# API Agent Landscape

A market map for API teams: which products agents can discover, understand, and use in real tasks. Claude Code, Codex, CLI, and MCP are evidence surfaces; the primary lens is API company readiness.

| Metric | Value |
|--------|-------|
| API companies ranked | 144 |
| Models | 2 |
| API categories covered | 32 |
| API benchmark signals | 288 |
| Average API score | 58 |

## Interpretation

For an API company, the benchmark is really asking whether agents can become successful API users: can they find the right docs, understand the product, authenticate, recover from errors, and finish a task without human intervention?

API is the primary market lens. CLI and MCP stay in the landscape because they reveal whether readiness holds across multiple entry points, not just one happy-path integration.

| Surface | Claude Code | Codex | Read |
|---------|-------------|-------|------|
| API | 59 | 57 | Claude Code +2 |
| CLI | 30 | 53 | Codex +23 |
| MCP | 38 | 39 | Codex +2 |

Rankings below favor companies with both Claude Code and Codex API rows when possible. One-off high scores remain useful signals, but they should not carry the same weight as repeated API performance.

## What API Teams Should Take Away

- **API readiness baseline:** 144 API companies average 58 across 288 scored API runs.
- **Interface risk:** CLI changes the market view most, with a 23-point swing.
- **Agent effort:** The fastest API slice is Codex at 3m 22s.
- **Friction hotspot:** Email averages 10 errors and 5m 43s runtime.

## Agent Lens For API Companies

| Agent | API Score | API Companies | API Categories | Avg Cost | Avg Runtime | Avg Tool Calls | Avg Errors |
|-------|-----------|---------------|----------------|----------|-------------|----------------|------------|
| Claude Code | 59 | 144 | 32 | $0.39 | 3m 47s | 18 | 4 |
| Codex | 57 | 144 | 32 | $1.75 | 3m 22s | 17 | 3 |

## Claude Vs Codex Surface Map

| Interface | Agent | Average Score | Companies | Categories | Current Leader |
|-----------|-------|---------------|-----------|------------|----------------|
| API | Claude Code | 59 | 144 | 32 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) |
| API | Codex | 57 | 144 | 32 | [Tavily](/leaderboard/codex/api/tavily) |
| CLI | Claude Code | 30 | 94 | 22 | [LiveKit](/leaderboard/claudecode/cli/livekit) |
| CLI | Codex | 53 | 56 | 20 | [Firecrawl](/leaderboard/codex/cli/firecrawl) |
| MCP | Claude Code | 38 | 75 | 24 | [Exa](/leaderboard/claudecode/mcp/exa) |
| MCP | Codex | 39 | 74 | 24 | [Exa](/leaderboard/codex/mcp/exa) |

## Category Leaders By Agent And Surface

These tables mirror the default rendered page state: one leader per category and surface.

### Claude Code Category Leaders

| Category | API | CLI | MCP |
|----------|-----|-----|-----|
| Search | [Firecrawl](/leaderboard/claudecode/api/firecrawl) | [Nimble](/leaderboard/claudecode/cli/nimbleway) | [Exa](/leaderboard/claudecode/mcp/exa) |
| Storage | [Box](/leaderboard/claudecode/api/box) | [Box](/leaderboard/claudecode/cli/box) | [Box](/leaderboard/claudecode/mcp/box) |
| Voice TTS | [ElevenLabs](/leaderboard/claudecode/api/elevenlabs) | [Rime](/leaderboard/claudecode/cli/rime) | [ElevenLabs](/leaderboard/claudecode/mcp/elevenlabs) |
| Document Parsing | [Reducto](/leaderboard/claudecode/api/reducto) | [Extend.ai](/leaderboard/claudecode/cli/extend-ai) | [Extend.ai](/leaderboard/claudecode/mcp/extend-ai) |
| Inference | [Fireworks AI](/leaderboard/claudecode/api/fireworks-ai) | [OpenRouter](/leaderboard/claudecode/cli/openrouter) | [Cerebras](/leaderboard/claudecode/mcp/cerebras) |
| Browser | [Anchor Browser](/leaderboard/claudecode/api/anchor-browser) | [Steel](/leaderboard/claudecode/cli/steel) | [Anchor Browser](/leaderboard/claudecode/mcp/anchor-browser) |
| Geocoding | [OpenCageData](/leaderboard/claudecode/api/opencagedata) | — | [OpenCageData](/leaderboard/claudecode/mcp/opencagedata) |
| Observability | [Datadog](/leaderboard/claudecode/api/datadog) | [Datadog](/leaderboard/claudecode/cli/datadog) | [Datadog](/leaderboard/claudecode/mcp/datadog) |
| Sandboxes | [Daytona](/leaderboard/claudecode/api/daytona) | [E2B](/leaderboard/claudecode/cli/e2b) | [E2B](/leaderboard/claudecode/mcp/e2b) |
| Vector Databases | [Chroma](/leaderboard/claudecode/api/chroma) | [Pinecone](/leaderboard/claudecode/cli/pinecone) | [LanceDB](/leaderboard/claudecode/mcp/lancedb) |
| Payment | [Stripe](/leaderboard/claudecode/api/stripe) | [Stripe](/leaderboard/claudecode/cli/stripe) | [Stripe](/leaderboard/claudecode/mcp/stripe) |
| Webscraping | [Scrapfly](/leaderboard/claudecode/api/scrapfly) | — | [fastCRW](/leaderboard/claudecode/mcp/fastcrw) |
| Voice Infra | [LiveKit](/leaderboard/claudecode/api/livekit) | [LiveKit](/leaderboard/claudecode/cli/livekit) | [LiveKit](/leaderboard/claudecode/mcp/livekit) |
| Durable Workflow | [Temporal](/leaderboard/claudecode/api/temporal) | [Temporal](/leaderboard/claudecode/cli/temporal) | [Prefect](/leaderboard/claudecode/mcp/prefect) |
| Voice STT | [Deepgram](/leaderboard/claudecode/api/deepgram) | [Deepgram](/leaderboard/claudecode/cli/deepgram) | [Deepgram](/leaderboard/claudecode/mcp/deepgram) |
| Graph Databases | [Neo4j](/leaderboard/claudecode/api/neo4j) | — | — |
| Auth | [WorkOS](/leaderboard/claudecode/api/workos) | [WorkOS](/leaderboard/claudecode/cli/workos) | [Descope](/leaderboard/claudecode/mcp/descope) |
| Cloud Hosting | [Render](/leaderboard/claudecode/api/render) | [Render](/leaderboard/claudecode/cli/render) | [Render](/leaderboard/claudecode/mcp/render) |
| Email | [Resend](/leaderboard/claudecode/api/resend) | [Agentmail](/leaderboard/claudecode/cli/agentmail) | [Resend](/leaderboard/claudecode/mcp/resend) |
| E-Signature | [PandaDoc](/leaderboard/claudecode/api/pandadoc) | — | — |
| Unified API | [Naive](/leaderboard/claudecode/api/naive) | [Naive](/leaderboard/claudecode/cli/naive) | [Naive](/leaderboard/claudecode/mcp/naive) |
| Voice Telephony | [Telnyx](/leaderboard/claudecode/api/telnyx) | [Twilio](/leaderboard/claudecode/cli/twilio) | [Plivo](/leaderboard/claudecode/mcp/plivo) |
| Meeting Bot | [Meetstream](/leaderboard/claudecode/api/meetstream) | [Meetstream](/leaderboard/claudecode/cli/meetstream) | [MeetGeek](/leaderboard/claudecode/mcp/meetgeek) |
| Stablecoin | [DFNS](/leaderboard/claudecode/api/dfns) | [Circle](/leaderboard/claudecode/cli/circle) | [BlindPay](/leaderboard/claudecode/mcp/blindpay) |
| Proxy | [Massive](/leaderboard/claudecode/api/massive) | — | [Massive](/leaderboard/claudecode/mcp/massive) |
| Verification | [Prelude](/leaderboard/claudecode/api/prelude) | — | — |
| Video Agent | [Tavus](/leaderboard/claudecode/api/tavus) | — | — |
| Neocloud | [Nebius AI Cloud](/leaderboard/claudecode/api/nebius-ai-cloud) | [Nebius AI Cloud](/leaderboard/claudecode/cli/nebius-ai-cloud) | — |
| Database | [Convex](/leaderboard/claudecode/api/convex) | — | [Convex](/leaderboard/claudecode/mcp/convex) |
| CMS | [Strapi](/leaderboard/claudecode/api/strapi) | — | — |
| Code Review | [Macroscope](/leaderboard/claudecode/api/macroscope) | [Semgrep](/leaderboard/claudecode/cli/semgrep) | — |
| Talent Directory | [Roster](/leaderboard/claudecode/api/roster) | — | — |

### Codex Category Leaders

| Category | API | CLI | MCP |
|----------|-----|-----|-----|
| Search | [Tavily](/leaderboard/codex/api/tavily) | [Firecrawl](/leaderboard/codex/cli/firecrawl) | [Exa](/leaderboard/codex/mcp/exa) |
| Payment | [Stripe](/leaderboard/codex/api/stripe) | [Stripe](/leaderboard/codex/cli/stripe) | [Stripe](/leaderboard/codex/mcp/stripe) |
| Storage | [Box](/leaderboard/codex/api/box) | [Box](/leaderboard/codex/cli/box) | [Box](/leaderboard/codex/mcp/box) |
| Inference | [Fireworks AI](/leaderboard/codex/api/fireworks-ai) | [OpenRouter](/leaderboard/codex/cli/openrouter) | [Cerebras](/leaderboard/codex/mcp/cerebras) |
| Observability | [Datadog](/leaderboard/codex/api/datadog) | [Datadog](/leaderboard/codex/cli/datadog) | [Datadog](/leaderboard/codex/mcp/datadog) |
| Graph Databases | [Neo4j](/leaderboard/codex/api/neo4j) | — | — |
| Auth | [WorkOS](/leaderboard/codex/api/workos) | [WorkOS](/leaderboard/codex/cli/workos) | [Descope](/leaderboard/codex/mcp/descope) |
| Browser | [Browserbase](/leaderboard/codex/api/browserbase) | [Browserbase](/leaderboard/codex/cli/browserbase) | [Anchor Browser](/leaderboard/codex/mcp/anchor-browser) |
| Geocoding | [OpenCageData](/leaderboard/codex/api/opencagedata) | — | [OpenCageData](/leaderboard/codex/mcp/opencagedata) |
| Webscraping | [fastCRW](/leaderboard/codex/api/fastcrw) | — | [fastCRW](/leaderboard/codex/mcp/fastcrw) |
| Voice TTS | [ElevenLabs](/leaderboard/codex/api/elevenlabs) | [ElevenLabs](/leaderboard/codex/cli/elevenlabs) | [ElevenLabs](/leaderboard/codex/mcp/elevenlabs) |
| Voice Infra | [LiveKit](/leaderboard/codex/api/livekit) | [LiveKit](/leaderboard/codex/cli/livekit) | [Pipecat](/leaderboard/codex/mcp/pipecat) |
| Durable Workflow | [Prefect](/leaderboard/codex/api/prefect) | [Temporal](/leaderboard/codex/cli/temporal) | [Prefect](/leaderboard/codex/mcp/prefect) |
| Sandboxes | [E2B](/leaderboard/codex/api/e2b) | [E2B](/leaderboard/codex/cli/e2b) | [Daytona](/leaderboard/codex/mcp/daytona) |
| Document Parsing | [Reducto](/leaderboard/codex/api/reducto) | [Extend.ai](/leaderboard/codex/cli/extend-ai) | [Extend.ai](/leaderboard/codex/mcp/extend-ai) |
| E-Signature | [Docusign](/leaderboard/codex/api/docusign) | — | — |
| Voice Telephony | [Twilio](/leaderboard/codex/api/twilio) | [Telnyx](/leaderboard/codex/cli/telnyx) | [Telnyx](/leaderboard/codex/mcp/telnyx) |
| Email | [Resend](/leaderboard/codex/api/resend) | [Resend](/leaderboard/codex/cli/resend) | [Agentmail](/leaderboard/codex/mcp/agentmail) |
| Unified API | [Apideck](/leaderboard/codex/api/apideck) | [Naive](/leaderboard/codex/cli/naive) | [Naive](/leaderboard/codex/mcp/naive) |
| Vector Databases | [Pinecone](/leaderboard/codex/api/pinecone) | [Pinecone](/leaderboard/codex/cli/pinecone) | [Qdrant](/leaderboard/codex/mcp/qdrant) |
| Cloud Hosting | [Render](/leaderboard/codex/api/render) | [Render](/leaderboard/codex/cli/render) | [Render](/leaderboard/codex/mcp/render) |
| Database | [Convex](/leaderboard/codex/api/convex) | — | [Convex](/leaderboard/codex/mcp/convex) |
| Neocloud | [Nebius AI Cloud](/leaderboard/codex/api/nebius-ai-cloud) | [Nebius AI Cloud](/leaderboard/codex/cli/nebius-ai-cloud) | — |
| Proxy | [Massive](/leaderboard/codex/api/massive) | — | [Massive](/leaderboard/codex/mcp/massive) |
| Video Agent | [Tavus](/leaderboard/codex/api/tavus) | — | — |
| Meeting Bot | [Recall.ai](/leaderboard/codex/api/recall-ai) | — | [MeetGeek](/leaderboard/codex/mcp/meetgeek) |
| Voice STT | [Deepgram](/leaderboard/codex/api/deepgram) | [Deepgram](/leaderboard/codex/cli/deepgram) | [Deepgram](/leaderboard/codex/mcp/deepgram) |
| Verification | [Surge](/leaderboard/codex/api/surge) | — | — |
| Stablecoin | [Kite](/leaderboard/codex/api/kite) | — | [Fireblocks](/leaderboard/codex/mcp/fireblocks) |
| CMS | [Strapi](/leaderboard/codex/api/strapi) | — | — |
| Code Review | [Macroscope](/leaderboard/codex/api/macroscope) | [Semgrep](/leaderboard/codex/cli/semgrep) | — |
| Talent Directory | [Roster](/leaderboard/codex/api/roster) | — | — |

## API, CLI, And MCP Chart Sections

The rendered Agent Landscape page ends with API, CLI, and MCP chart sections. Each section starts with the same overall chart used on the public arena pages, then repeats that chart by category. The model toggle switches Claude Code and Codex. Charts with no evaluated companies are omitted; in charts with evaluated companies, skipped rows remain visible as skipped rows.

| Surface | Agent | Rows | Scored | Skipped | Categories | Average Score | Avg Runtime | Avg Cost |
|---------|-------|------|--------|---------|------------|---------------|-------------|----------|
| API | Claude Code | 144 | 111 | 33 | 32 | 71 | 3m 47s | $0.39 |
| API | Codex | 144 | 114 | 30 | 32 | 67 | 3m 22s | $1.75 |
| CLI | Claude Code | 94 | 51 | 43 | 22 | 53 | 5m 23s | $0.26 |
| CLI | Codex | 56 | 52 | 4 | 20 | 55 | 4m 5s | $1.46 |
| MCP | Claude Code | 75 | 55 | 20 | 24 | 48 | 7m 13s | $0.46 |
| MCP | Codex | 74 | 51 | 23 | 24 | 53 | 6m 57s | $1.51 |

### Category Chart Data

Each row below corresponds to one category chart in the API, CLI, or MCP chart sections.

| Surface | Agent | Category | Rows | Scored | Skipped | Average Score | Current Leader |
|---------|-------|----------|------|--------|---------|---------------|----------------|
| API | Claude Code | Inference | 11 | 8 | 3 | 73 | [Fireworks AI](/leaderboard/claudecode/api/fireworks-ai) |
| API | Claude Code | Payment | 11 | 8 | 3 | 72 | [Stripe](/leaderboard/claudecode/api/stripe) |
| API | Claude Code | Sandboxes | 10 | 7 | 3 | 69 | [Daytona](/leaderboard/claudecode/api/daytona) |
| API | Claude Code | Search | 9 | 8 | 1 | 81 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) |
| API | Claude Code | Voice Telephony | 9 | 5 | 4 | 67 | [Telnyx](/leaderboard/claudecode/api/telnyx) |
| API | Claude Code | Durable Workflow | 8 | 3 | 5 | 77 | [Temporal](/leaderboard/claudecode/api/temporal) |
| API | Claude Code | Stablecoin | 7 | 5 | 2 | 58 | [DFNS](/leaderboard/claudecode/api/dfns) |
| API | Claude Code | Auth | 6 | 6 | 0 | 71 | [WorkOS](/leaderboard/claudecode/api/workos) |
| API | Claude Code | Vector Databases | 6 | 5 | 1 | 75 | [Chroma](/leaderboard/claudecode/api/chroma) |
| API | Claude Code | Voice STT | 6 | 4 | 2 | 73 | [Deepgram](/leaderboard/claudecode/api/deepgram) |
| API | Claude Code | Voice TTS | 6 | 6 | 0 | 77 | [ElevenLabs](/leaderboard/claudecode/api/elevenlabs) |
| API | Claude Code | Cloud Hosting | 5 | 3 | 2 | 61 | [Render](/leaderboard/claudecode/api/render) |
| API | Claude Code | Document Parsing | 5 | 5 | 0 | 73 | [Reducto](/leaderboard/claudecode/api/reducto) |
| API | Claude Code | Meeting Bot | 5 | 4 | 1 | 62 | [Meetstream](/leaderboard/claudecode/api/meetstream) |
| API | Claude Code | Voice Infra | 5 | 3 | 2 | 69 | [LiveKit](/leaderboard/claudecode/api/livekit) |
| API | Claude Code | Browser | 4 | 4 | 0 | 76 | [Anchor Browser](/leaderboard/claudecode/api/anchor-browser) |
| API | Claude Code | Graph Databases | 4 | 4 | 0 | 68 | [Neo4j](/leaderboard/claudecode/api/neo4j) |
| API | Claude Code | E-Signature | 3 | 3 | 0 | 70 | [PandaDoc](/leaderboard/claudecode/api/pandadoc) |
| API | Claude Code | Email | 3 | 3 | 0 | 62 | [Resend](/leaderboard/claudecode/api/resend) |
| API | Claude Code | Unified API | 3 | 3 | 0 | 73 | [Naive](/leaderboard/claudecode/api/naive) |
| API | Claude Code | Webscraping | 3 | 3 | 0 | 73 | [Scrapfly](/leaderboard/claudecode/api/scrapfly) |
| API | Claude Code | Observability | 2 | 2 | 0 | 72 | [Datadog](/leaderboard/claudecode/api/datadog) |
| API | Claude Code | Storage | 2 | 2 | 0 | 80 | [Box](/leaderboard/claudecode/api/box) |
| API | Claude Code | Verification | 2 | 2 | 0 | 64 | [Prelude](/leaderboard/claudecode/api/prelude) |
| API | Claude Code | Video Agent | 2 | 2 | 0 | 60 | [Tavus](/leaderboard/claudecode/api/tavus) |
| API | Claude Code | Geocoding | 1 | 1 | 0 | 83 | [OpenCageData](/leaderboard/claudecode/api/opencagedata) |
| API | Claude Code | Neocloud | 1 | 1 | 0 | 59 | [Nebius AI Cloud](/leaderboard/claudecode/api/nebius-ai-cloud) |
| API | Claude Code | Proxy | 1 | 1 | 0 | 65 | [Massive](/leaderboard/claudecode/api/massive) |
| API | Codex | Inference | 11 | 8 | 3 | 72 | [Fireworks AI](/leaderboard/codex/api/fireworks-ai) |
| API | Codex | Payment | 11 | 8 | 3 | 67 | [Stripe](/leaderboard/codex/api/stripe) |
| API | Codex | Sandboxes | 10 | 7 | 3 | 68 | [E2B](/leaderboard/codex/api/e2b) |
| API | Codex | Search | 9 | 8 | 1 | 80 | [Tavily](/leaderboard/codex/api/tavily) |
| API | Codex | Voice Telephony | 9 | 6 | 3 | 63 | [Twilio](/leaderboard/codex/api/twilio) |
| API | Codex | Durable Workflow | 8 | 3 | 5 | 74 | [Prefect](/leaderboard/codex/api/prefect) |
| API | Codex | Stablecoin | 7 | 5 | 2 | 46 | [Kite](/leaderboard/codex/api/kite) |
| API | Codex | Auth | 6 | 6 | 0 | 68 | [WorkOS](/leaderboard/codex/api/workos) |
| API | Codex | Vector Databases | 6 | 5 | 1 | 69 | [Pinecone](/leaderboard/codex/api/pinecone) |
| API | Codex | Voice STT | 6 | 4 | 2 | 48 | [Deepgram](/leaderboard/codex/api/deepgram) |
| API | Codex | Voice TTS | 6 | 6 | 0 | 74 | [ElevenLabs](/leaderboard/codex/api/elevenlabs) |
| API | Codex | Cloud Hosting | 5 | 3 | 2 | 51 | [Render](/leaderboard/codex/api/render) |
| API | Codex | Document Parsing | 5 | 5 | 0 | 59 | [Reducto](/leaderboard/codex/api/reducto) |
| API | Codex | Meeting Bot | 5 | 4 | 1 | 59 | [Recall.ai](/leaderboard/codex/api/recall-ai) |
| API | Codex | Voice Infra | 5 | 4 | 1 | 69 | [LiveKit](/leaderboard/codex/api/livekit) |
| API | Codex | Browser | 4 | 4 | 0 | 77 | [Browserbase](/leaderboard/codex/api/browserbase) |
| API | Codex | Graph Databases | 4 | 4 | 0 | 61 | [Neo4j](/leaderboard/codex/api/neo4j) |
| API | Codex | E-Signature | 3 | 3 | 0 | 69 | [Docusign](/leaderboard/codex/api/docusign) |
| API | Codex | Email | 3 | 3 | 0 | 71 | [Resend](/leaderboard/codex/api/resend) |
| API | Codex | Unified API | 3 | 3 | 0 | 65 | [Apideck](/leaderboard/codex/api/apideck) |
| API | Codex | Webscraping | 3 | 3 | 0 | 71 | [fastCRW](/leaderboard/codex/api/fastcrw) |
| API | Codex | Observability | 2 | 2 | 0 | 71 | [Datadog](/leaderboard/codex/api/datadog) |
| API | Codex | Storage | 2 | 2 | 0 | 81 | [Box](/leaderboard/codex/api/box) |
| API | Codex | Verification | 2 | 2 | 0 | 60 | [Surge](/leaderboard/codex/api/surge) |
| API | Codex | Video Agent | 2 | 2 | 0 | 64 | [Tavus](/leaderboard/codex/api/tavus) |
| API | Codex | Database | 1 | 1 | 0 | 72 | [Convex](/leaderboard/codex/api/convex) |
| API | Codex | Geocoding | 1 | 1 | 0 | 81 | [OpenCageData](/leaderboard/codex/api/opencagedata) |
| API | Codex | Neocloud | 1 | 1 | 0 | 65 | [Nebius AI Cloud](/leaderboard/codex/api/nebius-ai-cloud) |
| API | Codex | Proxy | 1 | 1 | 0 | 65 | [Massive](/leaderboard/codex/api/massive) |
| CLI | Claude Code | Payment | 10 | 1 | 9 | 77 | [Stripe](/leaderboard/claudecode/cli/stripe) |
| CLI | Claude Code | Inference | 8 | 3 | 5 | 34 | [OpenRouter](/leaderboard/claudecode/cli/openrouter) |
| CLI | Claude Code | Durable Workflow | 7 | 2 | 5 | 41 | [Temporal](/leaderboard/claudecode/cli/temporal) |
| CLI | Claude Code | Auth | 6 | 4 | 2 | 60 | [WorkOS](/leaderboard/claudecode/cli/workos) |
| CLI | Claude Code | Sandboxes | 6 | 5 | 1 | 56 | [E2B](/leaderboard/claudecode/cli/e2b) |
| CLI | Claude Code | Search | 6 | 4 | 2 | 84 | [Nimble](/leaderboard/claudecode/cli/nimbleway) |
| CLI | Claude Code | Vector Databases | 6 | 2 | 4 | 46 | [Pinecone](/leaderboard/claudecode/cli/pinecone) |
| CLI | Claude Code | Browser | 4 | 4 | 0 | 75 | [Steel](/leaderboard/claudecode/cli/steel) |
| CLI | Claude Code | Cloud Hosting | 4 | 3 | 1 | 30 | [Render](/leaderboard/claudecode/cli/render) |
| CLI | Claude Code | Code Review | 4 | 4 | 0 | 14 | [Semgrep](/leaderboard/claudecode/cli/semgrep) |
| CLI | Claude Code | Document Parsing | 4 | 4 | 0 | 63 | [Extend.ai](/leaderboard/claudecode/cli/extend-ai) |
| CLI | Claude Code | Email | 3 | 2 | 1 | 75 | [Agentmail](/leaderboard/claudecode/cli/agentmail) |
| CLI | Claude Code | Voice Infra | 3 | 1 | 2 | 89 | [LiveKit](/leaderboard/claudecode/cli/livekit) |
| CLI | Claude Code | Voice STT | 3 | 2 | 1 | 51 | [Deepgram](/leaderboard/claudecode/cli/deepgram) |
| CLI | Claude Code | Voice Telephony | 3 | 3 | 0 | 43 | [Twilio](/leaderboard/claudecode/cli/twilio) |
| CLI | Claude Code | Voice TTS | 3 | 3 | 0 | 44 | [Rime](/leaderboard/claudecode/cli/rime) |
| CLI | Claude Code | Neocloud | 1 | 1 | 0 | 42 | [Nebius AI Cloud](/leaderboard/claudecode/cli/nebius-ai-cloud) |
| CLI | Claude Code | Observability | 1 | 1 | 0 | 71 | [Datadog](/leaderboard/claudecode/cli/datadog) |
| CLI | Claude Code | Storage | 1 | 1 | 0 | 67 | [Box](/leaderboard/claudecode/cli/box) |
| CLI | Claude Code | Unified API | 1 | 1 | 0 | 47 | [Naive](/leaderboard/claudecode/cli/naive) |
| CLI | Codex | Sandboxes | 5 | 5 | 0 | 60 | [E2B](/leaderboard/codex/cli/e2b) |
| CLI | Codex | Auth | 4 | 4 | 0 | 53 | [WorkOS](/leaderboard/codex/cli/workos) |
| CLI | Codex | Browser | 4 | 4 | 0 | 72 | [Browserbase](/leaderboard/codex/cli/browserbase) |
| CLI | Codex | Cloud Hosting | 4 | 3 | 1 | 41 | [Render](/leaderboard/codex/cli/render) |
| CLI | Codex | Code Review | 4 | 4 | 0 | 12 | [Semgrep](/leaderboard/codex/cli/semgrep) |
| CLI | Codex | Document Parsing | 4 | 4 | 0 | 62 | [Extend.ai](/leaderboard/codex/cli/extend-ai) |
| CLI | Codex | Search | 4 | 4 | 0 | 83 | [Firecrawl](/leaderboard/codex/cli/firecrawl) |
| CLI | Codex | Vector Databases | 4 | 2 | 2 | 45 | [Pinecone](/leaderboard/codex/cli/pinecone) |
| CLI | Codex | Email | 3 | 2 | 1 | 74 | [Resend](/leaderboard/codex/cli/resend) |
| CLI | Codex | Inference | 3 | 3 | 0 | 45 | [OpenRouter](/leaderboard/codex/cli/openrouter) |
| CLI | Codex | Voice Telephony | 3 | 3 | 0 | 50 | [Telnyx](/leaderboard/codex/cli/telnyx) |
| CLI | Codex | Voice TTS | 3 | 3 | 0 | 47 | [ElevenLabs](/leaderboard/codex/cli/elevenlabs) |
| CLI | Codex | Durable Workflow | 2 | 2 | 0 | 59 | [Temporal](/leaderboard/codex/cli/temporal) |
| CLI | Codex | Voice Infra | 2 | 2 | 0 | 43 | [LiveKit](/leaderboard/codex/cli/livekit) |
| CLI | Codex | Voice STT | 2 | 2 | 0 | 70 | [Deepgram](/leaderboard/codex/cli/deepgram) |
| CLI | Codex | Neocloud | 1 | 1 | 0 | 39 | [Nebius AI Cloud](/leaderboard/codex/cli/nebius-ai-cloud) |
| CLI | Codex | Observability | 1 | 1 | 0 | 73 | [Datadog](/leaderboard/codex/cli/datadog) |
| CLI | Codex | Payment | 1 | 1 | 0 | 73 | [Stripe](/leaderboard/codex/cli/stripe) |
| CLI | Codex | Storage | 1 | 1 | 0 | 64 | [Box](/leaderboard/codex/cli/box) |
| CLI | Codex | Unified API | 1 | 1 | 0 | 73 | [Naive](/leaderboard/codex/cli/naive) |
| MCP | Claude Code | Search | 8 | 7 | 1 | 78 | [Exa](/leaderboard/claudecode/mcp/exa) |
| MCP | Claude Code | Payment | 7 | 5 | 2 | 39 | [Stripe](/leaderboard/claudecode/mcp/stripe) |
| MCP | Claude Code | Voice Telephony | 7 | 3 | 4 | 42 | [Plivo](/leaderboard/claudecode/mcp/plivo) |
| MCP | Claude Code | Auth | 6 | 4 | 2 | 58 | [Descope](/leaderboard/claudecode/mcp/descope) |
| MCP | Claude Code | Vector Databases | 6 | 6 | 0 | 56 | [LanceDB](/leaderboard/claudecode/mcp/lancedb) |
| MCP | Claude Code | Inference | 5 | 2 | 3 | 22 | [Cerebras](/leaderboard/claudecode/mcp/cerebras) |
| MCP | Claude Code | Cloud Hosting | 4 | 2 | 2 | 60 | [Render](/leaderboard/claudecode/mcp/render) |
| MCP | Claude Code | Sandboxes | 4 | 2 | 2 | 38 | [E2B](/leaderboard/claudecode/mcp/e2b) |
| MCP | Claude Code | Email | 3 | 3 | 0 | 32 | [Resend](/leaderboard/claudecode/mcp/resend) |
| MCP | Claude Code | Meeting Bot | 3 | 3 | 0 | 35 | [MeetGeek](/leaderboard/claudecode/mcp/meetgeek) |
| MCP | Claude Code | Stablecoin | 3 | 3 | 0 | 20 | [BlindPay](/leaderboard/claudecode/mcp/blindpay) |
| MCP | Claude Code | Voice TTS | 3 | 3 | 0 | 70 | [ElevenLabs](/leaderboard/claudecode/mcp/elevenlabs) |
| MCP | Claude Code | Document Parsing | 2 | 2 | 0 | 75 | [Extend.ai](/leaderboard/claudecode/mcp/extend-ai) |
| MCP | Claude Code | Durable Workflow | 2 | 1 | 1 | 63 | [Prefect](/leaderboard/claudecode/mcp/prefect) |
| MCP | Claude Code | Voice Infra | 2 | 1 | 1 | 26 | [LiveKit](/leaderboard/claudecode/mcp/livekit) |
| MCP | Claude Code | Webscraping | 2 | 2 | 0 | 33 | [fastCRW](/leaderboard/claudecode/mcp/fastcrw) |
| MCP | Claude Code | Database | 1 | 1 | 0 | 22 | [Convex](/leaderboard/claudecode/mcp/convex) |
| MCP | Claude Code | Observability | 1 | 1 | 0 | 15 | [Datadog](/leaderboard/claudecode/mcp/datadog) |
| MCP | Claude Code | Proxy | 1 | 1 | 0 | 14 | [Massive](/leaderboard/claudecode/mcp/massive) |
| MCP | Claude Code | Storage | 1 | 1 | 0 | 80 | [Box](/leaderboard/claudecode/mcp/box) |
| MCP | Claude Code | Unified API | 1 | 1 | 0 | 16 | [Naive](/leaderboard/claudecode/mcp/naive) |
| MCP | Claude Code | Voice STT | 1 | 1 | 0 | 20 | [Deepgram](/leaderboard/claudecode/mcp/deepgram) |
| MCP | Codex | Search | 8 | 7 | 1 | 75 | [Exa](/leaderboard/codex/mcp/exa) |
| MCP | Codex | Payment | 7 | 4 | 3 | 57 | [Stripe](/leaderboard/codex/mcp/stripe) |
| MCP | Codex | Voice Telephony | 7 | 3 | 4 | 52 | [Telnyx](/leaderboard/codex/mcp/telnyx) |
| MCP | Codex | Vector Databases | 6 | 5 | 1 | 44 | [Qdrant](/leaderboard/codex/mcp/qdrant) |
| MCP | Codex | Auth | 5 | 4 | 1 | 49 | [Descope](/leaderboard/codex/mcp/descope) |
| MCP | Codex | Inference | 5 | 2 | 3 | 28 | [Cerebras](/leaderboard/codex/mcp/cerebras) |
| MCP | Codex | Cloud Hosting | 4 | 2 | 2 | 60 | [Render](/leaderboard/codex/mcp/render) |
| MCP | Codex | Sandboxes | 4 | 2 | 2 | 51 | [Daytona](/leaderboard/codex/mcp/daytona) |
| MCP | Codex | Email | 3 | 3 | 0 | 54 | [Agentmail](/leaderboard/codex/mcp/agentmail) |
| MCP | Codex | Meeting Bot | 3 | 3 | 0 | 36 | [MeetGeek](/leaderboard/codex/mcp/meetgeek) |
| MCP | Codex | Voice TTS | 3 | 3 | 0 | 58 | [ElevenLabs](/leaderboard/codex/mcp/elevenlabs) |
| MCP | Codex | Document Parsing | 2 | 2 | 0 | 77 | [Extend.ai](/leaderboard/codex/mcp/extend-ai) |
| MCP | Codex | Durable Workflow | 2 | 1 | 1 | 47 | [Prefect](/leaderboard/codex/mcp/prefect) |
| MCP | Codex | Voice Infra | 2 | 2 | 0 | 36 | [Pipecat](/leaderboard/codex/mcp/pipecat) |
| MCP | Codex | Webscraping | 2 | 2 | 0 | 80 | [fastCRW](/leaderboard/codex/mcp/fastcrw) |
| MCP | Codex | Database | 1 | 1 | 0 | 20 | [Convex](/leaderboard/codex/mcp/convex) |
| MCP | Codex | Observability | 1 | 1 | 0 | 48 | [Datadog](/leaderboard/codex/mcp/datadog) |
| MCP | Codex | Proxy | 1 | 1 | 0 | 41 | [Massive](/leaderboard/codex/mcp/massive) |
| MCP | Codex | Storage | 1 | 1 | 0 | 73 | [Box](/leaderboard/codex/mcp/box) |
| MCP | Codex | Unified API | 1 | 1 | 0 | 15 | [Naive](/leaderboard/codex/mcp/naive) |
| MCP | Codex | Voice STT | 1 | 1 | 0 | 29 | [Deepgram](/leaderboard/codex/mcp/deepgram) |

## Leaders By API, CLI, MCP, And Overall

Overall includes companies scored by both agents across API, CLI, and MCP. API, CLI, and MCP include companies scored by both agents on that interface.

### Overall

Both agents across API, CLI, and MCP.

| Rank | Company | Category | Avg Score | Rows | Avg Runtime | Avg Errors |
|------|---------|----------|-----------|------|-------------|------------|
| 1 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) | Search | 86 | 6 | 2m 26s | 0.0 |
| 2 | [Tavily](/leaderboard/claudecode/api/tavily) | Search | 83 | 6 | 1m 20s | 0.3 |
| 3 | [Nimble](/leaderboard/claudecode/api/nimbleway) | Search | 82 | 6 | 1m 42s | 0.0 |
| 4 | [Jina AI](/leaderboard/claudecode/api/jina-ai) | Search | 81 | 6 | 2m 28s | 0.5 |
| 5 | [Stripe](/leaderboard/claudecode/api/stripe) | Payment | 79 | 6 | 2m 51s | 1.0 |
| 6 | [Box](/leaderboard/claudecode/api/box) | Storage | 77 | 6 | 3m 9s | 0.8 |

### API

Claude Code + Codex.

| Rank | Company | Category | Avg Score | Rows | Avg Runtime | Avg Errors |
|------|---------|----------|-----------|------|-------------|------------|
| 1 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) | Search | 90 | 2 | 1m 13s | 0.0 |
| 2 | [Box](/leaderboard/claudecode/api/box) | Storage | 89 | 2 | 1m 2s | 0.0 |
| 3 | [Tavily](/leaderboard/claudecode/api/tavily) | Search | 86 | 2 | 1m 2s | 0.5 |
| 4 | [TinyFish](/leaderboard/claudecode/api/tinyfish) | Search | 86 | 2 | 1m 24s | 0.5 |
| 5 | [Fireworks AI](/leaderboard/claudecode/api/fireworks-ai) | Inference | 86 | 2 | 3m 1s | 0.0 |
| 6 | [Stripe](/leaderboard/claudecode/api/stripe) | Payment | 85 | 2 | 1m 4s | 1.0 |

### CLI

Claude Code + Codex.

| Rank | Company | Category | Avg Score | Rows | Avg Runtime | Avg Errors |
|------|---------|----------|-----------|------|-------------|------------|
| 1 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) | Search | 86 | 2 | 1m 43s | 0.0 |
| 2 | [Nimble](/leaderboard/claudecode/api/nimbleway) | Search | 86 | 2 | 1m 15s | 0.0 |
| 3 | [LiveKit](/leaderboard/claudecode/api/livekit) | Voice Infra | 86 | 2 | 2m 14s | 0.0 |
| 4 | [Tavily](/leaderboard/claudecode/api/tavily) | Search | 81 | 2 | 1m 21s | 0.0 |
| 5 | [WorkOS](/leaderboard/claudecode/api/workos) | Auth | 81 | 2 | 2m 59s | 0.5 |
| 6 | [Jina AI](/leaderboard/claudecode/api/jina-ai) | Search | 80 | 2 | 2m 29s | 0.0 |

### MCP

Claude Code + Codex.

| Rank | Company | Category | Avg Score | Rows | Avg Runtime | Avg Errors |
|------|---------|----------|-----------|------|-------------|------------|
| 1 | [Exa](/leaderboard/claudecode/api/exa) | Search | 90 | 2 | 2m 50s | 0.0 |
| 2 | [Jina AI](/leaderboard/claudecode/api/jina-ai) | Search | 86 | 2 | 2m 57s | 0.0 |
| 3 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) | Search | 81 | 2 | 4m 20s | 0.0 |
| 4 | [Tavily](/leaderboard/claudecode/api/tavily) | Search | 81 | 2 | 1m 36s | 0.5 |
| 5 | [ElevenLabs](/leaderboard/claudecode/api/elevenlabs) | Voice TTS | 81 | 2 | 3m 48s | 1.0 |
| 6 | [Nimble](/leaderboard/claudecode/api/nimbleway) | Search | 79 | 2 | 2m 42s | 0.0 |

## API Company Leaderboard

Top API companies by blended Claude Code and Codex API benchmark score.

| Rank | Company | Category | Score | Rows |
|------|---------|----------|-------|------|
| 1 | [Firecrawl](/leaderboard/claudecode/api/firecrawl) | Search | 90 | 2 |
| 2 | [Box](/leaderboard/claudecode/api/box) | Storage | 89 | 2 |
| 3 | [TinyFish](/leaderboard/claudecode/api/tinyfish) | Search | 86 | 2 |
| 4 | [Tavily](/leaderboard/claudecode/api/tavily) | Search | 86 | 2 |
| 5 | [Fireworks AI](/leaderboard/claudecode/api/fireworks-ai) | Inference | 86 | 2 |
| 6 | [Stripe](/leaderboard/claudecode/api/stripe) | Payment | 85 | 2 |
| 7 | [Datadog](/leaderboard/claudecode/api/datadog) | Observability | 84 | 2 |
| 8 | [ElevenLabs](/leaderboard/claudecode/api/elevenlabs) | Voice TTS | 83 | 2 |
| 9 | [OpenCageData](/leaderboard/claudecode/api/opencagedata) | Geocoding | 82 | 2 |
| 10 | [Nimble](/leaderboard/claudecode/api/nimbleway) | Search | 81 | 2 |

## Categories Sensitive To Agent Choice

Large gaps usually point to ambiguous docs, unusual auth flows, or task paths that one agent can recover from better than another. Categories with fewer than 6 rows are filtered out when possible.

| Category | Claude Code | Codex | Leader | Gap | Rows |
|----------|-------------|-------|--------|-----|------|
| Voice STT | 55 | 39 | Claude Code | 16 | 12 |
| Document Parsing | 73 | 59 | Claude Code | 14 | 10 |
| Stablecoin | 46 | 37 | Claude Code | 9 | 14 |
| Unified API | 73 | 65 | Claude Code | 9 | 6 |
| Email | 62 | 71 | Codex | 8 | 6 |
| Graph Databases | 68 | 61 | Claude Code | 8 | 8 |
| Voice Infra | 51 | 58 | Codex | 7 | 10 |
| Cloud Hosting | 48 | 42 | Claude Code | 6 | 10 |
| Vector Databases | 67 | 62 | Claude Code | 5 | 12 |
| Voice Telephony | 45 | 49 | Codex | 4 | 18 |
| Payment | 57 | 53 | Claude Code | 4 | 22 |
| Voice TTS | 77 | 74 | Claude Code | 3 | 12 |

## Category Market Leaders

API category leaders, closest challengers, and category lock-in.

| Category | Leader | Challenger | Gap | Companies |
|----------|--------|------------|-----|-----------|
| Observability | [Datadog](/leaderboard/claudecode/api/datadog) (84) | BetterStack (60) | 24 | 2 |
| Cloud Hosting | [Render](/leaderboard/claudecode/api/render) (74) | Railway (52) | 22 | 5 |
| Storage | [Box](/leaderboard/claudecode/api/box) (89) | Dropbox (72) | 17 | 2 |
| Graph Databases | [Neo4j](/leaderboard/claudecode/api/neo4j) (81) | Memgraph (67) | 14 | 4 |
| Voice Infra | [LiveKit](/leaderboard/claudecode/api/livekit) (80) | Agora (69) | 11 | 5 |
| Document Parsing | [Reducto](/leaderboard/claudecode/api/reducto) (80) | Extend.ai (73) | 8 | 5 |
| Payment | [Stripe](/leaderboard/claudecode/api/stripe) (85) | Mollie (78) | 8 | 11 |
| Inference | [Fireworks AI](/leaderboard/claudecode/api/fireworks-ai) (86) | OpenRouter (79) | 7 | 11 |
| Meeting Bot | [Meetstream](/leaderboard/claudecode/api/meetstream) (67) | Meeting BaaS (61) | 6 | 5 |
| Auth | [WorkOS](/leaderboard/claudecode/api/workos) (79) | Scalekit (74) | 5 | 6 |
| Voice TTS | [ElevenLabs](/leaderboard/claudecode/api/elevenlabs) (83) | Resemble AI (79) | 5 | 6 |
| Vector Databases | [Chroma](/leaderboard/claudecode/api/chroma) (78) | Qdrant (73) | 5 | 6 |
| Webscraping | [fastCRW](/leaderboard/claudecode/api/fastcrw) (76) | Diffbot (71) | 5 | 3 |
| Search | [Firecrawl](/leaderboard/claudecode/api/firecrawl) (90) | TinyFish (86) | 4 | 9 |
| Voice STT | [Deepgram](/leaderboard/claudecode/api/deepgram) (71) | AssemblyAI (67) | 4 | 6 |

## Agent Effort And Cost

Average cost, runtime, tool calls, and errors on API company evals.

| Agent | Score | Avg Cost | Avg Runtime | Avg Tool Calls | Avg Errors | Rows |
|-------|-------|----------|-------------|----------------|------------|------|
| Claude Code | 59 | $0.39 | 3m 47s | 18 | 4 | 144 |
| Codex | 57 | $1.75 | 3m 22s | 17 | 3 | 144 |

## Friction Hotspots

API categories where agents spend the most effort recovering: more errors, longer runs, more tool calls, and higher cost.

| Category | Score | Avg Errors | Avg Runtime | Avg Cost | Avg Tool Calls | Rows |
|----------|-------|------------|-------------|----------|----------------|------|
| Email | 67 | 10 | 5m 43s | $1.69 | 35 | 6 |
| Stablecoin | 41 | 7 | 5m 42s | $2.18 | 29 | 14 |
| Auth | 69 | 6 | 4m 31s | $1.25 | 29 | 12 |
| Voice Infra | 54 | 6 | 5m 16s | $1.90 | 22 | 10 |
| Meeting Bot | 49 | 6 | 4m 28s | $0.87 | 17 | 10 |
| Sandboxes | 56 | 5 | 3m 54s | $1.61 | 17 | 20 |
| Voice Telephony | 47 | 5 | 6m 29s | $2.23 | 21 | 18 |
| Graph Databases | 64 | 5 | 3m 3s | $1.04 | 27 | 8 |
| Cloud Hosting | 45 | 5 | 7m 24s | $2.54 | 23 | 10 |
| Document Parsing | 66 | 5 | 3m 25s | $0.92 | 23 | 10 |
| Unified API | 69 | 3 | 3m 23s | $1.42 | 22 | 6 |
| E-Signature | 70 | 3 | 2m 21s | $0.91 | 21 | 6 |

## Compare

Compare companies side by side at [/leaderboard/claudecode/api/compare](/leaderboard/claudecode/api/compare). Use `/leaderboard/{model}/{interface}/{company}` for individual provider details.

View the rest of the DevTool Arena results at [/leaderboard/claudecode/api](/leaderboard/claudecode/api).

## Frequently Asked Questions

### What does the discovery score measure?

The discovery score measures whether key agent-ready resources, such as llms.txt, Context7, MCP server documentation, typed SDKs, OpenAPI specs, agent skills, and CLI support, exist and are publicly available. Our methodology verifies the presence and accessibility of these resources; it is not a live test of whether an AI agent can independently find or use them in a task.

As a result, a company may score well on discovery because these assets are publicly available, even if an agent would not reliably find them in every real-world workflow.

### What does the eval score measure?

The eval score measures how well an AI coding agent can complete a real integration task using a company's API. We give the agent a practical prompt, such as generating a script, running it, and verifying the output, to see whether it can actually get the job done.

We then evaluate performance across the full workflow: finding the right docs, generating valid code, creating the necessary files, and executing the task successfully end to end.

We also capture supporting signals such as runtime, cost, tool calls, errors, and final execution outcome. The goal of the eval score is to measure real-world agent performance, not just theoretical API readiness.

### How is the final leaderboard score calculated?

The final leaderboard score combines the eval score and discovery score. The API leaderboard weights task execution at 70% and discovery at 30%, so agent-ready resources help the score, but successful end-to-end execution matters most.

