (UTC+8); everything else is off-peak, including weekends. A request is billed at the rate in force when it is made, and every request in your logs records which one it was.

For reference, Claude Haiku 4.5 lists at $1.00 per million input tokens and $5.00 output, a blended $2.00 — from claude.com, checked 2026-10-01. DeepSeek V4.1 Flash through Tokenify blends to $0.262. They are different models with different capabilities — the point is that switching between them costs you one line, so you can measure the trade on your own workload instead of guessing at it.

What is and is not supported

Translated

system as a top-level field
Text and image content blocks
tool_use and tool_result round trips
tool_choice, including auto, any and a named tool
stop_sequences, temperature, top_p
Streaming lifecycle events, including tool JSON deltas
x-api-key auth and anthropic-version
Anthropic-shaped error envelopes

Not available

Anthropic’s own models — we do not resell them
Anthropic-specific beta headers and features
The Batches and Files APIs
Prompt caching control headers (cache hits are still billed at the cache rate when a supplier reports them)

Last updated 2026-10-01. Prices come from the live catalogue at the time this page was built.