ModelBench
Google logo
Models/Google

Google: Gemini 3 Flash Preview

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

Source-linked gemini-flash Closed weights Released 2025-12-17
API record Report
InputT
OutputT
Input price$0.5/M
Output price$3/M
Context1.04858M
Max output65.536K
Providers26
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Gemini 3 Flash Preview
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
AnyAPI google/gemini-3-flash-preview 1.04858M 65.536K — — — ReasoningToolsJSON Docs ↗
QiHang gemini-3-flash-preview 1.04858M 65.536K $0.07 $0.43 — ReasoningToolsJSON Docs ↗
Kilo Gateway google/gemini-3-flash-preview 1.04858M 65.536K $0.25 $1.5 $0.025 ReasoningToolsJSON Docs ↗
Opper gemini/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
NanoGPT google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Eden AI google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Eden AI vertex/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
DevPass (LLM Gateway) gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
GitHub Copilot gemini-3-flash-preview 128K 64K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Neon gemini-3-flash 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
FrogBot gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Abacus gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Cloudflare AI Gateway google-ai-studio/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Vertex gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Requesty google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningTools Docs ↗
Merge Gateway google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
OpenRouter google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Perplexity Agent google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningTools Docs ↗
Databricks databricks-gemini-3-flash 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Google gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
OrcaRouter google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Pioneer gemini-3-flash 1M 65K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
ZenMux google/gemini-3-flash-preview 1.048M 64K $0.5 $3 $0.05 ReasoningTools Docs ↗
AIHubMix gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
Ofox google/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗
CrossModel gemini/gemini-3-flash-preview 1.04858M 65.536K $0.5 $3 $0.05 ReasoningToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.07/M

Across 25 priced providers

Median input $0.5/M

Midpoint of listed rates

Highest input $0.5/M

7.1× the lowest listed rate

Output range $0.43 – $3

Per million output tokens

QiHang $0.07/MLowest
Kilo Gateway $0.25/M
Opper $0.5/M
NanoGPT $0.5/M
Eden AI $0.5/M
Eden AI $0.5/M
DevPass (LLM Gateway) $0.5/M
GitHub Copilot $0.5/M
Neon $0.5/M
FrogBot $0.5/M
Abacus $0.5/M
Cloudflare AI Gateway $0.5/M
Vertex $0.5/M
Requesty $0.5/M
Merge Gateway $0.5/M
OpenRouter $0.5/M
Perplexity Agent $0.5/M
Databricks $0.5/M
Google $0.5/M
OrcaRouter $0.5/M
Pioneer $0.5/M
ZenMux $0.5/M
AIHubMix $0.5/M
Ofox $0.5/M
CrossModel $0.5/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 128K to 1.04858M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
✓ Attachments Yes
✓ Vision input Yes
× Open weights No
Creator
Google
Model family
gemini-flash
Knowledge cutoff
2025-01
License
Not documented
Release date
2025-12-17
Model ID
google/gemini-3-flash-preview
Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
Design Arena: w…Design Arena: website Design Arena: c…Design Arena: codecategories Design Arena: g…Design Arena: gamedev Design Arena: 3dDesign Arena: 3d Design Arena: f…Design Arena: fullstack Design Arena: w…Design Arena: webapps Design Arena: m…Design Arena: mobileapps Design Arena: a…Design Arena: androidnative This model — Design Arena: website: 1208 elo (54.9th percentile) This model — Design Arena: codecategories: 1204 elo (52.7th percentile) This model — Design Arena: gamedev: 1189 elo (47.6th percentile) This model — Design Arena: 3d: 1212 elo (54.1th percentile) This model — Design Arena: fullstack: 1072 elo (22.4th percentile) This model — Design Arena: webapps: 1131 elo (22.4th percentile) This model — Design Arena: mobileapps: 1119 elo (13.6th percentile) This model — Design Arena: androidnative: 1069 elo (13.6th percentile)

Each axis is this model's percentile among the 8 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Design Arena: website elo Source ↗
Design Arena: website #79 of 175
Design Arena: codecategories elo Source ↗
Design Arena: codecategories #79 of 167
Design Arena: gamedev elo Source ↗
Design Arena: gamedev #86 of 166
Design Arena: 3d elo Source ↗
Design Arena: 3d #72 of 157
Design Arena: fullstack elo Source ↗
Design Arena: fullstack #52 of 67
Design Arena: webapps elo Source ↗
Design Arena: webapps #52 of 67
Design Arena: mobileapps elo Source ↗
Design Arena: mobileapps #56 of 66
Design Arena: androidnative elo Source ↗
Design Arena: androidnative #51 of 59
Design Arena: python-pptxslides elo Source ↗
Design Arena: python-pptxslides #46 of 47
Design Arena: godotgamedev elo Source ↗
Design Arena: godotgamedev #23 of 45
SWE-Bench Pro resolve rate Source ↗
SWE-Bench Pro #34 of 38
Design Arena: agenticslides elo Source ↗
Design Arena: agenticslides #14 of 17
Design Arena: agenticslides(python-pptx) elo Source ↗
Design Arena: agenticslides(python-pptx) #14 of 17
SWE-Atlas Codebase QnA score · Mini-SWE-Agent Source ↗
SWE-Atlas Codebase QnA #7 of 7
SWE-Atlas Test Writing score · Mini-SWE-Agent Source ↗
SWE-Atlas Test Writing #3 of 7
SWE-Atlas Refactoring score · Mini-SWE-Agent Source ↗
SWE-Atlas Refactoring #4 of 4

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Design Arena: website, the benchmark with the widest published coverage that this model appears in.

0 720 1441 $0.1 $1 $10 Claude Opus 5 — $5/M, score 1320.0 OpenAI: GPT-5.1 (batch) — $0.625/M, score 1199.0 Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 1135.0 OpenAI: GPT-5 (batch) — $0.625/M, score 1197.0 Gemini 3.1 Flash Lite Preview — $0.25/M, score 1095.0 OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 1010.0 Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 1077.0 Mistral: Mistral Small 3.2 24B — $0.075/M, score 908.0 GPT-5.1 Codex — $1.07/M, score 1174.0 GPT-5.4 — $2.5/M, score 1232.0 Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 1175.0 DeepSeek: DeepSeek V3.2 Exp — $0.27/M, score 1191.0 Anthropic: Claude Opus 4 — $15/M, score 1177.0 Qwen: Qwen3 235B A22B — $0.455/M, score 1043.0 Gemini 3.5 Flash — $1.5/M, score 1275.0 Z.ai: GLM 5.3 Flash (batch) — $0.075/M, score 1291.0 GPT-4.1 mini — $0.4/M, score 1010.0 DeepSeek V4 Pro — $0.435/M, score 1247.0 Claude Sonnet 5 — $2/M, score 1289.0 Mistral: Ministral 3 8B 2512 — $0.15/M, score 1077.0 Z.ai: GLM 5.1 — $0.966/M, score 1290.0 Gemini 3.7 Flash — $0.75/M, score 1315.0 Muse Spark 1.3 — $1.25/M, score 1359.0 Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 1267.0 Mistral: Mistral Large 3 2512 — $0.5/M, score 1175.0 DeepSeek V3.2 — $0.18/M, score 1187.0 OpenAI: GPT-5.5 (batch) — $2.5/M, score 1269.0 Anthropic: Claude Opus 4.7 — $5/M, score 1307.0 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 1275.0 Google: Gemini 2.5 Pro (batch) — $0.625/M, score 1179.0 Inception: Mercury 2 — $0.25/M, score 1035.0 OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 985.0 Gemini 3.6 Flash — $0.75/M, score 1312.0 Anthropic: Claude Sonnet 4.5 — $3/M, score 1202.0 Z.ai: GLM 4.7 Flash — $0.061/M, score 1206.0 Claude Fable 5 — $10/M, score 1310.0 Gemini 2.5 Pro — $1.25/M, score 1179.0 Z.ai: GLM 5.3 Flash — $0.15/M, score 1291.0 MiniMax: MiniMax M3 — $0.3/M, score 1271.0 Google: Gemini 2.5 Flash (batch) — $0.15/M, score 1127.0 Anthropic: Claude Fable 5.1 — $10/M, score 1322.0 Z.ai: GLM 5V Turbo — $1.2/M, score 1243.0 MoonshotAI: Kimi K2.7 Code (batch) — $0.95/M, score 1290.0 OpenAI: o3 (batch) — $1/M, score 1048.0 Inkling — $1.87/M, score 1226.0 OpenAI: gpt-oss-20b (batch) — $0.05/M, score 865.0 Muse Spark 1.1 — $1.25/M, score 1282.0 MiMo-V2.5 — $0.14/M, score 1279.0 MoonshotAI: Kimi K2 0711 — $0.57/M, score 1063.0 Kimi K2 Thinking — $0.4/M, score 1125.0 Qwen: Qwen3.8 Max (0803) — $2/M, score 1295.0 Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 1145.0 GPT-5.1 — $1.25/M, score 1199.0 Anthropic: Claude Fable 5.1 (batch) — $5/M, score 1322.0 Google: Gemini 3.8 Flash (batch) — $0.375/M, score 1315.0 Google: Gemini 3.7 Flash (batch) — $0.375/M, score 1315.0 GPT-5.3 Codex — $1.75/M, score 1175.0 Z.ai: GLM 5.3 (batch) — $0.7/M, score 1319.0 DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 1251.0 Anthropic: Claude Opus 4.6 (batch) — $2.5/M, score 1304.0 MoonshotAI: Kimi K3 (batch) — $3/M, score 1354.0 GPT-5.5 — $5/M, score 1269.0 OpenAI: GPT-5 Nano (batch) — $0.025/M, score 1114.0 Mistral: Codestral 2508 (batch) — $0.15/M, score 1025.0 Anthropic: Claude Sonnet 5 (batch) — $1/M, score 1289.0 OpenAI: GPT-5.2 (batch) — $0.875/M, score 1207.0 Anthropic: Claude Fable 5 (batch) — $5/M, score 1310.0 GPT-5.1 Codex mini — $0.22/M, score 1123.0 Thinking Machines: Inkling (batch) — $1/M, score 1226.0 GPT OSS 120B — $0.03/M, score 980.0 OpenAI: GPT-4o (batch) — $1.25/M, score 843.0 Mistral: Codestral 2508 — $0.3/M, score 1025.0 SpaceXAI: Grok 4.6 — $2/M, score 1306.0 DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 1199.0 GPT-5 Mini — $0.25/M, score 1137.0 Claude Opus 5 (batch) — $2.5/M, score 1320.0 o3 — $2/M, score 1048.0 OpenAI: GPT-5.4 (batch) — $1.25/M, score 1232.0 DeepSeek V4 Flash — $0.15/M, score 1220.0 DeepSeek Chat — $0.147/M, score 1132.0 Qwen: Qwen3 Max — $0.78/M, score 1131.0 Kimi K2.7 Code — $0.95/M, score 1279.0 GPT-4.1 — $2/M, score 1051.0 Z.ai: GLM 5.2 (batch) — $0.7/M, score 1307.0 Google: Gemini 3.6 Flash (batch) — $0.375/M, score 1312.0 Z.ai: GLM 5.3 — $1.4/M, score 1319.0 Anthropic: Claude Opus 4.8 — $5/M, score 1267.0 SpaceXAI: Grok 4.3 — $1.25/M, score 1206.0 Gemini 3 Flash Preview — $0.5/M, score 1208.0 MiniMax: MiniMax M3 (batch) — $0.3/M, score 1271.0 Gemini 3.8 Flash — $0.75/M, score 1315.0 NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 1144.0 OpenAI: o4 Mini (batch) — $0.55/M, score 998.0 Z.ai: GLM 5 — $0.6/M, score 1260.0 MiniMax: MiniMax M2.7 — $0.3/M, score 1258.0 SpaceXAI: Grok 4.5 — $2/M, score 1296.0 Mistral: Mistral Medium 3.1 — $0.4/M, score 1145.0 Kimi K2.6 — $0.95/M, score 1282.0 Google: Gemini 3 Flash Preview (batch) — $0.25/M, score 1208.0 GPT-5.2 — $1.75/M, score 1207.0 Kimi K3 — $3/M, score 1354.0 Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 1202.0 OpenAI: gpt-oss-120b (batch) — $0.15/M, score 980.0 OpenAI: GPT-4.1 (batch) — $1/M, score 1051.0 MiniMax: MiniMax M2 — $0.255/M, score 1155.0 Solar Pro 4 — $0.3/M, score 1188.0 Gemini 3.1 Pro Preview — $2/M, score 1265.0 Anthropic: Claude Opus 4.1 (batch) — $7.5/M, score 1189.0 Qwen: Qwen3 Coder 480B A35B — $0.3/M, score 1171.0 Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 1307.0 Mistral: Mistral Medium 3 — $0.4/M, score 1091.0 MiMo-V2.5-Pro — $0.435/M, score 1285.0 Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 1265.0 Anthropic: Claude Opus 4.1 — $15/M, score 1189.0 Anthropic: Claude Sonnet 4.6 — $3/M, score 1297.0 Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 1297.0 DeepSeek V4 Flash 0731 — $0.05/M, score 1251.0 GPT-5 — $1.25/M, score 1197.0 OpenAI: GPT-5 Mini (batch) — $0.125/M, score 1137.0 Anthropic: Claude Opus 4.5 (batch) — $2.5/M, score 1259.0 Qwen: Qwen3.7 Plus — $0.32/M, score 1282.0 SpaceXAI: Grok 4.3 (batch) — $1/M, score 1206.0 o4-mini — $1.1/M, score 998.0 Nemotron 3 Ultra 550B A55B — $0.5/M, score 1144.0 Anthropic: Claude Sonnet 4 — $3/M, score 1158.0 SpaceXAI: Grok 4.20 — $1.25/M, score 1242.0 Hy3 — $0.066/M, score 1194.0 Qwen: Qwen3.6 Plus — $0.325/M, score 1253.0 Z.ai: GLM 4.6 — $0.43/M, score 1187.0 GPT-4o — $2.5/M, score 843.0 Gemini 2.5 Flash — $0.3/M, score 1127.0 Muse Spark 1.2 — $1.25/M, score 1322.0 GPT-4.1 nano — $0.1/M, score 985.0 GPT OSS 20B — $0.02/M, score 865.0 Kimi K2.5 — $0.3/M, score 1261.0 Trinity Large Thinking — $0.25/M, score 1149.0 MoonshotAI: Kimi K2 0905 — $0.6/M, score 1120.0 Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 943.0 Z.ai: GLM 5.2 — $0.966/M, score 1307.0 Qwen: Qwen3.7 Max — $1.475/M, score 1285.0 Qwen: Qwen3.5 Plus 2026-02-15 — $0.26/M, score 1200.0 MiniMax: MiniMax M2.1 — $0.3/M, score 1214.0 Z.ai: GLM 4.7 — $0.4/M, score 1238.0 Mistral: Ministral 3 3B 2512 — $0.1/M, score 1040.0 Amazon: Nova Premier 1.0 — $2.5/M, score 847.0 DeepSeek: DeepSeek V3.1 — $0.25/M, score 1135.0 Z.ai: GLM 4.5 — $0.6/M, score 1182.0 Meta: Llama 4 Maverick — $0.2/M, score 883.0 Nex AGI: Nex-N2-Pro — $0.25/M, score 1236.0 Z.ai: GLM 5 Turbo — $1.2/M, score 1278.0 Qwen: Qwen3.5 397B A17B — $0.55/M, score 1203.0 MiniMax: MiniMax M2.5 — $0.3/M, score 1235.0 Anthropic: Claude Opus 4.6 — $5/M, score 1304.0 Mistral: Ministral 3 14B 2512 — $0.2/M, score 1093.0 Anthropic: Claude Opus 4.5 — $5/M, score 1259.0 Anthropic: Claude Haiku 4.5 — $1/M, score 1135.0 Qwen: Qwen3 Coder 30B A3B Instruct — $0.07/M, score 1100.0 Z.ai: GLM 4.5 Air — $0.13/M, score 1159.0 Qwen: Qwen3 235B A22B Thinking 2507 — $0.23/M, score 1065.0 Qwen: Qwen3 235B A22B Instruct 2507 — $0.22/M, score 1070.0 DeepSeek: R1 0528 — $0.5/M, score 1161.0 Qwen: Qwen3 30B A3B — $0.12/M, score 967.0 Meta: Llama 4 Scout — $0.1/M, score 762.0 Amazon: Nova Pro 1.0 — $0.8/M, score 808.0 GPT-5 Nano — $0.05/M, score 1114.0 Step 3.7 Flash — $0.185/M, score 1206.0 Gemini 3 Flash Preview Input price per million tokens (log scale) Elo

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Max Output Tokens65535 → 65536
Max Output Tokens65536 → 65535
Max Output Tokens65535 → 65536
Max Output Tokens65536 → 65535
Max Output Tokens65535 → 65536
Max Output Tokens65536 → 65535
Max Output Tokens65535 → 65536
Max Output Tokens65536 → 65535
Max Output Tokens65535 → 65536
Max Output Tokens65536 → 65535
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Sep 11, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗AnyAPI documentationprovider documentation ↗QiHang documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗Opper documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗Eden AI documentationprovider documentation ↗DevPass (LLM Gateway) documentationprovider documentation ↗GitHub Copilot documentationprovider documentation ↗Neon documentationprovider documentation ↗FrogBot documentationprovider documentation ↗Abacus documentationprovider documentation ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/google/gemini-3-flash-preview
curl
curl "https://model.kyssta.lol/api/v1/models/google/gemini-3-flash-preview"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Gemini 3 Flash Preview?

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs. It is published by Google and catalogued here from Models.dev.

How much does Gemini 3 Flash Preview cost?

Listed input pricing starts at $0.07 per million tokens from QiHang, rising to $0.5 across 25 listed providers.

What is the context length of Gemini 3 Flash Preview?

Gemini 3 Flash Preview accepts up to 1.04858M tokens of context and returns up to 65.536K output tokens.

Does Gemini 3 Flash Preview support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve Gemini 3 Flash Preview?

25 providers list this model: AnyAPI, QiHang, Kilo Gateway, Opper, NanoGPT, Eden AI and 19 more.

Are the weights for Gemini 3 Flash Preview open?

No. This model is served through hosted APIs only.

When was Gemini 3 Flash Preview released?

The catalog records a release date of 2025-12-17, last verified Sep 11, 2026.

More models from Google

View all →
Deep Research Max Preview

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

1.04858M ctx Veo 3.1 Preview

Video model for prompt-guided generation, editing, and motion workflows

1.024K ctx Gemini Omni Flash Preview

Video generation and editing model for fast, conversational text- and image-to-video workflows

1.04858M ctx $1.5/M in Gemini 3.5 Live Translate Preview

Low-latency audio-to-audio model for real-time speech translation across 70+ languages

131.072K ctx $3.5/M in