BlazeInfer
Models

Open-weight models, priced by token.

Open-weight models, tuned for agentic workloads: up to 1.25M tokens of context, a warm KV cache across turns, and cached input from $0.006 per 1M tokens.

GLM 5.3 Flash

Z.ai

fp8

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

Context
1.25M
Max output
128K
Input
$0.075
Cached input
$0.015
Output
$0.25

Prices in USD per 1M tokens.

$15 free credit ≈ 60M output tokens

Try GLM 5.3 Flash →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

DeepSeek V4.1 Flash

DeepSeek

fp8

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Context
1M
Max output
944K
Input
$0.045
Cached input
$0.006
Output
$0.50

Prices in USD per 1M tokens.

$15 free credit ≈ 30M output tokens

Try DeepSeek V4.1 Flash →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

Kimi K3

MoonshotAI

mxfp4

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Context
250K
Max output
100K
Input
$3.00
Cached input
$0.60
Output
$15.00

Prices in USD per 1M tokens.

$15 free credit ≈ 1M output tokens

Try Kimi K3 →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

Qwen3.8 27B

Qwen

bf16

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

Context
125K
Max output
128K
Input
$0.425
Cached input
$0.085
Output
$2.55

Prices in USD per 1M tokens.

$15 free credit ≈ 5.9M output tokens

Try Qwen3.8 27B →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

Kimi K2.6

MoonshotAI

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Context
125K
Max output
236K
Input
$0.95
Cached input
$0.19
Output
$4.00

Prices in USD per 1M tokens.

$15 free credit ≈ 3.8M output tokens

Try Kimi K2.6 →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

Gemma 4 31B

Google

bf16

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Context
100K
Max output
16K
Input
$0.30
Cached input
$0.10
Output
$1.25

Prices in USD per 1M tokens.

$15 free credit ≈ 12M output tokens

Try Gemma 4 31B →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

Gemma 4 26B A4B

Google

bf16

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Context
32K
Max output
32K
Input
$0.07
Cached input
$0.014
Output
$0.34

Prices in USD per 1M tokens.

$15 free credit ≈ 44M output tokens

Try Gemma 4 26B A4B →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

Qwen3.5-9B

Qwen

bf16

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

Context
16K
Max output
32K
Input
$0.10
Cached input
$0.02
Output
$0.15

Prices in USD per 1M tokens.

$15 free credit ≈ 100M output tokens

Try Qwen3.5-9B →
  • Image input
  • Tool calling
  • Reasoning
  • Structured output

MiniMax H3

MiniMax

Video generation from a prompt and reference media. Guide it with up to 9 images, 3 videos and 3 audio clips, and get back an MP4 through an asynchronous jobs API.

Output
MP4 video
Length
4–15 s
Max size
1344×768
Price
$0.50 / s

Prices in USD per second of generated video.

$15 free credit ≈ 30 seconds of video

Try MiniMax H3 →
  • Video generation
  • Image, video and audio references

Prices last updated 11 November 2026. Cached input is the price for prompt tokens served from the KV cache; see session affinity & caching.

Start building on BlazeInfer

Sign up, get $15 in credits once your account is approved, and start calling open-weight models in minutes.