AI Code Generation
Every model that writes code โ from dedicated coding models like Codestral and DeepSeek Coder to general LLMs with strong code capabilities. Compare context windows, pricing, language support, and real-world coding performance.
Live data โ updated daily
New
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
OpenAI GPT-6.1 Sol: GPT-6.1 reasoning at a fifth of Astra's price, over a 1M-token context window.
128K outIn: $3.50/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
New
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
OpenAI GPT-6.1 Terra: the mid-tier GPT-6.1 model at a tenth of Astra's price per token, over a 1M-token context window.
128K outIn: $1.75/1MOut: $8.75/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
OpenAI GPT-6 Astra โ frontier reasoning over a 1M-token context window.
128K outIn: $17.50/1MOut: $87.50/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
OpenAI GPT-6 Sol: GPT-6 reasoning at a fifth of Astra's price, over a 1M-token context window.
128K outIn: $3.50/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
OpenAI GPT-6 Luna: the fast, low-cost GPT-6 tier for high-volume chat and light agentic work, 1M-token context window.
128K outIn: $0.175/1MOut: $0.875/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Cost-efficient high-throughput model for budget-conscious applications
66K outIn: $0.175/1MOut: $0.7/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Google's latest GA Flash model for fast multimodal reasoning and agentic workloads.
66K outIn: $2.62/1MOut: $13.12/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Cost-efficient GA Flash model for high-throughput multimodal tasks.
66K outIn: $0.525/1MOut: $4.38/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Cost-efficient high-throughput model for budget-conscious applications.
66K outIn: $0.4375/1MOut: $2.62/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Google's most capable agentic model with 1M token context, 77.1% ARC-AGI-2 reasoning, and native tool use.
66K outIn: $3.50/1MOut: $21.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+2
Try on Zubnet โ
New
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Google's flagship reasoning model: a 1M-token context, text, image, video and audio in, text out, with native tool use and three thinking levels.
66K outIn: $3.50/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+2
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Mistral's open-weight flagship (public preview, 2026-10-06). 1.05T MoE (52B active) with a vision encoder; reasoning on demand, tools. 1M context.
262K outIn: $2.38/1MOut: $7.32/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Moonshot's open-weight 2.8T-parameter multimodal reasoning model with a 1M-token context window.
131K outIn: $5.25/1MOut: $26.25/1Mโโโโโ
ToolsStreamchatreasoningfunction_callingagentic+2
Try on Zubnet โ
New
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Moonshot's headline model: a 1M-token context window, native image understanding, tool use and reasoning.
In: $3.50/1MOut: $17.50/1Mโโโโโ
ToolsStreamchatreasoningfunction_callingagentic+2
Try on Zubnet โ
New
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Kimi K3.1 Pro at about 2โ3ร the speed, at a higher price: the same intelligence, with a 1M-token context window.
In: $7.00/1MOut: $35.00/1Mโโโโโ
ToolsStreamchatreasoningfunction_callingagentic+2
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Premium model for complex, multi-step work. Augure sovereign Canadian AI.
33K outIn: $3.15/1MOut: $7.56/1Mโโโโโ
ToolsStreamchattoolscoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Xiaomi's flagship MiMo model (V2.6, 2026-09). 1M context, accepts text and images, function calling and structured output, reasons before it answers.
131K outIn: $0.7612/1MOut: $1.52/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Xiaomi's fast, low-cost MiMo model (V2.6, 2026-09). 1M context, accepts text and images, function calling and structured output, reasons before it answers.
131K outIn: $0.245/1MOut: $0.49/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
MiMo V2.6 Pro on Xiaomi's high-speed tier, at a premium price. 1M context, accepts text and images, function calling and structured output.
131K outIn: $7.61/1MOut: $15.23/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
OpenAI GPT-4.1 (chat completions endpoint).
33K outIn: $3.50/1MOut: $14.00/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
OpenAI GPT-4.1 Mini (chat completions endpoint).
33K outIn: $0.7/1MOut: $2.80/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Ultra-fast model with 1M context. Best latency and cost efficiency for simple tasks.
33K outIn: $0.0385/1MOut: $0.378/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Balanced flagship model with 1M context. Best performance/cost ratio for most tasks.
33K outIn: $0.7/1MOut: $2.10/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Alibaba's 2.4T-parameter multimodal MoE flagship. 1M context, accepts text and images.
131K outIn: $3.50/1MOut: $10.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Flagship 1T+ parameter model. State-of-the-art reasoning, coding, and agent capabilities.
66K outIn: $0.2888/1MOut: $1.73/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
New
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Alibaba's newest Flash model. 1M context, accepts text and images, with tool use and thinking.
131K outIn: $0.1978/1MOut: $0.6685/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
New
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Low-cost Flash model with 1M context. Accepts text and images, with tool use and thinking.
131K outIn: $0.049/1MOut: $0.1925/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Flagship 1T+ parameter model. State-of-the-art reasoning, coding, and agent capabilities.
66K outIn: $0.0508/1MOut: $0.5022/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Cost-effective coding model optimized for speed. Fast code generation and completion at lower cost.
66K outIn: $0.252/1MOut: $1.00/1Mโโโโโ
ToolsStreamtoolscoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Multimodal frontier (vision/video); cheaper than Max.
8K outIn: $0.483/1MOut: $1.93/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
397B MoE model with 17B active parameters, 1M token context, multimodal (text/image/video)
8K outIn: $0.2013/1MOut: $1.20/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Qwen3.6 Plus, next-gen frontier LLM (Agentic Coding, vision/OCR, fine-grained localization). Replaces Qwen3.5 Plus.
8K outIn: $0.483/1MOut: $2.89/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Sonnet 5.5 by Anthropic (2026-09-28): the best combination of speed and intelligence, for everyday coding, documents and agents. 1M context, 128K output, adaptive thinking.
128K outIn: $3.50/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Anthropic's most capable Sonnet โ closes the gap with Opus for complex agents and coding (1M context)
128K outIn: $3.50/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Best Claude Sonnet for complex agents and coding (1M context)
128K outIn: $5.25/1MOut: $26.25/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Haiku 5.5 by Anthropic (2026-10-07): the fastest Claude, for high-volume, latency-sensitive work such as classification, extraction and routing. 1M context, 128K output, adaptive thinking.
128K outIn: $0.175/1MOut: $0.875/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Opus 5.5 by Anthropic (2026-09-21): the next Opus, for long-running agentic coding and knowledge work. 1M context, 128K output, adaptive thinking always on.
128K outIn: $7.00/1MOut: $35.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Anthropic's flagship Opus โ deep reasoning, agentic coding and long-horizon work (1M context)
128K outIn: $8.75/1MOut: $43.75/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Anthropic's most capable model for complex reasoning and agentic coding (1M context)
128K outIn: $8.75/1MOut: $43.75/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Highly capable Claude Opus for complex reasoning and coding (1M context)
128K outIn: $8.75/1MOut: $43.75/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Most capable Claude model with enhanced reasoning and coding
128K outIn: $8.75/1MOut: $43.75/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Fable 5 by Anthropic.
128K outIn: $17.50/1MOut: $87.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Fable 5.1 by Anthropic: the Fable before 5.2, for demanding reasoning and long-horizon agentic work. 1M context, 128K output, adaptive thinking always on.
128K outIn: $17.50/1MOut: $87.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
New
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Fable 5.2 by Anthropic: the most capable generally available Claude, for demanding reasoning and long-horizon agentic work. 1M context, 128K output, adaptive thinking always on.
128K outIn: $14.00/1MOut: $70.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
DeepSeek V4.1 Flash, the fast daily driver that replaced V4 Flash on 2026-09-10. 1M context, thinking (default) and non-thinking modes.
393K outIn: $0.2625/1MOut: $1.05/1Mโโโโโ
ToolsStreamchatreasoningtoolscoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
xAI's flagship general-purpose model. 1M context, balanced reasoning and chat.
8K outIn: $2.19/1MOut: $4.38/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Reasoning-mode variant of Grok 4.20. Slower but stronger on multi-step problems.
8K outIn: $2.19/1MOut: $4.38/1Mโโโโโ
ToolsStreamchatreasoningtoolsimage+1
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Non-reasoning variant of Grok 4.20. Fastest 4.20 path for chat and high-throughput tasks.
8K outIn: $2.19/1MOut: $4.38/1Mโโโโโ
ToolsStreamchattoolsimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Z.ai's latest flagship for agentic and coding tasks.
131K outIn: $2.45/1MOut: $7.70/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Z.ai's newest flagship for agentic and coding tasks. Always reasons; text-only input.
131K outIn: $2.45/1MOut: $7.70/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Z.ai's fast, low-cost GLM-5.3 variant: 1M context, tools, always reasons; text and image input.
131K outIn: $0.2625/1MOut: $0.875/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
New
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Inception Labs' most capable diffusion LLM: a 1M-token context, 131,072 max output, tool calling, reasoning_effort instant/low/medium/high (medium by default).
In: $0.175/1MOut: $0.6125/1Mโโโโโ
ToolsStreamchattoolscoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
DeepSeek flagship V4. 512K context, advanced reasoning + tool use.
66K outIn: $1.16/1MOut: $3.47/1Mโโโโโ
ToolsStreamchatreasoningtoolscoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Upstage flagship agentic model. 512K context (API-confirmed family), tool calling, structured outputs and opt-in reasoning. English/Korean/Japanese.
131K outIn: $0.525/1MOut: $2.10/1Mโโโโโ
ToolsStreamchatreasoningtoolscoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Upstage compact agentic MoE (35B total, 3B active). 524,288-token context (API-confirmed), tool calling and opt-in reasoning, English/Korean/Japanese.
131K outIn: $0.175/1MOut: $0.7/1Mโโโโโ
ToolsStreamchatreasoningtoolscoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
xAI's newest flagship, launched July 2026. 500K context, strongest reasoning + coding, trained alongside Cursor.
8K outIn: $3.50/1MOut: $10.50/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
xAI's newest flagship. 500K context, accepts text and images, strongest reasoning + coding.
8K outIn: $3.50/1MOut: $10.50/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
xAI's newest flagship (2026-09-21). 500K context, accepts text and images, function calling, structured outputs, reasoning.
8K outIn: $3.50/1MOut: $10.50/1Mโโโโโ
ToolsStreamchattoolsreasoningimage+1
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Sakana's multi-agent conductor, orchestrates a pool of frontier models for complex reasoning. Billed per token, orchestration included.
16K outIn: $8.75/1MOut: $52.50/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
OpenAI GPT-5.6 Sol โ frontier logic + deep reasoning, the flagship 5.6 tier.
128K outIn: $7.00/1MOut: $35.00/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
OpenAI GPT-5.6 Terra โ balanced business logic, mid 5.6 tier.
128K outIn: $3.50/1MOut: $21.00/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
OpenAI GPT-5.6 Luna โ high-volume streaming tasks, fast + economical 5.6 tier.
128K outIn: $0.35/1MOut: $2.10/1Mโโโโโ
ToolsStreamtoolsreasoningvisionimage+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
OpenAI flagship chat model (April 2026 release).
128K outIn: $8.75/1MOut: $52.50/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
OpenAI premium tier with deep reasoning. April 2026.
128K outIn: $52.50/1MOut: $315.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
OpenAI mid-tier flagship (March 2026).
128K outIn: $4.38/1MOut: $26.25/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
OpenAI fast/cheap chat model.
128K outIn: $1.31/1MOut: $7.88/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
OpenAI cheapest tier, very fast.
128K outIn: $0.35/1MOut: $2.19/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
OpenAI GPT-5.4 Pro (chat completions endpoint).
128K outIn: $52.50/1MOut: $315.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
OpenAI GPT-5.3 Codex (chat completions endpoint).
128K outIn: $3.06/1MOut: $24.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
OpenAI GPT-5.2 (chat completions endpoint).
128K outIn: $3.06/1MOut: $24.50/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
OpenAI GPT-5.2 Pro (chat completions endpoint).
128K outIn: $36.75/1MOut: $294.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
OpenAI GPT-5.1 (chat completions endpoint).
128K outIn: $2.19/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
OpenAI GPT-5 (chat completions endpoint).
128K outIn: $2.19/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
OpenAI GPT-5 Mini (chat completions endpoint).
128K outIn: $0.4375/1MOut: $3.50/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
OpenAI GPT-5 Nano (chat completions endpoint).
128K outIn: $0.0875/1MOut: $0.7/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
OpenAI GPT-5 Pro (chat completions endpoint).
128K outIn: $26.25/1MOut: $210.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Advanced vision-language model with 262K context. Excels at visual coding, spatial perception, and multimodal reasoning.
8K outIn: $0.252/1MOut: $2.51/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Alibaba's Agent Frontier flagship.
33K outIn: $2.89/1MOut: $8.66/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Google's open-weight dense model with 262K context and strong multilingual reasoning
33K outIn: $0.245/1MOut: $0.7/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Google's open-weight mixture-of-experts model, 26B total, 4B active parameters for fast inference
33K outIn: $0.105/1MOut: $0.5775/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.
8K outIn: $0.875/1MOut: $2.62/1Mโโโโโ
ToolsStreamchattoolsimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Fast and efficient model for simple tasks. Great balance of performance and cost.
8K outIn: $0.2625/1MOut: $1.05/1Mโโโโโ
ToolsStreamchattoolscoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Specialized model for code generation, completion, and understanding.
8K outIn: $0.525/1MOut: $1.57/1Mโโโโโ
Streamchatcoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Latest Kimi K2 reasoning model. Replaces K2 thinking variants (k2-thinking and k2-thinking-turbo) being retired 2026-05-25.
131K outIn: $1.66/1MOut: $7.00/1Mโโโโโ
ToolsStreamchatreasoningfunction_callingagentic+1
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Coding-specialized Kimi K2 model (k2.7). 256K context, agentic tool use and function calling, tuned for software engineering.
131K outIn: $1.66/1MOut: $7.00/1Mโโโโโ
ToolsStreamchatreasoningfunction_callingagentic+1
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
High-speed variant of Kimi K2.7 Code for low-latency agentic software engineering.
131K outIn: $3.32/1MOut: $14.00/1Mโโโโโ
ToolsStreamchatreasoningfunction_callingagentic+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
ByteDance Seed 2.0 Pro, flagship multimodal agent (text, image & video in โ text), strong tool use + reasoning, 256K context. Native via BytePlus (Ark).
66K outIn: $0.875/1MOut: $5.25/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
ByteDance Seed 2.1 Turbo, fast multimodal reasoning agent (text & image in โ text), strong tool use + thinking, 256K context. Native via BytePlus (Ark).
66K outIn: $0.875/1MOut: $4.38/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
ByteDance Seed 2.0 Lite, efficient multimodal agent (text, image & video in โ text), tool use + reasoning, 256K context. Native via BytePlus (Ark).
66K outIn: $0.4375/1MOut: $3.50/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
ByteDance Seed 2.0 Code (preview), coding-specialized agent (text & image in โ text), strong tool use + reasoning. Native via BytePlus (Ark).
66K outIn: $0.875/1MOut: $5.25/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Compact model tuned for code generation and structured output. 256K context.
8K outIn: $1.75/1MOut: $3.50/1Mโโโโโ
ToolsStreamchattoolsimagecoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
StepFun's multimodal flagship reasoning model.
16K outIn: $0.35/1MOut: $2.01/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
StepFun's latest reasoning model, 196B MoE (11B active), 256K context, open-source Apache 2.0. Fast agentic intelligence with strong code and math.
16K outIn: $0.175/1MOut: $0.525/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Newest reasoning model: the fastest of the Augure menu, strong at code, 256K context. Augure sovereign Canadian AI.
33K outIn: $1.89/1MOut: $3.78/1Mโโโโโ
Streamchatreasoningcoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Premium multimodal model with vision and tool use, strong bilingual EN/FR. Augure sovereign Canadian AI.
33K outIn: $3.15/1MOut: $7.56/1Mโโโโโ
ToolsStreamchattoolsreasoningvision+2
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Light tier: fast, thinking off, 256K context, served in Canada with no failover outside Canada. Replaces Tofino 2.5, retired by Augure on 2026-09-19.
16K outIn: $0.756/1MOut: $2.52/1Mโโโโโ
Streamchatcoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Most capable Z.ai model. 744B params (40B active MoE), 28.5T training tokens. Built for complex systems engineering and agentic tasks.
131K outIn: $1.75/1MOut: $5.60/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Native multimodal coding model. 744B MoE (40B active), 203K context. Optimized for design-to-code, GUI automation, and vision-grounded agentic tasks.
131K outIn: $2.10/1MOut: $7.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Latest flagship. 358B params, 204K context, 131K output. #1 on LiveCodeBench.
131K outIn: $1.05/1MOut: $3.85/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Flagship model with reasoning, coding, and agentic capabilities. 200K context.
131K outIn: $1.05/1MOut: $3.85/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Z.ai's current flagship for agentic and coding tasks.
131K outIn: $2.45/1MOut: $7.70/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Lightweight, completely free GLM-4.7 variant with 200K context.
131K outIn: $0/1MOut: $0/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Lightweight, high-speed and affordable GLM-4.7 variant with 200K context.
131K outIn: $0.1225/1MOut: $0.7/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Claude's best model for complex agents and coding
64K outIn: $5.25/1MOut: $26.25/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Claude's fastest and most intelligent Haiku model
64K outIn: $1.75/1MOut: $8.75/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
Premium model combining maximum intelligence with practical performance
64K outIn: $8.75/1MOut: $43.75/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Perplexity's advanced search model, deeper web research, multi-step reasoning with citations, 200K context.
16K outIn: $5.25/1MOut: $26.25/1Mโโโโโ
ToolsStreamtoolssearchcoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
OpenAI o3 (chat completions endpoint).
100K outIn: $3.50/1MOut: $14.00/1Mโโโโโ
ToolsStreamtoolsreasoningimagecoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Efficient reasoning model for everyday logic tasks.
40K outIn: $0.875/1MOut: $2.62/1Mโโโโโ
Streamchatreasoningcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Premier frontier-class multimodal model. Great balance between Large and Small.
8K outIn: $2.62/1MOut: $13.12/1Mโโโโโ
ToolsStreamchattoolsreasoningcoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
High-performance edge model with vision. Best Ministral for complex tasks.
8K outIn: $0.35/1MOut: $0.35/1Mโโโโโ
ToolsStreamchattoolsimagecoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
ByteDance Seed 2.0 Mini, fast lightweight multimodal agent (text, image & video in โ text), tool use. Native via BytePlus (Ark).
33K outIn: $0.175/1MOut: $0.7/1Mโโโโโ
ToolsStreamtoolsreasoningimagevideo+1
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
Mistral's model optimized for command-line and terminal-based coding workflows.
33K outIn: $0.175/1MOut: $0.525/1Mโโโโโ
ToolsStreamtoolscoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Previous flagship with thinking mode. MoE architecture, 128K context.
98K outIn: $1.05/1MOut: $3.85/1Mโโโโโ
Streamreasoningcoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Lightweight model optimized for efficiency. 128K context.
98K outIn: $0.35/1MOut: $1.93/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Free tier model. Great for testing and light workloads.
4K outIn: $0/1MOut: $0/1Mโโโโโ
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Perplexity's reasoning model, extended thinking with real-time web search, ideal for complex research and analysis.
16K outIn: $3.50/1MOut: $14.00/1Mโโโโโ
ToolsStreamtoolssearchreasoningcoder
Try on Zubnet โ
class TreeNode:
def __init__(self, val=0):
self.val = val
self.left = None
self.right = None
# Binary search tree
OpenAI GPT-4o (chat completions endpoint).
16K outIn: $4.38/1MOut: $17.50/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
func quickSort(arr []int) []int {
if len(arr) <= 1 {
return arr
}
pivot := arr[0]
OpenAI GPT-4o Mini (chat completions endpoint).
16K outIn: $0.2625/1MOut: $1.05/1Mโโโโโ
ToolsStreamtoolsimagecoder
Try on Zubnet โ
// React component
export const Button = ({ label }) => (
<button className="btn">
{label}
</button>
);
Upstage nightly build of Solar Pro 2 with latest improvements.
8K outIn: $0.2625/1MOut: $1.05/1Mโโโโโ
ToolsStreamchattoolscoder
Try on Zubnet โ
def fibonacci(n):
if n <= 1: return n
return fibonacci(n-1) + fibonacci(n-2)
# Dynamic programming version
def fib_dp(n):
Upstage advanced synthetic reasoning model with 64K context.
8K outIn: $0.2625/1MOut: $1.05/1Mโโโโโ
Streamchatcoder
Try on Zubnet โ
async function fetchData(url) {
const res = await fetch(url);
if (!res.ok) throw new Error();
return res.json();
}
Jina AI's code-specialized embedding model, 1.5B parameters optimized for code search and retrieval. 32K context.
In: $0.0875/1Mโโโโโ
Try on Zubnet โ
fn merge_sort(arr: &mut Vec<i32>) {
let len = arr.len();
if len <= 1 { return; }
let mid = len / 2;
Fast variant of GLM-5 with optimized speed and competitive quality.
In: $2.10/1MOut: $7.00/1M
ToolsStreamtoolsreasoningcoder
Try on Zubnet โ