Search by keyword or choose a provider.
OpenAI · Flagship
For complex reasoning and coding tasks.
API ID：gpt-6-astra
Context：1,050,000 tokens · Max output：128,000 tokens
Input $10 ·Cached input No comparable data ·Output $50 / 1M
Artificial Analysis Intelligence Index 53 · Effort max
Official sources：Official model page · Checked 2026-10-21
OpenAI · Balanced flagship
For complex work, with capability close to Astra at a lower API cost.
API ID：gpt-6.1-sol
Context：1,050,000 tokens · Max output：128,000 tokens
Input $2 ·Cached input No comparable data ·Output $10 / 1M
Artificial Analysis Intelligence Index 52 · Effort max
Official sources：Official model page · Checked 2026-10-21
Anthropic · Flagship
Well suited to long-running agentic coding and knowledge work.
API ID：claude-opus-5-5
Context：1,000,000 tokens · Max output：128,000 tokens
Input $4 ·Cached input No comparable data ·Output $20 / 1M
Artificial Analysis Intelligence Index 58 · Effort max with fallback
Official sources：Official model page · Checked 2026-10-21
Anthropic · Advanced reasoning
For difficult reasoning and long-running agent tasks; the provider suggests it when Opus at high effort still falls short on evaluations.
API ID：claude-fable-5-1
Context：1,000,000 tokens · Max output：128,000 tokens
Input $10 ·Cached input No comparable data ·Output $50 / 1M
Artificial Analysis Intelligence Index 53 · Effort max with fallback
Official sources：Official model page · Checked 2026-10-21
Anthropic · Balanced flagship
Balances response speed and capability for everyday coding, analysis, and agent workflows.
API ID：claude-sonnet-5-5
Context：1,000,000 tokens · Max output：128,000 tokens
Input $2 ·Cached input No comparable data ·Output $10 / 1M
Artificial Analysis Intelligence Index 56 · Effort max with fallback
Official sources：Official model page · Checked 2026-10-21
Anthropic · High throughput
For high-throughput, low-latency classification, extraction, and routing tasks.
API ID：claude-haiku-5-5
Context：1,000,000 tokens · Max output：128,000 tokens
Input $0.1 ·Cached input No comparable data ·Output $0.5 / 1M
Artificial Analysis Intelligence Index 43 · Effort max
Official sources：Official model page · Checked 2026-10-21
Google · Flagship
For complex software engineering, math, science questions, and multi-step agent tasks.
API ID：gemini-4-argon
Context：1,048,576 tokens · Max output：65,536 tokens
Input $2 ·Cached input $0.1 ·Output $10 / 1M
Artificial Analysis Intelligence Index 53 · Effort high
Official sources：Official model page · Checked 2026-10-21
DeepSeek · High throughput
Supports thinking and non-thinking modes; API pricing varies by peak or off-peak period and cache hit status.
API ID：deepseek-flash
Context：1,000,000 tokens · Max output：384,000 tokens
Input $0.3 ·Cached input $0.006 ·Output $1.2 / 1M
Artificial Analysis Intelligence Index 45 · Effort max
Official sources：Official model page · Checked 2026-10-21
Alibaba Cloud Qwen · Flagship
Supports thinking and non-thinking modes; available regions and prices depend on the Model Studio deployment region.
API ID：qwen3.8-max
Context：1,000,000 tokens · Max output：No comparable data
Input ¥12 ·Cached input No comparable data ·Output ¥36 / 1M
Artificial Analysis Intelligence Index 45 · Effort Not specified by leaderboard
Official sources：Official model page · Checked 2026-10-21
xAI · Flagship
The text API offers a 500K context window; requests at the 200K input threshold are billed at long-context rates.
API ID：grok-4.7
Context：500,000 tokens · Max output：No comparable data
Input $2 ·Cached input $0.5 ·Output $6 / 1M
Artificial Analysis Intelligence Index 46 · Effort xhigh
Official sources：Official model page · Checked 2026-10-21