impulse

Speech 2.6 Turbo

Open weightsSpeech
API id speech-2.6-turbo
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve Speech 2.6 Turbo. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
MiniMaxLab API
speech-2.6-turbo
-
ReplicateInference
speech-2.6-turbo
$60.00 / -

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
Audio
Open weights
License: Apache-2.0
Runtimes: SGLang, vLLM

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller MiniMax models

No similar MiniMax model keeps its key capabilities.

Other frontier labs

Open-weight picks

Model line

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

  1. UndatedSpeech 2.6 TurboLatestNot listed
  2. UndatedSpeech 02 TurboNot listed

Call it

Using MiniMax's API.

Python
from litellm import completion

response = completion(
    model="minimax/speech-2.6-turbo",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Speech 2.6 Turbo cost?

Its lowest listed price is at Replicate: $60.00 per million input tokens.

Which APIs offer Speech 2.6 Turbo?

Speech 2.6 Turbo runs on 2 APIs: MiniMax and Replicate.

Is Speech 2.6 Turbo being retired?

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

Is there a newer version of Speech 2.6 Turbo?

No. Speech 2.6 Turbo is the newest model in its line.

What is Speech 2.6 Turbo's API model id?

Use speech-2.6-turbo with MiniMax.

Sources

Raw catalog entry for speech-2.6-turbo on MiniMax
{
  "input_cost_per_character": 0.00006,
  "litellm_provider": "minimax",
  "mode": "audio_speech",
  "supported_endpoints": [
    "/v1/audio/speech"
  ]
}